DETAILED ACTION
This Office Action is responsive to the Applicant’s submission, filed on June 15, 2026, amending claims 1, 3, 6, 7 and 9, cancelling claims 2 and 5, and adding new claims 10 and 11. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on May 15, 2026 has been considered by the Examiner.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 7, 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2016/0300111 to Cosatto (“Cosatto”), and also over the article entitled “Global tracker: an online evaluation framework to improve tracking quality” by Badie et al. (“Badie”).
Regarding claims 1 and 9, Cosatto describes a process that provides a fast and efficient way to train a classifier to detect arbitrary objects passing in front of a fixed surveillance camera (see e.g. paragraphs 0005 and 0011). Like claimed, Cosatto particularly teaches:
acquiring labeled training data where a track is given as a label to a sequence of images, wherein the track is information representing a time series of a same moving object in the sequence of images and is automatically obtained by a tracker that tracks the same moving object in the sequence of images (see e.g. paragraphs 0005-0006 and 0012: Cosatto discloses that the process includes automatically extracting tracks of moving objects from within a set of video sequences captured by a fixed surveillance camera. Each track represents a time series of the same moving object in a video sequence and is automatically obtained by a tracker, i.e. a tracking method, that tracks the same moving object in in the video sequence – see e.g. paragraphs 0012-0013. An operator labels some of the tracks, which are then used to train a classifier using supervised machine learning – see e.g. paragraphs 0005-0006 and 0013-0014. The computing system necessary for training the classifier thus acquires labeled training data in which a labeled track is given as a label to a sequence of images, wherein the track is information representing a time series of a same moving object in the sequence of images and is automatically obtained by a tracker that tracks the same moving object in the sequence of images.);
a training data generation process that includes:
detecting a moving object in the sequence of images (see e.g. paragraphs 0011-0012: Cosatto teaches generating training data by, in part, identifying moving objects of interest within the set of video sequences by using background subtraction techniques.);
tracking the same moving object in the sequence of images by using the tracker to automatically obtain the track (see e.g. paragraph 0012: Cosatto teaches that an object tracking method is used to track the identified moving objects as they move across the field of view of the camera in the set of video sequences. Like indicated above, the tracking method is considered a tracker like claimed. Cosatto further suggests that the object tracking method generates a track for each identified moving object – see e.g. paragraphs 0012-0013.); and
generating the labeled training data by giving the track as the label to the sequence of images (see e.g. paragraphs 0013-0014: Cosatto teaches that an entire track is labeled, and can then be used to train a classifier. The labeled track thus represents the sequence of images and is used as labeled training data.); and
training an object identification model based on the labeled training data (see e.g. paragraphs 0005-0006 and 0014: like noted above, Cosatto discloses that the labeled tracks are used to train a classifier using supervised machine learning. The classifier is particularly trained to classify objects within image data – see e.g. paragraphs 0002-0004 and 0014 – and is thus considered an “object identification model” like claimed.).
Accordingly, Cosatto teaches a model training method similar to that of claim 1, which is for training an object identification model that is based on machine learning. Cosatto teaches that a video processing system comprising at least one processor can be configured to implement the above-noted tasks (see e.g. paragraph 0017). Such a video processing system for implementing the above-described teachings of Cosatto is considered a model training system similar to that of claim 9, which trains an object identification model that is based on machine learning. Cosatto, however, does not explicitly disclose that the training data generation process includes a track integration process that includes: (i) detecting two or more different tracks that are given to the same moving object; (ii) integrating the two or more different tracks into a single track; and (iii) determining an occurrence of the two or more different tracks such that the two or more different tracks are given to the same moving object based on an exit from a field of view of a camera and a re-entry to the field of view of the camera, as is further required by claims 1 and 9.
Badie generally describes an evaluation framework for estimating object detection and tracking quality during runtime (see e.g. the Abstract). Regarding the claimed invention, Badie particularly teaches that such a framework can be applied in a track integration process that includes (i) detecting two or more tracks (i.e. “tracklets”) that are given to the same moving object; (ii) integrating (i.e. merging) the two or more tracks into a single track; and (iii) determining an occurrence of the two or more different tracks such that the two or more different tracks are given to the same moving object based on an exit from a field of view of a camera and a re-entry to the field of view of the camera (e.g. if the object leaves the scene and comes back) (see e.g. the Abstract, section 3.1 “Tracklets” and section 3.4 “Re-acquisition and re-identification”).
It would have been obvious to one of ordinary skill in the art, having the teachings of Cosatto and Badie before the effective filing date of the claimed invention, to modify the method and system taught by Cosatto so as to further apply a track integration process like taught by Badie, wherein the track integration process comprises: (i) detecting two or more different tracks that are given to the same moving object; (ii) integrating the two or more different tracks into a single track; and (iii) determining an occurrence of the two or more different tracks such that the two or more different tracks are given to the same moving object based on an exit from a field of view of a camera and a re-entry to the field of view of the camera. It would have been advantageous to one of ordinary skill to utilize such a combination because it would ensure the same object is labeled consistently (i.e. with the same track id) in the video, as is evident from Badie (see e.g. the Abstract and section 3.4 “Re-acquisition and re-identification”). Accordingly, Cosatto and Badie are considered to teach, to one of ordinary skill in the art, a method like that of claim 1 and a system like that of claim 9.
As per claim 7, it would have been obvious, as is described above, to modify the method taught by Cosatto so as to further apply a track integration process like taught by Badie. Badie suggests that result of the track integration process is reflected in the labeled tracks (e.g. two tracklets for the same object are given the same id) (see e.g. section 3.4 “Re-acquisition and re-identification”). Like noted above, Cosatto teaches that the labeled tracks are used as training data (see e.g. paragraphs 0005-0006 and 0014). It thus follows that a result of the track integration process is reflected in the labeled training data (i.e. the labeled tracks). Accordingly, the above-described combination of Cosatto and Badie is further considered to teach a model training method like that of claim 7.
As per claim 10, Cosatto further teaches training the object identification model based on the labeled training data including supervised learning or semi-supervised learning of the object identification model (see e.g. paragraph 0005 and 0014: Cosatto discloses that the labeled tracks, i.e. the labeled training data, is used to train a classifier using supervised machine learning. Like noted above, the classifier is considered an object identification model.). Accordingly, the above-described combination of Cosatto and Badie is further considered to teach a model training method like that of claim 10.
Claims 3 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Cosatto and Badie described above, and also over WIPO Publication No. WO 2021/201774 A1 to Wang et al. (“Wang”).
Regarding claim 3, Cosatto and Badie teach a model training method like that of claim 1, as is described above, and which comprises steps for detecting a moving object in a sequence of images and for tracking the same moving object in the sequence of images by using a tracker. Cosatto further teaches using a bounding box to represent a location of the detected moving object in the sequence of images (see e.g. paragraphs 0006 and 0012). Cosatto and Badie, however, do not explicitly disclose that the tracker tracks the same moving object based on a movement of the bounding box, without performing feature extraction, as is further required by claim 3.
Wang nevertheless describes a tracker for tracking a moving object within a sequence of images, wherein a target object label (e.g. a bounding box) is applied to each image in the sequence to represent a location of the moving object in the sequence of images, and the tracker tracks the same moving object in the sequence of images based on a movement of the bounding box, without performing feature extraction (i.e. by detecting the bounding box movement instead of movement of the object itself) (see e.g. page 2, line 20 – page 3, line 6; page 3, lines 18-23; page 20, lines 15-27; and page 21, line 27 – page 22, line 12).
It would have been obvious to one of ordinary skill in the art, having the teachings of Cosatto, Badie and Wang before the effective filing date of the claimed invention, to modify the method taught by Cosatto and Badie so as to use the tracker taught by Wang to track the moving objects in the sequence of images, whereby a bounding box represents a location of a detected moving object in the sequence of images, and the tracker tracks the same moving object based on a movement of the bounding box, without performing feature extraction. It would have been advantageous to one of ordinary skill to utilize such a tracker because it can improve the accuracy of the object detection and tracking, as is taught by Wang (see e.g. page 3, lines 1-6). Accordingly, Cosatto, Badie and Wang are considered to teach, to one of ordinary skill in the art, a model training method like that of claim 3.
As per claim 4, it would have been obvious, as is described above, to modify the method taught by Cosatto and Badie so as to use the tracker taught by Wang to track the moving objects in the sequence of images. Wang particularly teaches that the tracker associates multiple bounding boxes representing the same moving object in the sequence of images with each other (e.g. based on a threshold distance), and provides a track comprising information indicating the multiple bounding boxes representing the same moving object in the sequence of images (see e.g. page 21, line 27 – page 22, line 12; and page 23, lines 1-18). Accordingly, the above-described combination of Cosatto, Badie and Wang is further considered to teach a method like that of claim 4.
Claims 6 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Cosatto and Badie described above, and also over U.S. Patent No. 12,236,685 to Pan et al. (“Pan”).
Regarding claim 6, Cosatto and Badie teach a model training method like that of claim 1, as is described above, and which comprises steps for detecting a moving object in a sequence of images and for tracking the same moving object in the sequence of images by using a tracker. As particularly described above, it would have been obvious to modify the method taught by Cosatto so as to further apply a track integration process like taught by Badie. Badie suggests that the track integration process (i.e. a re-acquisition step and re-identification step) includes calculating a degree of similarity between moving objects based on an extracted feature amount of each moving object (i.e. clustering the tracks based on the similarities of their object features), and determining that a first moving object of a first track and a second moving object of a second track are identical based on the degree of similarity (i.e. if the tracks are in the same cluster) and integrating the first track and the second track into the single track (see e.g. the Abstract, section 3.1 “Tracklets” and section 3.4 “Re-acquisition and re-identification”). Cosatto and Badie, however, do not explicitly disclose that the track integration process includes: (i) inputting the sequence of images into a feature extraction model to extract a feature amount of each moving object detected in the sequence of images and calculating a degree of similarity between moving objects based on the extracted feature amount; and (ii) when the degree of similarity between a first moving object of a first track and a second moving object of a second track is higher than a threshold, determining that the first moving object and the second moving object are identical and integrating the first track and the second track into the single track, as is required by claim 6.
Pan nevertheless describes a track integration process that includes (i) inputting a sequence of images into a feature extraction model to extract a feature amount of each moving object (e.g. pedestrian) detected in the sequence of images and calculating a degree of similarity between the moving objects based on the extracted feature amount; and (ii) when the degree of similarity between a first moving object of a first track and a second moving object of a second track is higher than a threshold, determining that the first moving object and the second moving object are identical and integrating the first track and the second track into a single track (see e.g. column 2, line 63-67; column 3, line 28 – column 4, line 18; column 5, lines 7-22; and column 7, line 48 – column 8, line 2).
It would have been obvious to one of ordinary skill in the art, having the teachings of Cosatto, Badie and Pan before the effective filing date of the claimed invention, to modify the method taught by Cosatto and Badie such that the track integration process includes: (i) inputting the sequence of images into a feature extraction model to extract a feature amount of each moving object detected in the sequence of images and calculating a degree of similarity between moving objects based on the extracted feature amount; and (ii) when the degree of similarity between a first moving object of a first track and a second moving object of a second track is higher than a threshold, determining that the first moving object and the second moving object are identical and integrating the first track and the second track into the single track, as is taught by Pan. It would have been advantageous to one of ordinary skill to utilize such a combination because it can provide a relatively efficient means to determine if two tracks belong to the same object, as is evident from Pan (see e.g. column 2, line 63-67; column 3, line 28 – column 4, line 18; and column 5, lines 7-22; and column 7, line 48 – column 8, line 2). Accordingly, Cosatto, Badie and Pan are considered to teach, to one of ordinary skill in the art, a model training method like that of claim 6.
Regarding claim 11, Cosatto and Badie teach a model training method like that of claim 1, as is described above, and which comprises steps for detecting a moving object in a sequence of images and for tracking the same moving object in the sequence of images by using a tracker. As particularly described above, it would have been obvious to modify the method taught by Cosatto so as to further apply a track integration process like taught by Badie. Badie suggests that the track integration process (i.e. a re-acquisition step and re-identification step) includes acquiring tracking result data, and checking whether or not there are overlapping tracks (i.e. multiple tracklets for the same object) based on the tracking result data and a degree of similarity between detected moving objects (see e.g. the Abstract, section 3.1 “Tracklets” and section 3.4 “Re-acquisition and re-identification”). Cosatto and Badie, however, do not explicitly teach checking whether or not there are overlapping tracks based on the tracking result data and a degree of similarity between detected moving objects relative to a threshold, as is required by claim 11.
Pan nevertheless describes a track integration process that includes acquiring tracking result data, and checking whether or not there are overlapping tracks based on the tracking result data and a degree of similarity between detected moving objects relative to a threshold (see e.g. column 2, line 63-67; column 3, line 28 – column 4, line 18; column 5, lines 7-22; and column 7, line 48 – column 8, line 2).
It would have been obvious to one of ordinary skill in the art, having the teachings of Cosatto, Badie and Pan before the effective filing date of the claimed invention, to modify the method taught by Cosatto and Badie such that the track integration process includes acquiring tracking result data, and checking whether or not there are overlapping tracks based on the tracking result data and a degree of similarity between detected moving objects relative to a threshold, as is taught by Pan. It would have been advantageous to one of ordinary skill to utilize such a combination because it can provide a relatively efficient means to determine if two tracks belong to the same object, as is evident from Pan (see e.g. column 2, line 63-67; column 3, line 28 – column 4, line 18; and column 5, lines 7-22; and column 7, line 48 – column 8, line 2). Accordingly, Cosatto, Badie and Pan are considered to teach, to one of ordinary skill in the art, a model training method like that of claim 11.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over the combination of Cosatto and Badie described above, and also over U.S. Patent Application Publication No. 2022/0092348 to Jakobsen et al. (“Jakobsen”).
Regarding claim 8, Cosatto and Badie teach a model training method like that of claim 1, as is described above, which comprises steps for acquiring labeled training data and for training an object identification model based on the labeled training data. Cosatto and Badie, however, do not explicitly teach that object identification model is a human re-identification model, as is required by claim 8.
Jakobsen nevertheless teaches generating training data from a sequence of images, wherein the training data is used for training an object identification model that is based on machine learning, and particularly where the object identification model is a human re-identification model (see e.g. paragraphs 0002-0003 and 0006-0008).
It would have been obvious to one of ordinary skill in the art, having the teachings of Cosatto, Badie and Jakobsen before the effective filing date of the claimed invention, to modify the method taught by Cosatto and Badie so as to use the generated training data to train an object identification that is a human re-identification model like taught by Jakobsen. It would have been advantageous to one of ordinary skill to utilize such a combination, because it would provide for a more efficient training, as is suggested by Jakobsen (see e.g. paragraphs 0003 and 0022). Accordingly, Cosatto, Badie and Jakobsen are considered to teach, to one of ordinary skill in the art, a model training method like that of claim 8.
Response to Arguments
The Examiner acknowledges the Applicant’s amendments to claims 1, 3, 6, 7 and 9, cancellation of claims 2 and 5, and addition of new claims 10 and 11. In response to these amendments, the 35 U.S.C. § 112(b) rejection presented in the previous Office Action to claim 7 is respectfully withdrawn, as are the 35 U.S.C. § 101 rejections presented in the same Office Action to claims 1-9. Moreover, the double patenting rejection presented in the previous Office Action is respectfully withdrawn in light of the Terminal Disclaimer filed on June 15, 2026.
The Applicant’s arguments addressing the 35 U.S.C. §§ 102 and 103 rejections presented in the previous Office Action have been considered, but are moot in view of the new grounds of rejection presented above, which are required in response to the Applicant’s amendments.
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 BLAINE T BASOM whose telephone number is (571)272-4044. The examiner can normally be reached Monday-Friday, 9:00 am - 5:30 pm, 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, Matt Ell can be reached at (571)270-3264. 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.
/BTB/
8/27/2026
/MATTHEW ELL/Supervisory Patent Examiner, Art Unit 2141
Prosecution Insights