DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Amendments
Applicant’s Amendment filed on 5/11/2026 has been entered and made of record.
Currently Pending claims: 1-20
Independent claims: 1 and 11
Amended claims: 1, 3, 5, 10, 11, 13, and 15
Response to Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an
Amendment received on 5/11/2026.
Applicant’s arguments, see page 10, filed 5/11/2026, with respect to objections of the specifications have been fully considered and are persuasive. The objection of the specification has been withdrawn.
Applicant’s arguments, see page 10, filed 5/11/2026, with respect to objections of claims 5 and 15 have been fully considered and are persuasive. The objections of claims 5 and 15 have been withdrawn.
Applicant’s arguments, see page 10, filed 5/11/2026, with respect to rejections under 35 U.S.C. § 112(b) of claims 3 and 13 have been fully considered and are persuasive. The rejections under 35 U.S.C. § 112(b) of claims 3 and 13 have been withdrawn.
Applicant’s arguments, see page 10-17, filed 5/11/2026, with respect to rejections under 35 U.S.C. § 101 of claims 1-20 have been fully considered and are persuasive. The rejections under 35 U.S.C. § 101 of claims 1-20 have been withdrawn.
Applicant's arguments, see pages 17-20, filed on 5/11/2026, with respect to rejections under 35 U.S.C. § 103 of claims 1-20 have been fully considered but they are not persuasive. Applicant argues on pages 17-20:
“Unlike Zhang (IEEE), which uses a LIDAR-based processing, Zhang (518) simply uses an image sensor 111 to "capture the images of the object at two different time points for the processor 120 to determine whether the object is a movable object in motion or not." Zhang (518), paragraph [0047]. Thus, Zhang (518)'s image-based method cannot help one of ordinary skill in the art to modify Zhang ([IEEE])'s LIDAR-based features, such as LIDAR-based points, Bayesian Filtering, probability, and the like. Indeed, even if combined, the alleged combination fails to teach or suggest at least "determine, via processing of a point cloud acquired by the sensor, an object in a first frame; ... determine a point representing the object in the first frame based on a representative moving direction of the object, wherein the representative moving direction is one of: ... output, based on a first position of the point in the first frame and a second position of the point in at least one frame before the first frame, a signal indicating whether the object is a moving object or a movable stationary object," as recite in present claim 1.”
The Examiner respectfully disagrees. Zhang (518) discloses that the image sensor is inclusive of LiDAR sensors at ¶0037, “the image sensor 111 may be a general camera, and the distance sensor 112 may be one or a combination of a depth camera (or RGBD camera), a LiDAR (Light Laser Detection and Ranging), an ultrasonic sensor and an infrared sensor, but the invention is not limited thereto.” Further, even if Zhang (518) had not explicitly disclosed the sensor being a LiDAR sensor, unless Zhang (518) explicitly discloses that its method is incompatible with LiDAR sensors, it would be reasonable to combine Zhang (518) with Zhang (IEEE) as Zhang (518) is only relied upon for the method of determining a moving object. The specific implementation using LiDAR data in place of RGB data would be obvious to one of ordinary skill in the art. The second half of the applicant’s argument, regarding the combination of the two references failing to teach or suggest the quoted sections claim 1 fails to comply with 37 CFR 1.111(b) because it amounts to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claim patentably distinguishes it from the references. Therefore, claims 1 and 11 are rejected using the same references cited previously, however, as necessitated by amendment.
Arguments regarding claims 2-10 and 12-20 rely on their dependencies and thus are considered moot. Therefore, claims 2-10 and 12-20 are rejected accordingly due to their dependencies.
Positive Statement Regarding - 35 USC § 101
The Examiner’s 35 U.S.C. 101 analysis recognizes that the claimed subject matter is directed to a practical application of a technical solution. The claimed elements, taken as a whole, recite specific steps describing the implementation of computer-based method for detecting object motion in a manner different from what a human would ordinarily do. Because the claims recite specific, claimed steps and structural elements that produce a tangible technical result, they are not directed to an abstract idea absent additional inventive concept limitations. Accordingly, the record supports a positive 101 determination for the present claims.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”).
Regarding claim 1, Zhang (IEEE) discloses an object recognition apparatus comprising: a sensor associated with a vehicle (Page 7, §A. Data Collection, Our AV is equipped with a Velodyne HDL-64E LIDAR, 3 external cameras and two GPS receivers on the roof); and a processor (Page 8, §A. Data Collection, All the experiments was processed on an Intel i7-4700, 3.20 GHz core processor) configured to: determine, via processing of a point cloud acquired by the sensor (Fig. 2; Fig. 3A caption, LIDAR point returns from the lower portion of a target vehicle; Page 3, §Pose Estimation, the vehicle point cloud), an object in a first frame (Page 3, §II.Data Pre-Processing for 3D Point Cloud, … Measurement points in [the] current frame… If the area of the roughly rectangular bounding box of the moving cluster satisfies the preset threshold, moving cluster will be classified as a moving vehicle. Examiner considers the current frame as the “first frame” and the moving vehicle as the “object”); determine a first moving direction of the object in the first frame (Page 3, §III. Pose Estimation, Here we address the core problem of pose estimation, namely how to estimate the target-vehicle center position and heading angle. Examiner considers the heading angle “the first moving direction”); determine a reliability value of the first moving direction (Eqn. 30; Page 7, §B. The Bayesian Filtering Component, The probability that the driving behavior belongs to the turning class can be denoted by the parameter ξ. The output of the BF component is the expected value of ξ. Examiner considers the expected value of ξ “a reliability value”); determine a point representing the object in the first frame based on a representative moving direction of the object (Page 4, right column, last paragraph, §III. Pose Estimation, In this way, the approximate estimation of vehicle pose (x, y, θ) is determined based on the vehicle point cloud and the vehicle motion. Examiner considers (x,y) to be a point representing the object), wherein the representative moving direction is one of: the first moving direction based on the reliability value being greater than a threshold value (Page 7, paragraph after eqn. 32, §B. The Bayesian Filtering Component, Given E (ξ | y ) and time t, the HMM–BF algorithm outputs the final behavior classification based on the specified threshold τbf . The driving behavior at time t is classified as turning if E (ξ | y ) > τbf. Since the limitation is recited in the alternative, Examiner considers this citation to disclose the entire limitation), or a second moving direction of the object in a second frame preceding the first frame based on the reliability value being less than or equal to the threshold value; [output, based on a first position of the point in the first frame and a second position of the point in at least one frame before the first frame, a signal indicating whether the object is a moving object or a movable stationary object; and control, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation] of the vehicle (Page 7, §A. Data Collection, our autonomous vehicle) [according to an identification of the object].
However, Zhang (IEEE) fails to disclose output, based on a first position of the point in the first frame and a second position of the point in at least one frame before the first frame, a signal indicating whether the object is a moving object or a movable stationary object; and control, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation according to an identification of the object.
Zhang (518) teaches output, based on a first position of the point in the first frame (Fig. 6B. Examiner considers any of the ends of the line segments on the ball the “the first position of the point”) and a second position of the point in at least one frame before the first frame (Fig. 6A. Examiner considers the corresponding point to the first point in Fig. 6B as “the second position of the point”), a signal indicating whether the object is a moving object or a movable stationary object (¶0047, To determine whether the object is a movable object in motion or not…Specifically, the processor 120 obtains distances between the object (ball) and a plurality of feature points in the image from the image shown in FIG. 6A. … Then, the processor 120 obtains distances between the object (ball) and the same feature points from the image shown in FIG. 6B, and determines whether the distances between the object (ball) and the plurality of feature points have changed at the two time points; if so, it is determined that the object (ball) is a movable object in motion; and otherwise, it is determined that the object (ball) is a static object. ¶0052, After the processor 120 determines whether the object is a movable object according to the above-mentioned embodiments, if the object is on an advancing path of the autonomous mobile device 10, the autonomous mobile device selectively performs obstacle avoidance by different obstacle avoidance distances according to whether the object is a movable object. Since the autonomous mobile device makes a decision based on the determination, a signal indicating whether the object is moving must be output); and control, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation according to an identification of the object (¶0052, After the processor 120 determines whether the object is a movable object according to the above-mentioned embodiments, if the object is on an advancing path of the autonomous mobile device 10, the autonomous mobile device selectively performs obstacle avoidance by different obstacle avoidance distances according to whether the object is a movable object. Examiner considers obstacle avoidance as a driving operation. Since the autonomous mobile device makes a decision based on the determination, a signal indicating whether the object is moving must be output).
Both Zhang (IEEE) and Zhang (518) are analogous to the claimed invention because Zhang (IEEE) is in the field of vehicle systems for detecting external objections and motion and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the output signal of Zhang (518) into vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to prevent potential damage caused by a collision as suggested by Zhang (518) at, ¶0035, to avoid damage to people or machines caused by an excessively small obstacle avoidance distance.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) with the teachings of Zhang (518) to obtain the invention as specified in claim 1.
Regarding claim 11, Zhang (IEEE) discloses an object recognition method performed by a processor (Page 8, §A. Data Collection, All the experiments was processed on an Intel i7-4700, 3.20 GHz core processor), the method comprising: determining, via a point cloud acquired by sensor associated with a vehicle (Page 7, §A. Data Collection, Our AV is equipped with a Velodyne HDL-64E LIDAR, 3 external cameras and two GPS receivers on the roof; Page 3, §Pose Estimation, the vehicle point cloud), an object in a first frame (Page 3, §II. Data Pre-Processing for 3D Point Cloud, … Measurement points in [the] current frame… If the area of the roughly rectangular bounding box of the moving cluster satisfies the preset threshold, moving cluster will be classified as a moving vehicle. Examiner considers the current frame as the “first frame” and the moving vehicle as the “object”); determining a first moving direction of the object in the first frame (Page 3, §III. Pose Estimation, Here we address the core problem of pose estimation, namely how to estimate the target-vehicle center position and heading angle. Examiner considers the heading angle “the first moving direction”); determining a reliability value of the first moving direction (Eqn. 30; Page 7, §B. The Bayesian Filtering Component, The probability that the driving behavior belongs to the turning class can be denoted by the parameter ξ. The output of the BF component is the expected value of ξ. Examiner considers the expected value of ξ “a reliability value”); determining a point representing the object in the first frame based on a representative moving direction of the object (Page 4, right column, last paragraph, §III. Pose Estimation, In this way, the approximate estimation of vehicle pose (x, y, θ) is determined based on the vehicle point cloud and the vehicle motion. Examiner considers (x,y) to be a point representing the object), wherein the representative moving direction is one of: the first moving direction based on the reliability value being greater than a threshold value (Page 7, paragraph after eqn. 32, §B. The Bayesian Filtering Component, Given E (ξ | y ) and time t, the HMM–BF algorithm outputs the final behavior classification based on the specified threshold τbf . The driving behavior at time t is classified as turning if E (ξ | y ) > τbf. Since the limitation is recited in the alternative, Examiner considers this citation to disclose the entire limitation), or a second moving direction of the object in a second frame preceding the first frame based on the reliability value being less than or equal to the threshold value; [and outputting, based on a first position of the point in the first frame and a second position of the point in at least one frame before the first frame, a signal indicating whether the object is a moving object or a movable stationary object; and controlling, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation] of the vehicle (Page 7, §A. Data Collection, our autonomous vehicle) [according to an identification of the object].
However, Zhang (IEEE) fails to disclose outputting, based on a first position of the point in the first frame and a second position of the point in at least one frame before the first frame, a signal indicating whether the object is a moving object or a movable stationary object and controlling, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation according to an identification of the object.
Zhang (518) teaches outputting, based on a first position of the point in the first frame (Fig. 6B. Examiner considers any of the ends of the line segments on the ball the “the first position of the point”) and a second position of the point in at least one frame before the first frame (Fig. 6A. Examiner considers the corresponding point to the first point in Fig. 6B as “the second position of the point”), a signal indicating whether the object is a moving object or a movable stationary object (¶0047, To determine whether the object is a movable object in motion or not…Specifically, the processor 120 obtains distances between the object (ball) and a plurality of feature points in the image from the image shown in FIG. 6A. … Then, the processor 120 obtains distances between the object (ball) and the same feature points from the image shown in FIG. 6B, and determines whether the distances between the object (ball) and the plurality of feature points have changed at the two time points; if so, it is determined that the object (ball) is a movable object in motion; and otherwise, it is determined that the object (ball) is a static object. ¶0052, After the processor 120 determines whether the object is a movable object according to the above-mentioned embodiments, if the object is on an advancing path of the autonomous mobile device 10, the autonomous mobile device selectively performs obstacle avoidance by different obstacle avoidance distances according to whether the object is a movable object. Since the robot makes a decision based on the determination, a signal indicating whether the object is moving must be output); and controlling, based on the signal indicating whether the object is a moving object or a movable stationary object, a driving operation according to an identification of the object (¶0052, After the processor 120 determines whether the object is a movable object according to the above-mentioned embodiments, if the object is on an advancing path of the autonomous mobile device 10, the autonomous mobile device selectively performs obstacle avoidance by different obstacle avoidance distances according to whether the object is a movable object. Examiner considers obstacle avoidance as a driving operation. Since the autonomous mobile device makes a decision based on the determination, a signal indicating whether the object is moving must be output).
Both Zhang (IEEE) and Zhang (518) are analogous to the claimed invention because Zhang (IEEE) is in the field of vehicle systems for detecting external objections and motion and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the output signal of Zhang (518) into vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to prevent potential damage caused by a collision as suggested by Zhang (518) at, ¶0035, to avoid damage to people or machines caused by an excessively small obstacle avoidance distance.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) with the teachings of Zhang (518) to obtain the invention as specified in claim 11.
Claims 2, 4, 7, 12, 14, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Liu et al. (2019, “Fast Dynamic Vehicle Detection in Road Scenarios Based on Pose Estimation with Convex-Hull Model”, Sensors, 19, 3136) (hereafter, “Liu”).
Regarding claim 2, in which claim 1 is incorporated, Zhang (IEEE) discloses wherein the processor is configured to [determine the point by]: determining an object box representing the object in the first frame (Fig. 3, top-left panel, box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); [determining, based on the representative moving direction, a line segment associated with the object box; and determining the point further based on the line segment]
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determine the point and determining, based on the representative moving direction, a line segment associated with the object box; and determining the point further based on the line segment.
Liu teaches determine the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and determining, based on the representative moving direction, a line segment associated with the object box (Fig. 3, 4; Page 6, §2.2 Position Inference, yv points to the moving direction of target vehicle…the vectors that point from the center of model to the center of each side constitute a normal vector set, and the vectors that point from the center of each side to the origin of the Lidar constitute the orientation vector set. For each edge, the angle between the orientation vector and normal vector show whether the edge can be seen under the perspective of the Lidar; Page 7, §2.2 Position Inference, Lines p1p2 and p2p3 are the two visible edges. As yv contributes to the normal vector set and line p1p2 is determined via the normal vector and orientation vector set, Examiner considers the determination as “based on the representative moving direction” and p1p2 as “line segment associated with the object box”); and determining the point further based on the line segment (Page 7, Eqn. 9, 10. The coordinates for the point C is based off of p1p2).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, The proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 2.
Regarding claim 4, in which claim 1 is incorporated, Zhang (IEEE) discloses wherein the processor is configured to [determine the point] by: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); [assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box; and determining the point, further based on the plurality of indices].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determine the point and assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box; and determining the point, further based on the plurality of indices.
Liu teaches determine the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box (Fig. 4. Examiner considers p1-p4 as indices); and determining the point, further based on the plurality of indices (Page 7, Eqn. 9, 10. The coordinates for the point C is based off of p1p2 which is defined by a “plurality of indices”).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, The proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 4.
Regarding claim 7, in which claim 1 is incorporated, Zhang (IEEE) discloses wherein the processor is configured to [determine the point] by: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); and [determining the point based on a center point of one line segment among line segments constituting the object box].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determine the point and determining the point based on a center point of one line segment among line segments constituting the object box.
Liu teaches determine the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and determining the point based on a center point of one line segment among line segments constituting the object box (Fig. 3; Page 7, Eqn. 9, 10; Page 6, §2.2 Position Inference, yv points to the moving direction of target vehicle…the vectors that point from the center of model to the center of each side constitute a normal vector set, and the vectors that point from the center of each side to the origin of the Lidar constitute the orientation vector set. Examiner considers the coordinates of C to be based off the “center point” of one of the sides of the bounding box in Fig. 3 as C depends on p1p2 which in turn is derived from vectors based off of the center point).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, the proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 7.
Regarding claim 12, in which claim 11 is incorporated, Zhang (IEEE) discloses wherein the determining of [the point] comprises: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); [determining, based on the representative moving direction, a line segment associated with the object box; and determining the point further based on the line segment]
However, Zhang (IEEE) in view of Zhang (518) fails to disclose the point and determining, based on the representative moving direction, a line segment associated with the object box; and determining the point further based on the line segment.
Liu teaches the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and determining, based on the representative moving direction, a line segment associated with the object box (Fig. 3, 4; Page 6, §2.2 Position Inference, yv points to the moving direction of target vehicle…the vectors that point from the center of model to the center of each side constitute a normal vector set, and the vectors that point from the center of each side to the origin of the Lidar constitute the orientation vector set. For each edge, the angle between the orientation vector and normal vector show whether the edge can be seen under the perspective of the Lidar; Page 7, §2.2 Position Inference, Lines p1p2 and p2p3 are the two visible edges. As yv contributes to the normal vector set and line p1p2 is determined via the normal vector and orientation vector set, Examiner considers the determination as “based on the representative moving direction” and p1p2 as “line segment associated with the object box”); and determining the point further based on the line segment (Page 7, Eqn. 9, 10. The coordinates for the point C is based off of p1p2).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, the proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 12.
Regarding claim 14, in which claim 11 is incorporated, Zhang (IEEE) discloses wherein the determining of [the point] comprises: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); [assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box; and determining the point, further based on the plurality of indices].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose the point and assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box; and determining the point, further based on the plurality of indices.
Liu teaches the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box (Fig. 4. Examiner considers p1-p4 as indices); and determining the point, further based on the plurality of indices (Page 7, Eqn. 9, 10. The coordinates for the point C is based off of p1p2 which is defined by a “plurality of indices”).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, the proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 14.
Regarding claim 17, in which claim 11 is incorporated, Zhang (IEEE) discloses wherein the determining of [the point] comprises: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); and [determining the point based on a center point of one line segment among line segments constituting the object box].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose the point and determining the point based on a center point of one line segment among line segments constituting the object box.
Liu teaches the point (Page 7, Eqn. 9, 10. Examiner considers C as “the point”) and determining the point based on a center point of one line segment among line segments constituting the object box (Fig. 3; Page 7, Eqn. 9, 10; Page 6, §2.2 Position Inference, yv points to the moving direction of target vehicle…the vectors that point from the center of model to the center of each side constitute a normal vector set, and the vectors that point from the center of each side to the origin of the Lidar constitute the orientation vector set. Examiner considers the coordinates of C to be based off the “center point” of one of the sides of the bounding box in Fig. 3 as C depends on p1p2 which in turn is derived from vectors based off of the center point).
Zhang (IEEE), Zhang (518), and Liu are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Liu into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been a more efficient and robust algorithm as suggested by Liu at Page 3, §1.2 Model-Based Method, the proposed pose-estimation method requires low computation and is robust to the environment.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Liu.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Liu to obtain the invention as specified in claim 17.
Claims 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Tsaregorodtsev et al. (2023, “Automated Static Camera Calibration with Intelligent Vehicles”, IEEE Intelligent Vehicles Symposium (IV)) (hereafter, “Tsaregorodtsev”).
Regarding claim 3, in which claim 1 is incorporated, Zhang (IEEE) discloses wherein the processor is configured to [determine the point] by: determining, based on the point cloud (Page 3, §Pose Estimation, the vehicle point cloud), an object box representing the object in a plurality of frames (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori; Page 4, §III. Pose estimation, three consecutive frames); and determining, based on a first position of the object box in the first frame and a second position of the object box in the at least one frame before the first frame, a first heading of the object box in the first frame (Fig. 5; Eqn. 6; Page 4, §III. Pose estimation, To address this we propose a multi frame fitting (MFF) model that fits point clouds from three consecutive frames to estimate the middle frame… In this way, the approximate estimation of vehicle pose. Examiner notes that in Eqn. 6, positions from multiple time points (tx and ty) are used to determine the pose which Examiner considers as “heading”); [determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame; determining a line segment associated with the object box based on the first heading being within a first range, the track heading being within a second range, and the representative moving direction being a specified direction; and determining the point further based on the line segment].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determine the point and disclose determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame; determining a line segment associated with the object box based on the first heading being within a first range, the track heading being within a second range, and the representative moving direction being a specified direction; and determining the point further based on the line segment.
Tsaregorodtsev teaches determine the point (Page 4, §F. Result Refinement, The vehicle corner point with the lowest distance to the projected bottom line of the bounding box rectangle is chosen as the new vehicle reference point) and disclose determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame (Fig. 1, top left panel; Page 3, §B. Data Acquisition and Pre-processing, Therefore, we use the Hungarian Algorithm [25] to find the most cost-effective box-to-box association between two frames…the track can be associated with a newly detected box…it is possible to reconstruct the path of each vehicle that drove. Fig. 1 illustrates heading direction associated with the tracks); determining a line segment associated with the object box (Page 4, §F. Result Refinement, By using the orientation information contained in xt and the known vehicle dimensions, we can calculate the footprint of the vehicle, i.e., the world coordinates of its corners in the ground plane. Due to geometrical constraints, one of these ground points must lie on the bounding box’s bottom edge. For refinement, the bounding box of the vehicle is projected onto the ground plane resulting in a quadrilateral. The projection is made with one of the previously obtained hypothetical transformations. The required ground plane is estimated by performing a principal component analysis (PCA) [29] of the recorded localization track. Examiner considers the bottom edge a line segment) based on the first heading being within a first range (Fig. 1, middle panel. Examiner considers the headings at the locations where bounding boxes are measured to be the “first range”), the track heading being within a second range (Fig. 1, top left panel. Examiner considers the different headings associated with the entire track to be the “second range”), and the representative moving direction being a specified direction (Page 4, §F. Result Refinement, By using the orientation information contained in xt); and determining the point further based on the line segment (Page 4, §F. Result Refinement, The vehicle corner point with the lowest distance to the projected bottom line of the bounding box rectangle is chosen as the new vehicle reference point).
Zhang (IEEE), Zhang (518), and Chen are analogous to the claimed invention because Zhang (IEEE) and Tsaregorodtsev are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Tsaregorodtsev into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to allow for road access by other users during calibration as suggested by Tsaregorodtsev at Abstract, furthermore, we do not limit road access for other road users during calibration.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Tsaregorodtsev.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Tsaregorodtsev to obtain the invention as specified in claim 3.
Regarding claim 13, in which claim 11 is incorporated, Zhang (IEEE) discloses wherein the determining of [the point] comprises: determining, based on the point cloud (Page 3, §Pose Estimation, the vehicle point cloud), an object box representing the object in a plurality of frames (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori; Page 4, §III. Pose estimation, three consecutive frames); and determining, based on a first position of the object box in the first frame and a second position of the object box in the at least one frame before the first frame, a first heading of the object box in the first frame (Fig. 5; Eqn. 6; Page 4, §III. Pose estimation, To address this we propose a multi frame fitting (MFF) model that fits point clouds from three consecutive frames to estimate the middle frame… In this way, the approximate estimation of vehicle pose. Examiner notes that in Eqn. 6, positions from multiple time points (tx and ty) are used to determine the pose which Examiner considers as “heading”); [determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame; determining a line segment associated with the object box based on the first heading being within a first range, the track heading being within a second range, and the representative moving direction being a specified direction; and determining the point further based on the line segment].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose the point and disclose determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame; determining a line segment associated with the object box based on the first heading being within a first range, the track heading being within a second range, and the representative moving direction being a specified direction; and determining the point further based on the line segment.
Tsaregorodtsev teaches the point (Page 4, §F. Result Refinement, The vehicle corner point with the lowest distance to the projected bottom line of the bounding box rectangle is chosen as the new vehicle reference point) and disclose determining, based on the first heading and a second heading of the object box in the at least one frame before the first frame, a track heading of the object box in the first frame (Fig. 1, top left panel; Page 3, §B. Data Acquisition and Pre-processing, Therefore, we use the Hungarian Algorithm [25] to find the most cost-effective box-to-box association between two frames…the track can be associated with a newly detected box…it is possible to reconstruct the path of each vehicle that drove. Fig. 1 illustrates heading direction associated with the tracks); determining a line segment associated with the object box (Page 4, §F. Result Refinement, By using the orientation information contained in xt and the known vehicle dimensions, we can calculate the footprint of the vehicle, i.e., the world coordinates of its corners in the ground plane. Due to geometrical constraints, one of these ground points must lie on the bounding box’s bottom edge. For refinement, the bounding box of the vehicle is projected onto the ground plane resulting in a quadrilateral. The projection is made with one of the previously obtained hypothetical transformations. The required ground plane is estimated by performing a principal component analysis (PCA) [29] of the recorded localization track. Examiner considers the bottom edge a line segment) based on the first heading being within a first range (Fig. 1, middle panel. Examiner considers the headings at the locations where bounding boxes are measured to be the “first range”), the track heading being within a second range (Fig. 1, top left panel. Examiner considers the different headings associated with the entire track to be the “second range”), and the representative moving direction being a specified direction (Page 4, §F. Result Refinement, By using the orientation information contained in xt); and determining the point further based on the line segment (Page 4, §F. Result Refinement, The vehicle corner point with the lowest distance to the projected bottom line of the bounding box rectangle is chosen as the new vehicle reference point).
Zhang (IEEE), Zhang (518), and Chen are analogous to the claimed invention because Zhang (IEEE) and Tsaregorodtsev are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Tsaregorodtsev into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to allow for road access by other users during calibration as suggested by Tsaregorodtsev at Abstract, furthermore, we do not limit road access for other road users during calibration.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Tsaregorodtsev .
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Tsaregorodtsev to obtain the invention as specified in claim 13.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Chen et al. (US 2024/0265710) (hereafter, “Chen”).
Regarding claim 6, in which claim 1 is incorporated, Zhang (IEEE) discloses wherein the processor is configured to [determine the point] by: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); and [determining the point based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle, or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determine the point and determining the point based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle, or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle.
Chen teaches determining the point (¶0056, For example, the reference point is a midpoint of the bottom boundary of the bounding box) based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle (Fig. 5A; ¶0042, The autonomous vehicle may track objects moving along a same direction; ¶0056, For example, the reference point is a midpoint of the bottom boundary of the bounding box. As illustrated in Fig. 5A of Chen, the vehicle pictured ahead (520) is in a lane parallel to the observer or “the vehicle” in the instant claim. As the bounding box is in a plane perpendicular to the observer, all four sides are equidistant longitudinally to the observer. Therefore, any line of the bounding box (540) is considered to be “a smallest longitudinal distance”. Since the limitation is recited in the alternative, Examiner considers Chen to teach the limitation in its entirety), or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle.
Zhang (IEEE), Zhang (518), and Chen are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Chen into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to enable the operation of the vehicle as suggested by Chen at ¶0043, so as to allow the operation of the autonomous vehicle to proceed.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Chen.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Chen to obtain the invention as specified in claim 6.
Regarding claim 16, in which claim 11 is incorporated, Zhang (IEEE) discloses wherein the determining of [the point] comprises: determining an object box representing the object in the first frame (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori); and [determining the point based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle, or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle].
However, Zhang (IEEE) in view of Zhang (518) fails to disclose the point and determining the point based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle, or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle.
Chen teaches the point and determining the point (¶0056, For example, the reference point is a midpoint of the bottom boundary of the bounding box) based on one of: a first line segment having, among line segments associated with the object box, a smallest longitudinal distance to the vehicle, based on the representative moving direction being parallel to a longitudinal axis of the vehicle (Fig. 5A; ¶0042, The autonomous vehicle may track objects moving along a same direction; ¶0056, For example, the reference point is a midpoint of the bottom boundary of the bounding box. From Examiner’s interpretation of Fig. 5A, the vehicle pictured ahead is in a lane parallel to the observer or “the vehicle” in the instant claim. As the bounding box is in a plane perpendicular to the observer, all four sides are equidistant longitudinally to the observer. Therefore, any line of the bounding box is considered to be “a smallest longitudinal distance”. Since the limitation is recited in the alternative, Examiner considers Chen to teach the limitation in its entirety), or a second line segment having, among the line segments associated with the object box, a smallest lateral distance to the vehicle, based on the representative moving direction being perpendicular to the longitudinal axis of the vehicle.
Zhang (IEEE), Zhang (518), and Chen are analogous to the claimed invention because Zhang (IEEE) and Liu are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the reference point determination of Chen into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to enable the operation of the vehicle as suggested by Chen at ¶0043, so as to allow the operation of the autonomous vehicle to proceed.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Chen.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Chen to obtain the invention as specified in claim 16.
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Watanabe et al. (US 2023/0152811) (hereafter, “Watanabe”).
Regarding claim 8, Zhang (IEEE) in view of Zhang (518) discloses the object recognition apparatus of claim 1.
However, Zhang (IEEE) in view of Zhang (518) fails to disclose wherein the processor is configured to determine the first moving direction of the object in the first frame based on a value obtained by adding a first distance moved by the vehicle to a second distance moved by the object with respect to the vehicle, wherein the second distance is determined based on a difference between the first position and the second position.
Watanabe teaches wherein the processor is configured to determine the first moving direction of the object in the first frame based on a value obtained by adding a first distance moved by the vehicle to a second distance moved by the object with respect to the vehicle (¶0120, The movement vector is information including a moving speed and a moving direction. The object detection unit 219 estimates the movement vector of the nearby object based on the change in the distance from the mobile robot 20 to the nearby object… according to the change of the position of the nearby object over time; ¶0124, The mobile robot 20 is moving upward. Examiner considers the calculation of the change in the distance from the robot to the object to indicate an addition of the robot’s movement and the object’s movement), wherein the second distance is determined based on a difference between the first position and the second position (¶0120, According to the change of the position of the nearby object over time. Examiner considers the change in the object’s position of time to indicate a difference between a first and a second position).
Zhang (IEEE), Zhang (518), and Watanabe are analogous to the claimed invention because Zhang (IEEE) is in the field of vehicle systems for detecting external objections and motion, and Zhang (518) and Watanabe are in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the moving direction determination of Watanabe into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve the motion estimation as suggested by Watanabe at ¶0122, it is possible to improve the accuracy of the estimation of the moving speed and the moving direction.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Watanabe .
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Watanabe to obtain the invention as specified in claim 8.
Regarding claim 18, Zhang (IEEE) in view of Zhang (518) discloses the object recognition method of claim 11.
However, Zhang (IEEE) in view of Zhang (518) fails to disclose wherein the determining of the first moving direction of the object in the first frame comprises determining the first moving direction of the object in the first frame based on a value obtained by adding a first distance moved by the vehicle to a second distance moved by the object with respect to the vehicle, wherein the second distance is determined based on a difference between the first position and the second position.
Watanabe teaches wherein the determining of the first moving direction of the object in the first frame comprises determining the first moving direction of the object in the first frame based on a value obtained by adding a first distance moved by the vehicle to a second distance moved by the object with respect to the vehicle (¶0120, The movement vector is information including a moving speed and a moving direction. The object detection unit 219 estimates the movement vector of the nearby object based on the change in the distance from the mobile robot 20 to the nearby object… according to the change of the position of the nearby object over time; ¶0124, The mobile robot 20 is moving upward. Examiner considers the calculation of the change in the distance from the robot to the object to indicate an addition of the robot’s movement and the object’s movement), wherein the second distance is determined based on a difference between the first position and the second position (¶0120, According to the change of the position of the nearby object over time. Examiner considers the change in the object’s position of time to indicate a difference between a first and a second position).
Zhang (IEEE), Zhang (518), and Watanabe are analogous to the claimed invention because Zhang (IEEE) is in the field of vehicle systems for detecting external objections and motion, and Zhang (518) and Watanabe are in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the moving direction determination of Watanabe into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve the motion estimation as suggested by Watanabe at ¶0122, it is possible to improve the accuracy of the estimation of the moving speed and the moving direction.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Watanabe .
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Watanabe to obtain the invention as specified in claim 18.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Iketani (US 2008/0166024).
Regarding claim 9, Zhang (IEEE) in view of Zhang (518) discloses the object recognition apparatus of claim 1.
However, Zhang (IEEE) in view of Zhang (518) fails to disclose wherein the processor is configured to determine whether the object is a moving object or a movable stationary object further based on a speed of the object, wherein the speed of the object is determined based on the first position and the second position.
Iketani teaches wherein the processor is configured to determine whether the object is a moving object or a movable stationary object further based on a speed of the object (Fig. 22; ¶0085 As will be described with reference to FIG. 22 or the like, the vector classifying portion 262 detects the type of the movement vector detected at each feature point based on … the speed of the automotive vehicle detected by the vehicle speed sensor 113. Examiner notes that the method in Fig. 22 ultimately determines whether an object is moving or stationary), wherein the speed of the object is determined based on the first position and the second position (Eqn. 1, 2; ¶0060, X(t-k) and Z(t-k) represent the x- and z-axis directional positions of the object calculated k times before. Examiner considers the two positions at two separate time points used in the equations as the first and second positions).
Zhang (IEEE), Zhang (518), and Iketani are analogous to the claimed invention because Zhang (IEEE) and Iketani are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the motion determination of Iketani into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve detection performance as suggested by Iketani at ¶0105, it is possible to decrease the processing load and to thus improve the detection performance.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Iketani.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Iketani to obtain the invention as specified in claim 9.
Regarding claim 19, Zhang (IEEE) in view of Zhang (518) discloses the object recognition method of claim 11.
However, Zhang (IEEE) in view of Zhang (518) fails to disclose determining whether the object is a moving object or a movable stationary object further based on a speed of the object, wherein the speed of the object is determined based on the first position and the second position.
Iketani teaches determining whether the object is a moving object or a movable stationary object further based on a speed of the object (Fig. 22; ¶0085 As will be described with reference to FIG. 22 or the like, the vector classifying portion 262 detects the type of the movement vector detected at each feature point based on … the speed of the automotive vehicle detected by the vehicle speed sensor 113. Examiner notes that the method in Fig. 22 ultimately determines whether an object is moving or stationary), wherein the speed of the object is determined based on the first position and the second position (Eqn. 1, 2; ¶0060, X(t-k) and Z(t-k) represent the x- and z-axis directional positions of the object calculated k times before. Examiner considers the two positions at two separate time points used in the equations as the first and second positions).
Zhang (IEEE), Zhang (518), and Iketani are analogous to the claimed invention because Zhang (IEEE) and Iketani are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the motion determination of Iketani into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve detection performance as suggested by Iketani at ¶0105, it is possible to decrease the processing load and to thus improve the detection performance.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Iketani.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Iketani to obtain the invention as specified in claim 19.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (2019, “A Framework for Tuning Behavior Classification at Intersections Using 3D LIDAR”, IEEE Transactions on Vehicular Technology, Vol. 68, No. 8) (hereafter, “Zhang (IEEE)”) in view of Zhang et al. (US 2024/0103518) (hereafter, “Zhang (518)”) as applied to claims 1 and 11 above, and further in view of Chavez-Garcia et al. (2016, “Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking”, IEEE Transactions on Intelligent Transportation Systems, Vol. 17, No. 2) (hereafter, “Chavez-Garcia”).
Regarding claim 10, in which claim 1 is incorporated, Zhang (IEEE) discloses [wherein the processor is further configured to assign, to the object, one of: a first identifier indicating that the object is a moving object, or a second identifier indicating that the object is a movable stationary object], wherein the point representing the object in the first frame is determined further based on a point cloud acquired by a LiDAR (Light Detection And Ranging) sensor (Fig. 2; Fig. 3A caption, LIDAR point returns from the lower portion of a target vehicle; Page 3, §Pose Estimation, the vehicle point cloud; Page 4, right column, last paragraph, §III. Pose Estimation, In this way, the approximate estimation of vehicle pose (x, y, θ) is determined based on the vehicle point cloud and the vehicle motion. Examiner considers (x,y) to be a point representing the object), and wherein the sensor comprises the LiDAR sensor (Page 7, §A. Data Collection, Our AV is equipped with a Velodyne HDL-64E LIDAR).
However, Zhang (IEEE) in view of Zhang (518) fails to disclose wherein the processor is further configured to assign, to the object, one of: a first identifier indicating that the object is a moving object, or a second identifier indicating that the object is a movable stationary object.
Chavez-Garcia teaches wherein the processor is further configured to assign, to the object, one of: a first identifier indicating that the object is a moving object (Fig. 8, Right panels. Examiner considers the speed labels as identifiers that the object is moving), or a second identifier indicating that the object is a movable stationary object (Fig. 8, Right-most panel. The label ped_61 is not accompanied by a speed label. Examiner considers this an identifier indicating an object is a movable stationary object (as pedestrians are movable)).
Zhang (IEEE), Zhang (518), and Chavez-Garcia are analogous to the claimed invention because Zhang (IEEE) and Chavez-Garcia are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the motion identifiers of Chavez-Garcia into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve the tracking process as suggested by Chavez-Garcia at page 533, §X. Conclusion and Perspectives, the tracking stage benefits from the reduction of mis-detections and from the more accurate classification information to accelerate the tracking process.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Chavez-Garcia.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Chavez-Garcia to obtain the invention as specified in claim 10.
Regarding claim 20, Zhang (IEEE) in view of Zhang (518) discloses the object recognition method of claim 11.
However, Zhang (IEEE) in view of Zhang (518) fails to disclose assigning, to the object, one of: a first identifier indicating that the object is a moving object, or a second identifier indicating that the object is a movable stationary object.
Chavez-Garcia teaches assigning, to the object, one of: a first identifier indicating that the object is a moving object (Fig. 8, Right panels. Examiner considers the speed labels as identifiers that the object is moving), or a second identifier indicating that the object is a movable stationary object (Fig. 8, Right-most panel. The label ped_61 is not accompanied by a speed label. Examiner considers this an identifier indicating an object is a movable stationary object (as pedestrians are movable)).
Zhang (IEEE), Zhang (518), and Chavez-Garcia are analogous to the claimed invention because Zhang (IEEE) and Chavez-Garcia are in the field of vehicle systems for detecting external objections and motion, and Zhang (518) is in the field of detecting external objects and motion using sensor systems. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the motion identifiers of Chavez-Garcia into the output signal of Zhang (518) and the vehicle object and motion direction detection system of Zhang (IEEE). The suggestion/motivation for doing so would have been to improve the tracking process as suggested by Chavez-Garcia at page 533, §X. Conclusion and Perspectives, the tracking stage benefits from the reduction of mis-detections and from the more accurate classification information to accelerate the tracking process.
This method of improving Zhang (IEEE) was within the ordinary ability of one of ordinary skill in the art based on the teachings of Zhang (518) and Chavez-Garcia.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Zhang (IEEE) and the teachings of Zhang (518) with the teachings of Chavez-Garcia to obtain the invention as specified in claim 20.
Allowable Subject Matter
Claims 5 and 15 objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claims 5 and 15, Zhang (IEEE) discloses the determining of an object box (Fig. 3, top-left panel, red box; Page 4, right column, §III. Pose Estimation, The length and width of rectangular bounding box of vehicle measurement model modeled a priori), Tsaregorodtsev teaches the determining of a track heading (Fig. 1, top left panel; Page 3, §B. Data Acquisition and Pre-processing, Therefore, we use the Hungarian Algorithm [25] to find the most cost-effective box-to-box association between two frames…the track can be associated with a newly detected box…it is possible to reconstruct the path of each vehicle that drove), and Liu teaches assigning indices to the object box (Fig. 4. Examiner considers p1-p4 as indices). However, none of the cited references of the record individually or in combination teach “assigning a different index, of a plurality of indices, to each of a plurality of vertices forming the object box, based on the first heading being within a first range, the track heading being within a second range, and the representative moving direction being a specified direction”, in combination with other limitations, in claims 5 and 15 as a whole.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Baeg et al. (US 2022/0189040) discloses determining a moving direction of a vehicle with a bounding box (¶0092, the moving direction of an object is recognized using the oriented bounding box).
Bauch et al. (US 2021/0387617) discloses determining a reference point on a moving vehicle (¶0050, For the determined reference point 312 of a vehicle 102 moving in, a set of vertical lines 311 can be determined).
Suzuki et al. (US 2019/0285718) discloses determining the moving direction and distance of a vehicle (¶0089, the traveling locus L (moving distance and moving direction) of the vehicle from the beacon to the parking position).
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAOMAO DING whose telephone number is (571)272-7237. The examiner can normally be reached Mon-Fri 9:00-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Henok Shiferaw can be reached at (571) 272-4637. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/XIAOMAO DING/Examiner, Art Unit 2676
/Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676
Prosecution Insights