DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . The Amendment filed 1 January, 2026 (hereinafter “the Amendment’) has been entered and considered. Claims 1, 8, 10, 15, 22, and 24 have been amended. Claims 1-28, all the claims pending in the application, are rejected. All modifications to the rejection set forth in the present action were necessitated by Applicants’ claim amendments; accordingly, this action is made final.
Remarks
2. 35 USC §112(b)
The 112(b) rejections are withdrawn in view of the amendments.
Prior Art Rejections
On page 9-10 of the Amendment, the Applicant contends that Yuan does not teach or suggest “match the key points and the associated feature descriptors related to the one or more other vehicles to the key points and the associated feature descriptors related to the first vehicle” and “wherein the combined image is generated by stitching together the view of the first vehicle and the at least one ROI view of the at least one vehicle.”
The Applicant further contends that Yuan’s description of “BBox matching” clusters and merges bounding boxes from different cooperative vehicles by aligning and merging the bounding boxes rather than “matching key points and associated feature descriptors,”, as amended claim 1 recites. The Examiner respectfully disagrees and points to the Non-Final Rejection of 17 October, 2025, where the Examiner relies on Yuan, §III, §§A: “In our proposed framework, the cooperative CAV Ci (1 _ i _ Nv) generates and shares to the ego CAV C0 the CPMi that contains Bi, the selected and aggregated deep feature information Fi and the coordinates of Ki keypoints”, and Yuan, §III, §§B, P[001]: “the shared features are fused”, where it is explicitly disclosed that the CPMi is shared between vehicles which contain the Bi information which contains the deep feature information Fi and the coordinates of the keypoints, where Fi are the associated feature descriptors to the coordinates of the shared keypoints. Furthermore, fusion provides matching, see Fig. 2. Furthermore, Fig. 2-3 disclose matching keypoints, not just bounding boxes, and the bounding boxes contain the keypoints that are matched.
The applicant further states that claim 1 requires that the combined image is generated by stitching together the vehicles views and contends that Yuan outputs refined 3D bounding boxes and classification scores, not a stitched together view of the multiple vehicles. The Examiner respectfully disagrees and points to Gutke, Fig. 1 where it shows the EGO vehicle which has its own “view” which contains the keypoints acquired by the EGO itself, the EGO vehicle also receives CPM, which contains the deep feature information and the coordinates of keypoints from a second vehicle, which are then fused/stitched to the EGO’s view where overlapping keypoints are matched and the EGO’s view is then updated. View, as understood by the Examiner, describes what the EGO/1st vehicle can “see”, where the vehicle “sees” keypoints, therefore when keypoints are shared from a secondary vehicle to the first EGO vehicle, the points are matched and “stitched” together and it provides an updated view, as seen by the 1st EGO vehicle. The language of the claim does not require that the output is a 2D image/photograph of two separate “view-points” that were stitched together from separate vehicle views.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
3. Claims 1-2, 4-9, 15-16 and 18-23 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by “Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving” by Yunshuang Yuan et al., (herein after “Yuan”).
Regarding claim 1,
An apparatus for wireless communications (Yuan, §I, P[001]: “cooperative perception based on connected and automated vehicles (CAVs) can effectively mitigate these problems by sharing sensed information collected from different viewing directions of multiple AVs in a network. The perceived information is shared among vehicles via Collective Perception Messages (CPMs).”), the apparatus comprising:
at least one memory the (Yuan, §IV, §§C, P[002]: “Nvidia 1080Ti GPU”, where the instructions are stored in a memory.); and
at least one processor (Yuan, §IV, §§C, P[002]: “Nvidia 1080Ti GPU”) coupled to the at least one memory and configured to:
receive, from a first vehicle, a view request for a visual view of a region of interest (ROI) (Yuan, Fig. 2 discloses the sharing of two ROIs withing feature extraction, which requires requesting the appropriate data to be transmitted.);
output, for transmission to the first vehicle and one or more other vehicles, an information request for key points and associated feature descriptors related to a view of the first vehicle and key points and associated feature descriptors related to one or more respective views of the one or more other vehicles is disclosed by Yuan in Fig. 2, where the two ROIs are shared and the keypoints with their associated feature descriptors are combined by matching, see Yuan, §III, §§A: “In our proposed framework, the cooperative CAV Ci (1 _ i _ Nv) generates and shares to the ego CAV C0 the CPMi that contains Bi, the selected and aggregated deep feature information Fi and the coordinates of Ki keypoints”, and Yuan, §III, §§B, P[001]: “the shared features are fused”, where for the transfer of data to take place, a request for the pertinent data is made.;
match the key points and the associated feature descriptors related to the one or more other vehicles to the key points and the associated feature descriptors related to the first vehicle is disclosed by Yuan, §III, §§A: “In our proposed framework, the cooperative CAV Ci (1 _ i _ Nv) generates and shares to the ego CAV C0 the CPMi that contains Bi, the selected and aggregated deep feature information Fi and the coordinates of Ki keypoints”, and Yuan, §III, §§B, P[001]: “the shared features are fused”;
determine, based on the matching, at least one vehicle of the one or more other vehicles to provide at least one ROI view of the ROI (Yuan, §III, §§B, P[006]: “This aggregation is achieved by a VSA-based RoI-grid pooling module which is originally proposed by [6]. It divides the proposal box into regular grids and summarizes the neighboring keypoints information for each grid center. The aggregated grid features are then stretched to a vector and fed to the fully connected layers to generate the final cooperative detection result which contains a binary classification between positive and negative proposals and the proposal box refinement regression.”);
determine at least one mapping between the at least one vehicle and the first vehicle (Yuan, Fig. 2, the coordinates and poses are shared and mapped, and the feature maps are also shared; Yuan, §IV, §§B: “the shared feature maps”); and
combine, using the at least one mapping, the at least one ROI view of the at least one vehicle with the view of the first vehicle to generate a combined image having the visual view of the ROI, wherein the combined image is generated by stitching together the view of the first vehicle and the at least one ROI view of the at least one vehicle. (Yuan, Fig. 2, Fusion & Detection: frame showing combined points, and see Fig. 1 of Yuan and the description of Fig. 1., where the information is shared to the EGO vehicle to update its ROI view. Fig. 1 shows the EGO vehicle which has its own “view” which contains the keypoints acquired by the EGO itself, the EGO vehicle also receives CPM, which contains the deep feature information and the coordinates of keypoints from a second vehicle, which are then fused/stitched to the EGO’s view where overlapping keypoints are matched and the EGO’s view is then updated. View, as understood by the Examiner, describes what the EGO/1st vehicle can “see”, where the vehicle “sees” keypoints, therefore when keypoints are shared from a secondary vehicle to the first EGO vehicle, the points are matched and “stitched” together and it provides an updated view, as seen by the 1st EGO vehicle.).
Regarding claim 2, wherein the at least one processor is configured to output the combined image for transmission to the first vehicle is disclosed by Yuan in Fig. 1, where the information is output to the EGO vehicle.
Regarding claim 4, wherein a shape of the ROI is one of a circle, a square, a rectangle, a triangle, or a polygon is disclosed by Yuan in Fig. 2, where the ROI is a “grid”.
Regarding claim 5, wherein the view request comprises coordinates for the ROI and at least one of a raw image or a compressed image is disclosed by Yuan in §III, §§B, P[004]: “we compose the CPMi with the sensor pose of CAV Ci , proposals Bi , coordinates and features of keypoints”, and §IV, §§B, P[002]: “We take the raw data fusion strategy as a baseline. This strategy avoids any data loss during sharing, hence is more likely to perform best”
Regarding claim 6, wherein the view request comprises at least one of vehicle information of the first vehicle or camera information of the first vehicle is disclosed by Yuan in Fig. 1, where it discloses that information is sent to the EGO vehicle, therefore the information request comprises EGO vehicle information.
Regarding claim 7, wherein the vehicle information comprises at least one of a location of the first vehicle, a make of the first vehicle, or a model of the first vehicle (Yuan, Fig. 1 shows the location of the first vehicle, and the coords of the location are known to fuse keypoints of the image.).
Regarding claim 8, wherein the view request comprises the camera information of the first vehicle, and wherein the camera information comprises at least one of a camera rotation, camera intrinsic parameters, or camera extrinsic parameters of a camera of the first vehicle (Yuan, §III, §§B, P[004]: “. For the point cloud PCi , we compose the CPMi with the sensor pose of CAV Ci , proposals Bi , coordinates and features of keypoints”).
Regarding claim 9, wherein the information request comprises at least one of a key point detection method to use for detecting the key points, one or more types of the associated feature descriptors, a number of the key points and the associated feature descriptors, a request that the key points are uniformly sampled in an image space, at least one of a raw image or a compressed image, or intrinsic parameters of a camera (Yuan, §III, §§B, P[004]: “. For the point cloud PCi , we compose the CPMi with the sensor pose of CAV Ci , proposals Bi , coordinates and features of keypoints”).
Regarding claim 15, A method for wireless communications by a device is disclosed by Yuan in §V, §§B, P[003]: “the wireless network can handle larger CPMs,”
Claims 15-16 and 18-23 recite features nearly identical to those recited in claims 1-2 and 4-9,
respectively. Claims 15-16 and 18-23 are rejected for reasons analogous to those discussed above in conjunction with claims 1-2 and 4-9, respectively.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
4. Claims 3, 12-13, 17, and 26-27 are rejected under 35 U.S.C. 103 as being unpatentable over Yuan in view of “EMP: Edge-assisted Multi-vehicle Perception” by Xumiao Zhang et al., (herein after “Zhang”).
Regarding claim 3, Yuan discloses that the vehicles share information based on proximity (Yuan, §IV, §§A: “communication range within 40 m”) and does not explicitly disclose wherein the apparatus is a car-to-cloud (C2C) server.
However, Zhang discloses wherein the apparatus is a car-to-cloud (C2C) server in the §Abstract: “In EMP, multiple nearby CAVs share their raw sensor data with an edge server which then merges CAVs’ individual views to form a more complete view with a higher resolution.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yuan to utilize and edge cloud server, as taught by Zhang, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have provided the benefit of reducing end-to-end latency.
Regarding claim 12, wherein the number of the key points is based on an intensity metric for each of the key points which is inherently found within point cloud keypoints, as disclosed by Zhang in §2.3, bottom of the page, “1A point cloud contains ∼130K points (64 vertical angles and 2083 horizontal angles) consisting of location and intensity information (𝑥 𝑦𝑧-𝑖, 4 floating-point numbers).”, where if the intensity of the incident light is too low, then no keypoint is produced from the LiDAR detection.
Regarding claim 13, wherein the intensity metric for each of the key points is specified as a sharpness of a corner in a Harris corner measure describes an innate feature of the Harris detection method, where a higher corner score directly corresponds to a sharper corner because the score reflects a large variation in intensity across all directions within a local window, which is a defining characteristic of a sharp corner, see attached Harris Corner Detector Wiki Article.
Claims 17 and 26-27 recite features nearly identical to those recited in claims 3 and 12-13,
respectively. Claims 17 and 26-27 are rejected for reasons analogous to those discussed
above in conjunction with claims 3 and 12-13, respectively.
5. Claims 10-11 and 24-25 are rejected under 35 U.S.C. 103 as being unpatentable over Yuan in view of US 20180232947 A1 by Youval Nehmadi et al., (herein after “Nehmadi”).
Regarding claim 10, as best understood, Yuan does not explicitly disclose wherein the key point detection method is one of a Harris corner detector, a features from an accelerated segment test (FAST) method, or a speeded up robust features (SURF), that is, Yuan does not disclose that the keypoint detector is specifically a Harris method, FAST method, or SURF method.
However, Nehmadi discloses using a Harris keypoint detection method in P[0120]: “These locations can be further refined using feature tracking, which may be calculated 1011 using an appropriate detector, such as a Harris, DoG or Lucas-Kanade-Tomasi tracker. These features may be characterized using SIFT, SURF, ORB, FREAK or other suitable descriptors.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yuan to incorporate a Harris keypoint detection method, as taught by Nehmadi, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have provided the benefit of increasing accuracy in detection for distinguishing between edges and corners.
Regarding claim 11, wherein the one or more types of the associated feature descriptors comprises at least one of a binary robust independent elementary features (BRIEF), an orientated fast and rotated BRIEF (ORB), or a speeded up robust features (SURF) is disclosed by Nehmadi in P[0120]: “These locations can be further refined using feature tracking, which may be calculated 1011 using an appropriate detector, such as a Harris, DoG or Lucas-Kanade-Tomasi tracker. These features may be characterized using SIFT, SURF, ORB, FREAK or other suitable descriptors.”
Claims 24-25 recite features nearly identical to those recited in claims 10-11, respectively. Claims 24-25 are rejected for reasons analogous to those discussed above in conjunction with claims 10-11, respectively.
6. Claims 14 and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Yuan as applied to Claim 1 above, in view of US 20200236401 A1 by Danillo Graziosi, (herein after “Graziosi”).
Regarding claim 14, wherein the at least one mapping comprises at least one homography (Yuan, Fig. 2, the coordinates and poses are shared and mapped, and the feature maps are also shared; Yuan, §IV, §§B: “the shared feature maps”). The features are mapped to the EGO vehicles perspective as shown in in the description of Fig. 1 which utilizes a type of 3D homography to spatially link together the separate detections/3D image, instead of 2D. Yuan lacks specifically utilizing a homography matrix for mapping purposes. Graziosi discloses utilizing a 3D homography for mapping in §Abstract: “A method of point cloud coding using homography transform sends the homography transform of the 3D patches, instead of the explicit projection values (such as bounding boxes and patch orientation, rotation). The method has a more compact notation, is more efficient in terms of transmission, and allows for a faster decoding, particularly in cases where the 3D points will be reprojected.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yaun to incorporate 3D Homography for mapping, as taught by Graziosi, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have provided the benefit of increased data transmission efficiency.
Claim 28 recites features nearly identical to those recited in claim 14. Claim 28 is rejected for reasons analogous to those discussed above in conjunction with claim 14.
7. Claims 1-2, 4-9, 15-16 and 18-23 are rejected under 35 U.S.C. 103 as being unpatentable over Yuan as applied to Claim 1 above, in view of “Cooperative Perception With V2V Communication for Autonomous Vehicles” by Hieu Ngo et al., (herein after “Ngo”).
Regarding claims 1 and 15, where “stitching together the view(s)” means more than sharing and fusing of matching keypionts from separate vehicles, Ngo makes explicit what Yao discloses implicitly.
Ngo discloses combine, using the at least one mapping, the at least one ROI view of the at least one vehicle with the view of the first vehicle to generate a combined image having the visual view of the ROI, wherein the combined image is generated by stitching together the view of the first vehicle and the at least one ROI view of the at least one vehicle in Fig. 2 where it is explicitly shown that a combined image is generated based on the stitching of two separate BEV maps from different viewpoints, Ngo, §III, §§Algorithm 2: “to apply BEV map stitching to get the final BEV map”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Yuan to stitch together shared V2V information, as taught by Ngo, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have provided the benefit of improving route planning modules for vehicles.
Conclusion
8. THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TY M BEATTY whose telephone number is (703) 756-5370. The examiner can normally
be reached Mon-Fri: 8AM-4PM EST..
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,
Gregory Morse can be reached on (571) 272 - 3838. 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.
/TY MITCHELL BEATTY/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698