DETAILED ACTION
Claims 1-16 are currently pending and have been examined in this application. This is the first action on the merits.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This communication is in response to the application filed 08/31/2025.
Priority
Acknowledgment is made of applicant's claim for foreign priority based on an application filed in Republic of Korea on 10/31/2024. It is noted, however, that applicant has not filed a certified copy of the KR10-2024-0152197 application as required by 37 CFR 1.55.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-16 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The term “rough outline” in claim 1 (repeated in Claim 9) is a relative term which renders the claim indefinite. The term “rough” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. For the purpose of continued examination, “rough outline” will be interpreted to include any approximation of size or shape. Claims 2-8 and 10-16 are rejected for being dependent on an indefinite claim.
The term “large vehicle” in claim 5 (repeated in Claim 13) is a relative term which renders the claim indefinite. The term “large” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. It is unclear where the delineation is between a large and small vehicle. For the purpose of continued examination, “large vehicle” will be interpreted to include any vehicle.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 3-5, 7, 9, 11-13, 15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Choi (US20240142575).
Claim 1:
Choi explicitly teaches:
An intelligent vehicle recognition device applied to an intelligent transportation system, comprising: an antenna assembly including a transmitting antenna group including a plurality of transmitting antennas configured to transmit a radar signal toward a vehicle moving in a lane direction, and a receiving antenna group including a plurality of receiving antennas configured to receive a radar signal reflected from the vehicle;
(Choi) – “In operation 140, the processor 710 according to an example may calculate an angle of arrival. In addition to the object's range information (e.g., a vehicle, a person, a guardrail, a traffic light, and the like), in a real-world driving scenario of a vehicle on a road, there may also be a desire for information about the angle of arrival of the object. The processor 710 according to an example may estimate the angle of arrival based on the result of operation 130. To estimate the angle of arrival, a plurality of transmission and reception antennas may be configured in an array form and a Digital Beam Forming (DBF) algorithm or an Angle of Arrival (AoA) MULtiple Signal Classification (MUSIC) algorithm may be used, thus identifying in a direction of the object from the driving direction of the vehicle. The DBF algorithm may be an algorithm for obtaining angular information of an unknown target.” (Para 0056)
“An array antenna may include a plurality of antenna elements. Multiple input multiple output (MIMO) may be implemented through the plurality of antenna elements. Here, a plurality of MIMO channels may be formed by the plurality of antenna elements. For example, a plurality of channels corresponding to M×N virtual antennas may be formed through M transmission antenna elements and N reception antenna elements.” (Para 0089)
“Radar data may be generated based on the radar transmission signal and the radar reception signal. For example, the radar device may transmit the radar transmission signal through the array antenna based on the frequency modulation model. When the radar transmission signal is reflected by a target, the radar device may receive the radar reception signal through the array antenna.” (Para 0090)
a radar signal processing circuit configured to process the radar signal received by
the receiving antenna group to output a radar point cloud including speed information and position information of each point;
(Choi) - “An electronic device may use a radar device attached to a driving vehicle to recognize objects (e.g., surrounding vehicles, obstacles, terrain, and the like) around the driving vehicle. In order to recognize the objects, the electronic device may transform radar data into point cloud data.” (Para 0048)
“Referring to FIG. 1, in operation 120, the processor 710 according to an example may perform at least one of a range Fast Fourier Transform (FFT) and a Doppler FFT based on the radar data. Through the operation, the processor 710 may obtain a range to a point cloud (e.g., a relative range) based on the driving vehicle and the velocity (e.g., a relative velocity or a radial velocity) of the point cloud.” (Para 0052)
“In a non-limiting example, point cloud data may be generated based on radar data received from a radar device attached to the driving vehicle. A point clouds may include a set of points measured on the surface of an object generated by a 3D laser. The processor 710 may process the radar data to generate the point cloud data.” (Para 0060)
a track generation and detection circuit configured to cluster a group of dense radar point clouds having similar features in a vehicle lane direction in a designated vehicle recognition section to create and detect a plurality of tracks representing at least a part of the vehicle; and
(Choi) – “In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
Examiner Note: Per BRI, an area where a radar device acquires radar data corresponds with a designated vehicle recognition section.
a vehicle type determination circuit configured to recognize a rough outline of the vehicle based on horizontal and vertical distributions of the plurality of tracks to determine a type of vehicle.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of the first clusters.” (Para 0013)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
Examiner Note: Per BRI, point clouds in a coordinate system having at least x and y axes corresponds with horizontal and vertical distributions. Size corresponds with rough outline (see 112 rejection above).
Claim 3:
Choi teaches the respective limitations of Claim 1. Choi further teaches:
wherein the track creation and detection circuit includes a track accumulation circuit configured to accumulate tracks included in a plurality of frames.
(Choi) – “In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
Claim 4:
Choi teaches the respective limitations of Claim 1. Choi further teaches:
wherein the vehicle type determination circuit includes a track feature classification circuit configured to determine a type of vehicle based on at least one of a width and height of each track belonging to the vehicle, a distance between center points of consecutive tracks, and the number of tracks.
(Choi) – “In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
“In a non-limiting example, a driving vehicle 650 may be moving in a driving direction 660. In this case, the coordinates of the y-axis 630 of the driving vehicle 650 may change over time. As the driving vehicle 650 moves, an object around the driving vehicle 650 may also change. For example, as displayed in a camera image 600, an object 610 (e.g., a vehicle) may be on the left side of the driving vehicle 650. In an example, the camera image 600 may be displayed on a display device, such as display device 750 described below in greater detail with reference to FIG. 7. When the object 610 exists, point clouds of the object 610 may be displayed as an area 611 on the second coordinate system 601. The point clouds in the area 611 may be points in one cluster generated as a result of clustering point clouds.” (Para 0102)
Examiner Note: Fig. 6 shows a width and height of each track belonging to the vehicle.
PNG
media_image1.png
464
767
media_image1.png
Greyscale
Claim 5:
Choi teaches the respective limitations of Claim 1. Choi further teaches:
wherein the vehicle type determination circuit further includes a first large vehicle classification circuit configured to classify a 2D image acquired by projecting a spatial distribution of accumulated tracks of the recognized vehicle in three directions including forward, up, and to the side, using a machine learning algorithm, to determine a type of large vehicle when the determined vehicle is a large vehicle; and
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
“In a non-limiting example, a driving vehicle 650 may be moving in a driving direction 660. In this case, the coordinates of the y-axis 630 of the driving vehicle 650 may change over time. As the driving vehicle 650 moves, an object around the driving vehicle 650 may also change. For example, as displayed in a camera image 600, an object 610 (e.g., a vehicle) may be on the left side of the driving vehicle 650. In an example, the camera image 600 may be displayed on a display device, such as display device 750 described below in greater detail with reference to FIG. 7. When the object 610 exists, point clouds of the object 610 may be displayed as an area 611 on the second coordinate system 601. The point clouds in the area 611 may be points in one cluster generated as a result of clustering point clouds.” (Para 0102)
Examiner Note: Fig. 6 shows a large vehicle in a 2D image and points projected in three dimensions.
PNG
media_image1.png
464
767
media_image1.png
Greyscale
a second large vehicle classification circuit configured to determine a type of large vehicle based on machine learning, with at least one of a width and height of each track belonging to the vehicle, a distance between center points of consecutive tracks, and the number of tracks as a feature, based on the horizontal and vertical distributions of the tracks created and detected in an extended recognition section when the determined vehicle is a large vehicle.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
“In a non-limiting example, a driving vehicle 650 may be moving in a driving direction 660. In this case, the coordinates of the y-axis 630 of the driving vehicle 650 may change over time. As the driving vehicle 650 moves, an object around the driving vehicle 650 may also change. For example, as displayed in a camera image 600, an object 610 (e.g., a vehicle) may be on the left side of the driving vehicle 650. In an example, the camera image 600 may be displayed on a display device, such as display device 750 described below in greater detail with reference to FIG. 7. When the object 610 exists, point clouds of the object 610 may be displayed as an area 611 on the second coordinate system 601. The point clouds in the area 611 may be points in one cluster generated as a result of clustering point clouds.” (Para 0102)
Claim 7:
Choi teaches the respective limitations of Claim 3. Choi further teaches:
further comprising: a vehicle speed calculation circuit configured to calculate a speed of the vehicle from positions of the same tracks present in the consecutive frames and Doppler values of the tracks.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“An electronic device may use a radar device attached to a driving vehicle to recognize objects (e.g., surrounding vehicles, obstacles, terrain, and the like) around the driving vehicle. In order to recognize the objects, the electronic device may transform radar data into point cloud data.” (Para 0048)
“Referring to FIG. 1, in operation 120, the processor 710 according to an example may perform at least one of a range Fast Fourier Transform (FFT) and a Doppler FFT based on the radar data. Through the operation, the processor 710 may obtain a range to a point cloud (e.g., a relative range) based on the driving vehicle and the velocity (e.g., a relative velocity or a radial velocity) of the point cloud.” (Para 0052)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
Claim 9:
Choi explicitly teaches:
An intelligent vehicle recognition method (S1000) applied to an intelligent transportation system, the method comprising: a radar transmission and reception operation (S100) of transmitting, by a transmitting antenna group including a plurality of transmitting antennas, a radar signal toward a vehicle moving in a lane direction, and receiving, by a receiving antenna group including a plurality of receiving antennas, a radar signal reflected from the vehicle;
(Choi) – “In operation 140, the processor 710 according to an example may calculate an angle of arrival. In addition to the object's range information (e.g., a vehicle, a person, a guardrail, a traffic light, and the like), in a real-world driving scenario of a vehicle on a road, there may also be a desire for information about the angle of arrival of the object. The processor 710 according to an example may estimate the angle of arrival based on the result of operation 130. To estimate the angle of arrival, a plurality of transmission and reception antennas may be configured in an array form and a Digital Beam Forming (DBF) algorithm or an Angle of Arrival (AoA) MULtiple Signal Classification (MUSIC) algorithm may be used, thus identifying in a direction of the object from the driving direction of the vehicle. The DBF algorithm may be an algorithm for obtaining angular information of an unknown target.” (Para 0056)
“An array antenna may include a plurality of antenna elements. Multiple input multiple output (MIMO) may be implemented through the plurality of antenna elements. Here, a plurality of MIMO channels may be formed by the plurality of antenna elements. For example, a plurality of channels corresponding to M×N virtual antennas may be formed through M transmission antenna elements and N reception antenna elements.” (Para 0089)
“Radar data may be generated based on the radar transmission signal and the radar reception signal. For example, the radar device may transmit the radar transmission signal through the array antenna based on the frequency modulation model. When the radar transmission signal is reflected by a target, the radar device may receive the radar reception signal through the array antenna.” (Para 0090)
a radar signal processing operation (S200) of processing the radar signal received by the receiving antenna group to output a radar point cloud including speed information and position information of respective points;
(Choi) - “An electronic device may use a radar device attached to a driving vehicle to recognize objects (e.g., surrounding vehicles, obstacles, terrain, and the like) around the driving vehicle. In order to recognize the objects, the electronic device may transform radar data into point cloud data.” (Para 0048)
“Referring to FIG. 1, in operation 120, the processor 710 according to an example may perform at least one of a range Fast Fourier Transform (FFT) and a Doppler FFT based on the radar data. Through the operation, the processor 710 may obtain a range to a point cloud (e.g., a relative range) based on the driving vehicle and the velocity (e.g., a relative velocity or a radial velocity) of the point cloud.” (Para 0052)
“In a non-limiting example, point cloud data may be generated based on radar data received from a radar device attached to the driving vehicle. A point clouds may include a set of points measured on the surface of an object generated by a 3D laser. The processor 710 may process the radar data to generate the point cloud data.” (Para 0060)
a track creation and detection operation (S300) of clustering a group of dense s radar point clouds having similar features in a vehicle lane direction in a designated vehicle recognition section to create and detect a plurality of tracks representing at least a part of the vehicle; and
(Choi) – “In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 may track a cluster corresponding to at least one target object in the point cloud data of each of one or more first timepoints, the first timepoints being timepoints prior to timepoint termed as the second timepoint. In an example, the first timepoints may be one or more previous timepoints, prior to the detection of the target object. Thus, the one or more first timepoints may be a past timepoint compared to the second timepoint. The processor 710 may track the cluster corresponding to the target object in the point cloud data of each of the one or more first timepoints, so that the point clouds corresponding to the cluster may be identified in the past point cloud data.” (Para 0071)
“The processor 710 according to an example may accumulate and store point cloud data generated over time. Furthermore, the processor 710 may track a cluster corresponding to a target object in the accumulated point cloud data in a reverse direction 490 of time. For example, the processor 710 may track a cluster in the point cloud data 440 of the first timepoint B 401 to identify point clouds included in the cluster and then track the cluster in the point cloud data 420 of the first timepoint A 400.” (Para 0099)
Examiner Note: Per BRI, an area where a radar device acquires radar data corresponds with a designated vehicle recognition section.
a vehicle type determination operation (S500) of recognizing a rough outline of the vehicle based on horizontal and vertical distributions of the plurality of tracks to determine io a type of vehicle.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of the first clusters.” (Para 0013)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
Examiner Note: Per BRI, point clouds in a coordinate system having at least x and y axes corresponds with horizontal and vertical distributions. Size corresponds with rough outline (see 112 rejection above).
Claim 11:
Rejected for the same reasons as Claim 3
Claim 12:
Rejected for the same reasons as Claim 4
Claim 13:
Rejected for the same reasons as Claim 5
Claim 15:
Rejected for the same reasons as Claim 7
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.
Claim(s) 2, 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Choi (US20240142575) in view of Kishigami (US20140327567).
Claim 2:
Choi teaches the respective limitations of Claim 1. Choi further teaches:
wherein, in the antenna assembly, the plurality of transmitting antennas or the plurality of receiving antennas are spaced apart from each other in a horizontal direction and a vertical direction to receive a radar signal including angle-of-arrival information [in an azimuth direction and an elevation direction].
(Choi) – “In operation 140, the processor 710 according to an example may calculate an angle of arrival. In addition to the object's range information (e.g., a vehicle, a person, a guardrail, a traffic light, and the like), in a real-world driving scenario of a vehicle on a road, there may also be a desire for information about the angle of arrival of the object. The processor 710 according to an example may estimate the angle of arrival based on the result of operation 130. To estimate the angle of arrival, a plurality of transmission and reception antennas may be configured in an array form and a Digital Beam Forming (DBF) algorithm or an Angle of Arrival (AoA) MULtiple Signal Classification (MUSIC) algorithm may be used, thus identifying in a direction of the object from the driving direction of the vehicle. The DBF algorithm may be an algorithm for obtaining angular information of an unknown target.” (Para 0056)
“An array antenna may include a plurality of antenna elements. Multiple input multiple output (MIMO) may be implemented through the plurality of antenna elements. Here, a plurality of MIMO channels may be formed by the plurality of antenna elements. For example, a plurality of channels corresponding to M×N virtual antennas may be formed through M transmission antenna elements and N reception antenna elements.” (Para 0089)
“Radar data may be generated based on the radar transmission signal and the radar reception signal. For example, the radar device may transmit the radar transmission signal through the array antenna based on the frequency modulation model. When the radar transmission signal is reflected by a target, the radar device may receive the radar reception signal through the array antenna.” (Para 0090)
Choi does not explicitly teach:
in an azimuth direction and an elevation direction
Kishigami, in the same field of endeavor of radar devices, teaches:
in an azimuth direction and an elevation direction
(Kishigami) – “Each antenna system processor performs coherent integration on a prescribed number of correlation values between a reception signal and a transmission code. A correlation matrix generator generates a correlation matrix on the basis of coherent integration values. A distance estimator estimates a distance to a target. A direction vector storage is stored with direction vectors each of which includes an azimuth component with respect to a target and an elevation angle component of a line connecting a transmission antenna and the target in which a prescribed direction is used as a reference. An incoming direction estimator estimates a signal incoming direction from the target using the correlation matrix and the direction vectors in which the elevation angle component range is restricted on the basis of the distance to the target.” (Abstract)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the object tracking of Choi with the radar device of Kishigami. One of ordinary skill in the art would have been motivated to make these modifications with a reasonable expectation of success, “to provide a radar device which can and increase the accuracy of estimation of a signal incoming direction from a target while reducing the amount of calculation for the estimation of a signal incoming direction.” (Kishigami Para 0015)
Claim 10:
Rejected for the same reasons as Claim 2
Claim(s) 6, 8, 14, 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Choi (US20240142575) in view of Shen (US20240362919).
Claim 6:
Choi teaches the respective limitations of Claim 1. Choi further teaches:
further comprising a valid track selection circuit configured to [remove at least one of a ghost track, a noise track, and a track including no license plate from among the plurality of tracks], and select a track [including a license plate] as a valid track.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of the first clusters.” (Para 0013)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
Choi does not explicitly teach:
remove at least one of a ghost track, a noise track, and a track including no license plate from among the plurality of tracks…including a license plate
Shen, in the same field of endeavor of vehicle tracking, teaches:
remove at least one of a ghost track, a noise track, and a track including no license plate from among the plurality of tracks…including a license plate
(Shen) – “An object with known dimensions, such as a license plate, can be identified and used to track the vehicle movement inside the traffic circle. Subsequent pictures are taken by the same set of cameras and the data are used by the central control to calculate the speed and the moving direction of the vehicle. The central control will monitor which direction the vehicle will exit the traffic circle and how long it will take the vehicle to exit the traffic circle at the monitored speed.” (Para 0024)
“To improve image quality at low light, a readout noise from the image sensor must be reduced as much as possible. Correlated double sampling readout may remove kTC noise from RST gate 406 and reduce the readout noise by at least an order of magnitude. A low noise circuit design is also required for the pixel source follower amplifier 408, the pixel bias circuit 412, and a column amplifier and comparator circuitry of analog to digital converters (ADC).” (Para 0042)
“FIG. 10A-10D illustrate the tracked object, e.g., the license plate of the moving vehicle by the cameras 1 and 1′ in the traffic circle. The vehicle moves away from its initial position entering the traffic circle, the cameras 1 and 1′ can at least detect its speed, the angular speed, and the distance from its initial position, as described previously.” (Para 0061)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the object tracking of Choi with the object tracking of Shen. One of ordinary skill in the art would have been motivated to make these modifications with a reasonable expectation of success, “in order to reduce congestions and traffic accidents” (Shen Para 0001)
Claim 8:
Choi teaches the respective limitations of Claim 7. Choi further teaches:
[a license plate position output circuit configured to output a position and speed of a license plate and] a type of vehicle from track-of-interest information determined by a track-of-interest determination circuit when the speed of the vehicle calculated by the vehicle speed calculation circuit exceeds a reference speed.
(Choi) – “The first point cloud data and second point cloud data may respectively include data expressed in a three-dimensional (3D) second coordinate system or a four-dimensional (4D) second coordinate system comprising two or three axes indicating a position and one axis indicating a velocity, and the second coordinate system may include an absolute coordinate system capable of displaying a position of a driving vehicle and a position of an object. The clustering of the second point clouds may include clustering the second point clouds based on a density degree of the second point clouds in the second point cloud data.” (Para 0010)
“The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of the first clusters.” (Para 0013)
“In a general aspect, here is provided a device including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to detect, at a second time point, a target object among second point cloud data according to a density degree of second point clouds in the second point cloud data, classify the target object into a type of object, and track the target object among first point clouds in first point cloud data from a plurality of previous timepoints.” (Para 0025)
“The second coordinate system may be a 3D coordinate system (or a 4D coordinate system) including two axes (or three axes) indicating a position and one axis indicating a velocity. For example, an x-axis and a y-axis may indicate a position, and a z-axis may indicate a velocity. In another example, x, y, and z axes may indicate a position, and an r-axis may indicate a velocity.” (Para 0059)
“As a result of the clustering, at least one cluster may be determined. For example, when there are three objects (e.g., three vehicles) in an area where a radar device acquires radar data, three clusters may be determined from the point cloud data. In this example, each cluster may correspond to an object, or a target object, such as the example three vehicles discussed above. Accordingly, the processor 710 may apply point clouds included in a cluster to the neural network and thus obtain output data corresponding to the cluster. The output data may include at least one of a type, a position, a size, and a movement direction of an object corresponding to each of at least one cluster. The type of the object may refer to the type of an object around a driving vehicle. For example, the type of the object may include a vehicle, a person, a guardrail, a lane, a crosswalk, a traffic light, and the like. The output data may include the probability that a cluster corresponds to the type of an object. The position of the object may be a specific position where the object exists in a coordinate system. For example, the output data may include the probability that an object exists in a specific position. The size of the object may be an estimated size based on the point cloud data. For example, the output data may include the size of an object corresponding to a cluster and the probability that the object corresponding to the cluster has the applicable size. The movement direction may be the movement direction of an object. An object may be stationary or moving. The driving vehicle may recognize a direction in which the object is moving. The direction the driving vehicle is moving may be used to predict the next position of the object. For example, the output data may include the probability that the moving direction of the object is in a specific direction.” (Para 0062)
“The processor 710 according to an example may apply accumulated point clouds 520 to the pretrained neural network 540. The accumulated point clouds 520 may include data obtained by merging point clouds of each cluster of one or more first timepoints into one time unit. For example, the accumulated point clouds 520 may be determined based on the point cloud data 420 of the first timepoint A 400, the point cloud data 440 of the first timepoint B 401, and the point cloud data 460 of the second timepoint 402. Since point clouds have two-dimensional (2D) coordinates representing positions, time-series data may be accumulated by positioning the 2D coordinates on one coordinate plane. The processor 710 may obtain output data from the pretrained neural network 540. The processor 710 may determine some of one or more clusters to be a target object based on the reliability of the output data 550.” (Para 0081)
Examiner Note: Per BRI, any non-zero speed may correspond with exceeds a reference speed.
Choi does not explicitly teach:
a license plate position output circuit configured to output a position and speed of a license plate and…when the speed of the vehicle calculated by the vehicle speed calculation circuit exceeds a reference speed
Shen, in the same field of endeavor of vehicle tracking, teaches:
a license plate position output circuit configured to output a position and speed of a license plate and…when the speed of the vehicle calculated by the vehicle speed calculation circuit exceeds a reference speed
(Shen) – “An object with known dimensions, such as a license plate, can be identified and used to track the vehicle movement inside the traffic circle. Subsequent pictures are taken by the same set of cameras and the data are used by the central control to calculate the speed and the moving direction of the vehicle. The central control will monitor which direction the vehicle will exit the traffic circle and how long it will take the vehicle to exit the traffic circle at the monitored speed.” (Para 0024)
“To improve image quality at low light, a readout noise from the image sensor must be reduced as much as possible. Correlated double sampling readout may remove kTC noise from RST gate 406 and reduce the readout noise by at least an order of magnitude. A low noise circuit design is also required for the pixel source follower amplifier 408, the pixel bias circuit 412, and a column amplifier and comparator circuitry of analog to digital converters (ADC).” (Para 0042)
“FIG. 10A-10D illustrate the tracked object, e.g., the license plate of the moving vehicle by the cameras 1 and 1′ in the traffic circle. The vehicle moves away from its initial position entering the traffic circle, the cameras 1 and 1′ can at least detect its speed, the angular speed, and the distance from its initial position, as described previously.” (Para 0061)
Therefore, it would be obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the object tracking of Choi with the object tracking of Shen. One of ordinary skill in the art would have been motivated to make these modifications with a reasonable expectation of success, “in order to reduce congestions and traffic accidents” (Shen Para 0001)
Claim 14:
Rejected for the same reasons as Claim 6
Claim 16:
Rejected for the same reasons as Claim 8
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ko (US20240161604) teaches a similar intelligent transport system.
Narumi (WO2023053664) teaches tracking license plates.
Nishimura (US20210398421) teaches license plate detection.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID RUBEN PEDERSEN whose telephone number is (571)272-9696. The examiner can normally be reached M-Th: 07:00 -16:00 Eastern.
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, Ramon Mercado can be reached at (571) 270-5744. 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.
/DAVID RUBEN PEDERSEN/Examiner, Art Unit 3658
Prosecution Insights