Prosecution Insights
Last updated: April 19, 2026
Application No. 18/505,732

MACHINE LEARNING MODEL FOR MULTI-CAMERA MULTI-PERSON TRACKING

Non-Final OA §101§103
Filed
Nov 09, 2023
Examiner
LIN, JESSICA YIFANG
Art Unit
2668
Tech Center
2600 — Communications
Assignee
NEC Laboratories America Inc.
OA Round
2 (Non-Final)
75%
Grant Probability
Favorable
2-3
OA Rounds
2y 3m
To Grant
99%
With Interview

Examiner Intelligence

Grants 75% — above average
75%
Career Allow Rate
3 granted / 4 resolved
+13.0% vs TC avg
Strong +33% interview lift
Without
With
+33.3%
Interview Lift
resolved cases with interview
Typical timeline
2y 3m
Avg Prosecution
29 currently pending
Career history
33
Total Applications
across all art units

Statute-Specific Performance

§101
7.9%
-32.1% vs TC avg
§103
53.5%
+13.5% vs TC avg
§102
32.7%
-7.3% vs TC avg
§112
4.0%
-36.0% vs TC avg
Black line = Tech Center average estimate • Based on career data from 4 resolved cases

Office Action

§101 §103
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 . Information Disclosure Statement The information disclosure statement (IDS) submitted on November 9, 2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception without significantly more. Claim 1 is directed to a method for tracking movement. Under Step 2A Prong One, the claim recites abstract ideas including: (1) Mathematical concepts: "generating scores for pairs of detection images" (mathematical calculations), "generating a pairwise detection graph using the detection images as nodes and the scores as weighted edges" (mathematical relationships and graph theory), and "constrained answer set programming problem" (mathematical algorithms and optimization); (2) Mental processes: "performing person detection" (observation), "combining visual and location information" (evaluation and comparison that can be performed in the human mind or with pen and paper), and "tracking movement of an individual based on ... logical assumptions" (mental process of observation and logical reasoning); (3) Certain methods of organizing human activity: "tracking movement of an individual" (managing information about human behavior and movement). Under Step 2A Prong Two, the claim does not integrate the judicial exception into a practical application. The additional elements amount to: (1) generic data sources ("multiple video streams," "frames"), (2) insignificant extra-solution activity ("performing an action responsive to the tracked movement"), and (3) mere instructions to apply the abstract idea in the field of video surveillance (field of use). These elements do not improve the functioning of a computer or other technology, do not effect a particular transformation, and do not apply the abstract idea with a particular machine in a meaningful way. Under Step 2B, the additional elements do not provide an inventive concept. The elements represent well-understood, routine, conventional activity in the art, including: using conventional person detection techniques, performing routine data combinations, using standard graph data structures, and applying known optimization algorithms. The specification acknowledges using known techniques such as re-identification models (ResNet, VIT networks) and standard camera projection mathematics. Claims 2-9 depend from Claim 1 and add limitations that are also well-understood, routine, conventional activities that do not amount to significantly more than the judicial exception. Claim 10 recites the same abstract ideas as Claim 1 in system format. The recitation of generic computer components ("hardware processor," "memory") does not integrate the judicial exception into a practical application or provide significantly more. Claims 11-18 depend from Claim 10 and are ineligible for the same reasons as Claims 2-9. Claim 19 recites the same abstract ideas as Claim 1 with the addition of "in a healthcare facility" (field of use limitation) and "generating a report for a healthcare professional for decision making related to a patient's treatment" (insignificant post-solution activity of applying the result). These limitations do not integrate the abstract idea into a practical application or provide significantly more. Claim 20 depends on Claim 19 and is ineligible for the same reasons. To overcome this rejection, applicant could: I. Add specific technical improvements to camera systems or video processing 2. Recite unconventional implementation details of the answer set programming approach 3. Claim specific technical features that provide more than routine data processing 4. Provide evidence that the combination produces unexpected results 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. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claim(s) 1-5, 8-14, 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (Chinese Patent CN 112131904 A) in view of Suchan, Jakob, et al. "Visual explanation by high-level abduction: On answer-set programming driven reasoning about moving objects." Proceedings of the AAAI conference on artificial intelligence. Vol. 32. No. 1. 2018. (Year: 2018), Shen, Yantao, et al. "Person re-identification with deep similarity-guided graph neural network." Proceedings of the European conference on computer vision (ECCV). 2018. (Year: 2018), and Buehler et. al. (European Patent EP-1563686-B1) . Regarding claim 1, Wu discloses a method for tracking movement, comprising: performing person detection in frames from multiple video streams to identify detection images (Wu, Abstract). PNG media_image1.png 262 732 media_image1.png Greyscale However, Wu fails to teach combining visual and location information from the detection images to generate scores for pairs of detection images across the multiple video streams and across frames of respective video streams; generating a pairwise detection graph using the detection images as nodes and the scores as weighted edges; tracking movement of an individual based a constrained answer set programming problem, with constraints determined based on matching scores and logical assumptions; and performing an action responsive to the tracked movement. Shen teaches combining visual and location information from the detection images to generate scores for pairs of detection images across the multiple video streams and across frames of respective video streams (Shen, 3.1 Graph Formulation and Node Features, by inputting image pair into a Siamese-CNN for pairwise relation feature encoding); generating a pairwise detection graph using the detection images as nodes and the scores as weighted edges (Shen, 3.2 Similarity-Guided Graph Neural Network, establish edges E on graph G where the node features are updated as a weighted addition fusion). PNG media_image2.png 886 1098 media_image2.png Greyscale PNG media_image3.png 662 1110 media_image3.png Greyscale Suchan teaches tracking movement of an individual based a constrained answer set programming problem (Suchan, A Hybrid Architecture for Visual Explanation based on the integration of high-level abductive reasoning within Answer Set Programming (ASP)), with constraints determined based on matching scores and logical assumptions (Suchan, Figure 2 People Movement, Beliefs as (Spatial) constraints). PNG media_image4.png 436 494 media_image4.png Greyscale PNG media_image5.png 340 948 media_image5.png Greyscale Buehler et. al. teaches performing an action responsive to the tracked movement (Buehler et. al. [0104]). PNG media_image6.png 76 748 media_image6.png Greyscale Shen is analogous to the claimed invention because it is reasonably pertinent to the problem of person reidentification, which aims at finding the person in images of interest in a set of images across different cameras without error in the intelligent surveillance systems. Suchan is analogous to the claimed invention because it addresses the answer set programming problem for visual perception and object tracking of moving people in the setting of movies. Buehler et. al. is analogous to the claimed invention because it pertains to surveillance, security, public safety, and tracking human movement. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method for video surveillance of Wu to incorporate the teachings of Shen, Suchan, and Buehler et. al. so that the solution of the claimed invention is fully addressed and to have a more robust and accurate person image feature representation. Regarding claim 2, the combination of Wu, Suchan, Shen, and Buehler et. al. discloses the method of claim 1. Buehler et. al. further teaches further comprising synchronizing the multiple video streams to identify temporal correspondences between frames of the multiple video streams (Buehler et. al. Figures 1, 5). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have included the teachings of Buehler et. al. with the teachings of Wu, Suchan, and Shen so that the multiple video streams are observed for a substantially long period of recorded time. PNG media_image7.png 750 574 media_image7.png Greyscale Regarding claim 3, the combination of Wu, Shen, Suchan, and Buehler et.al. discloses the method of claim 1. Buehler et. al. further teaches further comprising extracting the visual information based on a visual similarity between detection images (Buehler et. al. Figures 6A, 6B, 7A, 7B). It is important to the claimed invention to have identified a target of visual similarity that defines the human of interest. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Buehler et. al. with the combination of Wu, Shen, and Suchan so that there is an objective target identified. Regarding claim 4, the combination of Wu, Shen, Suchan, and Buehler et. al. discloses the method of claim 1. Suchan further teaches further comprising extracting the location information based on a projection of two-dimensional coordinates into a three-dimensional environment for the detection images and determining a distance between the projected coordinates (Suchan, Ontology: Space, Time, Objects, Events where the tracks of the objects are measured in basic spatial 2D and 3D space coordinates). PNG media_image8.png 502 496 media_image8.png Greyscale PNG media_image9.png 746 492 media_image9.png Greyscale It is important to the claimed invention to have quantified distance between 2D coordinates in a 3D environment. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Suchan with the teachings of Wu, Shen, and Buehler et. al. so that the distance between two defined coordinates between people in a scene is measured and recorded. Regarding claim 5, the combination of Wu, Suchan, Shen, and Buehler et. al. discloses the method of claim 1. Buehler et. al. further teaches wherein generating the pairwise detection graph includes determining edges between detection images from different frames of a same video stream and determining edges between detection images from different video streams at corresponding times (Buehler et. al. Figures 6A, 6B, 7A, 7B). It is critical to the claimed invention to produce a graph that is from pairwise detection results so that the identification of people can be visualized. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Buehler et. al. so that human surveillance solutions can be fully utilized. Regarding claim 10, the rejection analysis of claim 1 is incorporated herein. The combination of Wu, Suchan, Shen, and Buehler et. al. also teaches a system for tracking movement, comprising: a hardware processor (Buehler et. al., [0042]); and a memory that stores a computer program which, when executed by the hardware processor, causes the hardware processor to: (Buehler et. al. [0047], lines 47-48) perform person detection in frames from multiple video streams to identify detection images (Wu, Abstract); combine visual and location information from the detection images to generate scores for pairs of detection images across the multiple video streams and across frames of respective video streams (Shen, 3.1 Graph Formulation and Node Features, by inputting image pair into a Siamese-CNN for pairwise relation feature encoding); generate a pairwise detection graph using the detection images as nodes and the scores as weighted edges (Shen, 3.2 Similarity-Guided Graph Neural Network, establish edges E on graph G where the node features are updated as a weighted addition fusion); track movement of an individual based a constrained answer set programming problem (Suchan, A Hybrid Architecture for Visual Explanation based on the integration of high-level abductive reasoning within Answer Set Programming (ASP)), with constraints determined based on matching scores and logical assumptions (Suchan, Figure 2 People Movement, Beliefs as (Spatial) constraints); and perform an action responsive to the tracked movement (Buehler et. al. [0104]). Shen is analogous to the claimed invention because it is reasonably pertinent to the problem of person reidentification, which aims at finding the person in images of interest in a set of images across different cameras without error in the intelligent surveillance systems. Suchan is analogous to the claimed invention because it addresses the answer set programming problem for visual perception and object tracking of moving people in the setting of movies. Buehler et. al. is analogous to the claimed invention because it pertains to surveillance, security, public safety, and tracking human movement. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method for video surveillance of Wu to incorporate the teachings of Shen, Suchan, and Buehler et. al. so that the solution of the claimed invention is fully addressed and to have a more robust and accurate person image feature representation. Regarding claim 11, the combination of Wu, Suchan, Shen, and Buehler, et. al. teaches the system of claim 10, wherein the computer program further causes the hardware processor to synchronize the multiple video streams to identify temporal correspondences between frames of the multiple video streams (Buehler et. al. Figures 7A, 7B). It is important to the claimed invention to have the complete computer program and hardware necessary to carry out the tasks disclosed. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Buehler et. al. that also includes a system of CCTV surveillance for security purposes. Regarding claim 12, the combination of Wu, Suchan, Shen, and Buehler et. al. teaches the system of claim 10, wherein the computer program further causes the hardware processor to extract the visual information based on a visual similarity between detection images (Buehler et. al. [0089]). PNG media_image10.png 22 736 media_image10.png Greyscale PNG media_image11.png 184 738 media_image11.png Greyscale It is important to the claimed invention to have the complete computer program and hardware necessary to carry out the tasks disclosed. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Buehler et. al. that also includes a system of CCTV surveillance for security purposes. Regarding claim 13, the combination of Wu, Suchan, Shen, and Buehler et. al. further discloses the system of claim 10, wherein the computer program further causes the hardware processor to extract the location information based on a projection of two-dimensional coordinates into a three-dimensional environment for the detection images and determining a distance between the projected coordinates (Suchan, Ontology: Space, Time, Objects, Events where the tracks of the objects are measured in basic spatial 2D and 3D space coordinates). It is important to the claimed invention to have quantified distance between 2D coordinates in a 3D environment. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have included the teachings of Suchan with the teachings of Wu, Shen, and Buehler et. al. so that the distance between two defined coordinates between people in a scene is measured and recorded. Regarding claim 14, the combination of Wu, Suchan, Shen, and Buehler et. al. further teaches the system of claim 10, wherein the computer program further causes the hardware processor to determine edges between detection images from different frames of a same video stream and to determine edges between detection images from different video streams at corresponding times (Buehler Figure 4). PNG media_image12.png 863 339 media_image12.png Greyscale The edge detection of detection images is an important solution to the claimed invention because it reduces error in overlapping video streams with multiple people. Thus, it would have been obvious to one skilled in the art prior to the effective filing date to have included the teachings of Buehler et. al. with the teachings of Wu, Shen, and Suchan to include the solution for edge detection in multiple video frames. Regarding claim 17, the combination of Wu, Suchan, Shen, and Buehler et. al. further teaches the system of claim 10, wherein the computer program further causes the hardware processor to an output from a visual branch to an output of a location branch to combine the visual and location information (Buehler et. al. Figure 15, Figure 4, Figure 1). PNG media_image13.png 696 640 media_image13.png Greyscale This is an important aspect for person identification based on time and location, especially related to personal security. Thus, it would have been obvious to one skilled in the art prior to the effective filing date to have included the teachings of Buehler et. al. so that the information collected is matched to the correct person of interest. Regarding claim 8, the combination of Wu, Shen, Suchan, and Buehler et. al. discloses the method of claim 1. Shen further teaches wherein combining the visual and location information includes adding an output from a visual branch to an output of a location branch (Shen, 2.2 (Graph for Machine Learning)—“After the message propagation among different nodes (samples), the mapping function will output the classification or regression results of each node”). PNG media_image14.png 376 558 media_image14.png Greyscale Shen et. al. is considered analogous to the claimed invention because it is reasonably pertinent to the problem of person reidentification, which aims at finding the person in images of interest in a set of images across different cameras without error in the intelligent surveillance systems. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the method for video surveillance using CAS with greater accuracy of Buehler et. al to incorporate the teachings of Shen et.al by including the re-identification solution of having a more robust and accurate person image feature representation through fusion weights for updating the nodes’ features (Shen et. al 2.2 (Graph for machine learning)). PNG media_image15.png 120 558 media_image15.png Greyscale PNG media_image16.png 182 572 media_image16.png Greyscale Regarding claim 9, Shen in the combination also teaches the method of claim 8, wherein the visual branch includes processing the detection images with a re-identification model (Shen et. al. Abstract). PNG media_image17.png 268 366 media_image17.png Greyscale Regarding 18, the rejection of claim 9 is incorporated herein. Claim(s) 19-20, 6-7, 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Wu (Chinese Patent CN 112131904 A) in view of Suchan, Jakob, et al. "Visual explanation by high-level abduction: On answer-set programming driven reasoning about moving objects." Proceedings of the AAAI conference on artificial intelligence. Vol. 32. No. 1. 2018. (Year: 2018), Shen, Yantao, et al. "Person re-identification with deep similarity-guided graph neural network." Proceedings of the European conference on computer vision (ECCV). 2018. (Year: 2018), and Buehler et. al. (European Patent EP-1563686-B1) as applied to claim 1 and 10 above, and further in view of Johnson et. al. (United States Patent US 12,106,654 B2) and Ross (United States Patent US 2022/0022006A1). Regarding Claim 19, which overlaps substantially in scope as in claim 1 except for “tracking movement in a healthcare facility” and “generating a report for a healthcare professional for decision-making related to a patient’s treatment, based on the tracked movement”. Thus, the rejection of claim 1 based on the combination of Wu, Shen, Suchan, and Buehler is incorporated herein. Wu, Shen, Suchan and Buehler does not teach the limitation “tracking movement in a healthcare facility” as further recited. However, Johnson et. al teaches a method for tracking movement in a healthcare facility, comprising: performing person detection in frames from multiple video streams in a healthcare facility to identify detection images (Abstract, claim 9) PNG media_image18.png 506 504 media_image18.png Greyscale PNG media_image19.png 260 356 media_image19.png Greyscale And generating a report for a healthcare professional for decision-making related to a patient’s treatment, based on the tracked movement (Johnson et. al: Col. 7, lines 62-67, Col. 8, lines 5- 23). PNG media_image20.png 84 320 media_image20.png Greyscale PNG media_image21.png 330 324 media_image21.png Greyscale Johnson is analogous to the claimed invention because it is pertinent to the problem of patient monitoring in a healthcare facility for fall reduction. One of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to incorporate the teaching of Johnson for the benefit of fall mitigation of tracked patients in a healthcare facility. The combination of Wu, Shen, Suchan, Buehler and Johnson fail to teach “generating a report for a healthcare professional for decision-making related to a patient’s treatment, based on the tracked movement” as further recited. However, Ross teaches wherein the action includes generating a report for a healthcare professional for decision-making related to a patient’s treatment, based on tracked movement of the patient (Ross Fig. 1, 3, Abstract). PNG media_image22.png 616 560 media_image22.png Greyscale PNG media_image23.png 726 946 media_image23.png Greyscale Ross is considered analogous to the claimed invention because it is reasonably pertinent to the problem of providing safety and security for patients receiving treatment and will allow healthcare professionals to make an informed treatment decision based on recorded movement data. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Ross for the benefit of generating a report for a healthcare professional for decision-making related to a patient’s treatment, based on tracked movement of the patient (Ross Fig. 1, 3, Abstract). Regarding claim 20, Buehler et. al. in the combination further teaches the method of claim 19, wherein generating the pairwise detection graph includes determining edges between detection images from different frames of a same video stream (Buehler et. al. Fig. 4, 5) and determining edges between detection images from different video streams at corresponding times (Buehler et. al. Fig. 4, [0057]). PNG media_image24.png 152 728 media_image24.png Greyscale Regarding claims 6, 7, 15, 16, the rejection of claims 19-20 above is fully incorporated herein. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day off. 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, Vu Le can be reached at 571-272-7332. 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. /JESSICA YIFANG LIN/Examiner, Art Unit 2668 February 26, 2026 /VU LE/Supervisory Patent Examiner, Art Unit 2668
Read full office action

Prosecution Timeline

Nov 09, 2023
Application Filed
Nov 06, 2025
Non-Final Rejection — §101, §103
Feb 09, 2026
Response Filed
Feb 26, 2026
Non-Final Rejection — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12597139
CONTROLLING AN ALERT SIGNAL FOR SPECTRAL COMPUTED TOMOGRAPHY IMAGING
2y 5m to grant Granted Apr 07, 2026
Study what changed to get past this examiner. Based on 1 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

2-3
Expected OA Rounds
75%
Grant Probability
99%
With Interview (+33.3%)
2y 3m
Median Time to Grant
Moderate
PTA Risk
Based on 4 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month