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 .
Response to Amendment
The amendments filed June 22, 2026 have been entered. Claims 1-5, 7-15, and 17-21 are pending in this application. Claims 1, 7, 11, and 17 have been amended. Claim 21 is new. Applicant’s amendments to the claims have overcome all rejections under 35 U.S.C. 101 set forth in the Non-Final Rejection filed March 20, 2026.
Response to Arguments
Applicant’s arguments with respect to claims 1 and 11 have been considered but are moot because the new ground of rejection based on Kim et al. (KR 20230089228 A) does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 8, 10-11, 18, and 20-21 are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Kim et al. (KR 20230089228 A), hereinafter Kim.
Regarding claim 1, Kim teaches an object detection apparatus comprising:
a processor (see para. 54) configured to:
obtain, via at least one sensor, point cloud data comprising an object (para. 49, “The 3D LiDAR device (10) can irradiate a laser or the like into a target area and can measure the distance to an object (1), such as an object or person located within the target area, by utilizing the time of flight [TOF] of the laser. Here, the 3D LiDAR device (10) can measure multiple points within a target area simultaneously or sequentially to generate 3D coordinates for each point, and thereby generate 3D point cloud data for the target area.”),
perform data augmentation of the point cloud data by applying an augmentation technique, wherein the augmentation technique is determined based on a characteristic of the object (para. 70, “The augmentation unit (130) can generate augmented point cloud data that modifies point cloud data or point cloud data by part by reflecting changes in human movement, changes in human occlusion, and changes in measurement distance.”), and
control autonomous driving of a vehicle based on the augmented point cloud data (para. 49, “Point cloud data generated from a 3D LiDAR device (10) can be utilized in various fields such as autonomous driving or obstacle detection for automobiles, mobile robots, drones, etc., and for this purpose, the point cloud data can be input as training data for machine learning or deep learning.”),
wherein the processor is configured to perform the data augmentation by determining augmentation application intensity based on at least one of a distance or a degree of occlusion of the object (para. 82, “That is, when a part of the body is obscured by an object or the like, that part becomes invisible, so the point cloud data for each part set as the obscured part can be deleted to generate obscuration augmentation data. In this case, occlusion augmented data can be generated as shown in Fig. 9.”; Fig. 9, obscuration augmentation data and thus intensity of augmentation application increases as the obscured area increases; para. 84, “In the case of noise augmentation data and distance augmentation data, they can be generated by reflecting the change in the number of data points in the point cloud data according to the measurement distance between the 3D LiDAR device (10) and the person (1). That is, referring to FIG. 10, when the measurement distance between the 3D LiDAR device (10) and the person (1) is close at 3m, the point cloud data of the human body area (P) corresponds to 1190 points, but when the measurement distance is 7m, the point cloud data of the human body area (P) is 659 points, and when the measurement distance is 10m, the point cloud data is 213 points, and it can be seen that it gradually decreases. Accordingly, the augmentation unit (130) can generate augmented point cloud data according to distance change by utilizing the received regular point cloud data”).
Regarding claims 8 and 18, Kim teaches the object detection apparatus of claim 1 and the method of claim 11,
wherein the augmentation technique comprises at least one of a dropout technique, a sparse technique, or a noise technique (para. 27, “Here, the augmentation unit can generate noise augmented data by adding random noise data to the normal point cloud data if the number of data included in the normal point cloud data is less than a set value.”).
Regarding claims 10 and 20, Kim teaches the object detection apparatus of claim 1 and the method of claim 11, wherein the processor is further configured to:
train an object detection model using the augmented point cloud data (see paras. 49 and 70).
Regarding claim 11, Kim teaches a method performed by an apparatus of a vehicle (see para. 49), the method comprising:
obtaining, via at least one sensor of the vehicle, point cloud data comprising an object (see para. 49),
performing data augmentation of the point cloud data by applying an augmentation technique, wherein the augmentation technique is determined based on a characteristic of the object (see para. 70), and
controlling autonomous driving of a vehicle based on the augmented point cloud data (see para. 49), wherein the performing of the data augmentation comprises:
determining augmentation application intensity based on at least one of a distance or a degree of occlusion of the object (see paras. 82-84 and Fig. 9).
Regarding claim 21, Kim teaches the object detection apparatus of claim 1,
wherein the distance comprises a distance between a point of the object and a point of the vehicle (see para. 49 for evidence of a measured distance to a point on an object in relation to a host vehicle).
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.
Claims 2-4 and 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Choi et al. (Part-Aware Data Augmentation for 3D Object Detection in Point Cloud [2021]), hereinafter Choi.
Regarding claims 2 and 12, Kim teaches the object detection apparatus of claim 1 and the method of claim 11, but fails to teach wherein the processor is configured to perform the data augmentation by:
segmenting the object into a plurality of partitions, determining a density of each of the plurality of segmented partitions, and determining, based on the determined density of each of the plurality of segmented partitions, a valid partition.
However, Choi teaches wherein the processor is configured to perform the data augmentation by:
segmenting the object into a plurality of partitions, determining a density of each of the plurality of segmented partitions, and determining, based on the determined density of each of the plurality of segmented partitions, a valid partition (page 3394 right-hand column, “The density of LiDAR points decreases cubically as the distance of the box increases. As the point density decreases, the shape of the object cannot be fully recognized, which is one of the most significant factors in reducing the performance of LiDAR-based detectors. We propose sparsifying partitions as an augmentation method which makes some dense partitions sparse to improve distant objects’ recognition.”).
Kim and Choi are considered to be analogous to the claimed invention because they are in the same field of point cloud augmentation. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim with the teachings of Grebe with the motivation of being able to isolate and process points belonging to distinct features.
Regarding claims 3 and 13, Kim in view of Choi teaches the object detection apparatus of claim 2 and the method of claim 12, but Kim fails to teach wherein the processor is configured to segment the object by:
determining a quantity of partitions and a partition segmentation scheme based on a type of the object and the characteristic of the object.
However, Choi teaches wherein the processor is configured to segment the object by:
determining a quantity of partitions and a partition segmentation scheme based on a type of the object and the characteristic of the object (page 3393, “Part-aware partitioning is necessary to separate the characteristic sub-parts of an object and it enables more diverse and efficient augmentation than existing methods. Because the location of characteristic parts for each class is different, Car, Pedestrian and Cyclist are divided into 8, 4 and 4 partitions respectively [Fig. 2, First column]. When using partition-based augmentation, instead of applying the same augmentation to the entire object, different augmentations can be applied to each intra-object sub-parts.”)).
Kim and Choi are considered to be analogous to the claimed invention because they are in the same field of point cloud augmentation. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim with the teachings of Choi with the motivation of being able to isolate and process points belonging to distinct features.
Regarding claims 4 and 14, Kim in view of Choi teaches the object detection apparatus of claim 2 and the method of claim 12, but Kim fails to teach wherein the processor is configured to determine the density by:
determining the density using a quantity of a plurality of points of the object and a quantity of points which belong to each partition of the plurality of segmented partitions.
However, Choi teaches wherein the processor is configured to determine the density by:
determining the density using a quantity of a plurality of points of the object and a quantity of points which belong to each partition of the plurality of segmented partitions (see page 3394 right-hand column, where point density relates to both the number of points in a detection and in a partition).
Kim and Choi are considered to be analogous to the claimed invention because they are in the same field of point cloud augmentation. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim with the teachings of Choi with the motivation of being able to segment a point cloud based on point density, which reflects distance to a sensor.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Choi and further in view of Grebe (US 20240402325 A1).
Regarding claims 5 and 15, Kim in view of Choi teaches the object detection apparatus of claim 2 and the method of claim 12, but Kim fails to teach wherein the processor is configured to determine the valid partition by:
comparing the determined density of a selected partition, of the plurality of segmented partitions, with a predetermined threshold, and determining, based on the determined density of the selected partition being greater than the predetermined threshold, the selected partition as the valid partition.
However, Grebe teaches wherein the processor is configured to determine the valid partition by:
comparing the determined density of a selected partition, of the plurality of segmented partitions, with a predetermined threshold, and determining, based on the determined density of the selected partition being greater than the predetermined threshold, the selected partition as the valid partition (para. 7, “In one embodiment, the points are grouped into clusters using a clustering algorithm, such as the DBSCAN clustering algorithm. The clusters are then identified as objects [potential obstacles] or noise [e.g., ground clutter] based on both density and SNR. In another embodiment, a machine learning algorithm is used to group points as potential obstacles.”; paras. 35-37, “Edge points are at the edge of the cluster, and outliers are clearly outside the cluster. The Neighbors are returned as ‘possible observations.’ A ‘possible observation’ is a radar reflection that is possible part of an object. Embodiments include varying, based on a point's SNR, the number neighboring points required for a point to be considered a core point. The lower the SNR, the larger the number of surrounding points required to be considered a core point. 3. Expand cluster. The clusters are then identified or grown starting from identified core points, until points meeting the ‘edge point’ definition are reached. 4. Main loop. The process loops through all the points, calling an ‘expand_cluster’ function on all points until all points have been assigned a cluster ID or identified as outliers.”; Fig. 2, point cloud is partitioned/clustered into clutter and objects).
Kim, Choi, and Grebe are considered to be analogous to the claimed invention because they are in the same field of point cloud augmentation. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim in view of Choi with the teachings of Grebe with the motivation of being able to more accurately segment a detected object.
Claim 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Grebe.
Regarding claims 7 and 17, Kim teaches the object detection apparatus of claim 1 and the method of claim 11, but fails to teach wherein the processor is configured to determine the augmentation application intensity by:
determining a smallest distance of the object among distances between:
an origin with respect to a vehicle coordinate system, and points in the object.
However, Grebe teaches wherein the processor is configured to determine the augmentation application intensity by:
determining a smallest distance of the object among distances between: an origin with respect to a vehicle coordinate system, and points in the object (para. 6, “In embodiments, the density of points around each point is determined. A range is determined for each of the points. The noise threshold is adjusted to be lower for longer range points. A density threshold is adjusted to be lower for longer ranges. The density threshold for a point is required to exceed the density threshold for the point to be classified as part of a potential obstacle.”; Fig. 3, range is determined by the distance between an origin with respect to a vehicle coordinate system and points in a cluster which may be an object).
Kim and Grebe are considered to be analogous to the claimed invention because they are in the same field of point cloud augmentation in vehicle sensing systems. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim with the teachings of Grebe with the motivation of being able to set distance-based bounds of an augmentation intensity.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Kim in view of Song et al. (US 20210284184 A1), hereinafter Song.
Regarding claims 9 and 19, Kim teaches the object detection apparatus of claim 1 and the method of claim 11, but fails to teach wherein the processor is configured to perform the data augmentation by:
determining a final augmentation technique to be applied to the data augmentation based on a selection probability for each predetermined augmentation technique.
However, Song teaches
determining a final augmentation technique to be applied to the data augmentation based on a selection probability for each predetermined augmentation technique (para. 102, “The point cloud augmentation policy 400 is composed of one or more ‘sub-policies’ 402-A-402-N. Each sub-policy, in turn, is composed of one or more transformation operations [e.g., 404-A-404-M], e.g., data point processing operations, e.g., intensity perturbing operations, jittering operations, or dropout operations. As such, each point cloud augmentation policy 400 can be said to define a sequence of multiple transformation operations. Each transformation operation has an associated magnitude [e.g., 406-A-406-M] and an associated probability [e.g., 408-A-408-M]. For convenience, a transformation operation [e.g., 404-A] and its corresponding magnitude [e.g., 406-A] and probability [e.g., 408-A] can be collectively referred to in this document as a ‘transformation tuple’.”; Fig. 4 in view of para. 80, each augmentation/transformation operation has an associated probability of application where operation 404-M is the final transformation operation).
Kim and Song are considered to be analogous to the claimed invention because they are in the same field of point cloud segmentation in vehicle sensing systems. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Grebe with the teachings of Song with the motivation of attempting to optimize data augmentation.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 ERIC K HODAC whose telephone number is (571) 270-0123. The examiner can normally be reached M-Th 8-6.
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, VLADIMIR MAGLOIRE can be reached at (571) 270-5144. 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.
/ERIC K HODAC/Examiner, Art Unit 3648
/OLUMIDE AJIBADE AKONAI/Primary Examiner, Art Unit 3648
Prosecution Insights