DETAILED ACTION
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
A Preliminary Amendment was received 11/14/2024 to amend the specification, abstract, drawings and claims. Claims 1-15 are pending with amendments to claims 1, 4-6, 9-11, 14-15.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on November 14, 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is considered by 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 1-4, 6-9, 11-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites a pose analyzing apparatus comprising: at least one memory that is configured to store instructions; and at least one processor that is configured to execute the instructions (memory and processor are generic computer components performing a task that is an abstract idea mental process) to:
acquire a target image on which two or more persons are captured (a person can visually see a field of view with people);
estimate a pose for each one of the persons (a person can mentally identify a given pose of a target person within the field of view of people);
classify the persons into two or more pose groups based on the poses of the persons (a person can mentally classify the pose of each person viewed in the field of view); and
output group information indicating at least one of the pose groups (a person mentally classifying each person seen in a field of view into a group of a given pose; also considered a post-solution activity under MPEP § 2106.05(g)).
Claim 2 recites the pose analyzing apparatus according to claim 1 (as described above), wherein the classification of the persons includes: for each one of the persons, computing a similarity score that represents a degree of similarity between the pose of the person and a reference pose (a person may view an intended pose of a person (such as knowledge as to a template pose position in a synchronized motion) and determine how similar the analyzed pose is to the template pose); and assigning each person to the pose group corresponding to the similarity score of the person, the pose groups being associated with different ranges of the similarity score from each other (a person can assess a given pose for multiple people observed to classify and mentally assign each person and pose to a given classification based on a given similarity assessment).
Claim 3 recites the pose analyzing apparatus according to claim 1 (as described above), wherein the classification of the persons includes performing clustering on the persons based on their poses to divide the persons into two or more clusters, thereby obtaining clusters as the pose groups (a person can assess a given pose for multiple people observed to classify and mentally assign each person and pose to a given classification group (cluster) of multiple groupings (clusters)).
Claim 4 recites the pose analyzing apparatus according to claim 1 (as described above), wherein the classification of the persons includes: classifying the persons into two or more type groups based on types of the poses of the person, the type groups being associated with different types of poses from each other (a person can assess a given pose for each person viewed of multiple people observed and mentally assign each person and pose to multiple sub-groups of the various groupings based on the viewed pose); and for each one of the type groups, classifying the persons in the type group into the pose groups (the classified pose is classified into a given one or more sub-groups based on the classified pose).
Claim 6 recites a pose analyzing method performed by a computer (generic computer components (memory and processor) performing a task that is an abstract idea mental process), comprising: steps identical to claim 1 (as described above).
Claim 7 recites the pose analyzing method according to claim 6, with further limitations identical to claim 2 (as described above).
Claim 8 recites the pose analyzing method according to claim 6, with further limitations identical to claim 3 (as described above).
Claim 9 recites the pose analyzing method according to claim 6, with further limitations identical to claim 4 (as described above).
Claim 11 recites a non-transitory computer-readable storage medium storing a program that causes a computer (generic computer components (memory and processor) performing a task that is an abstract idea mental process) to execute: perform steps identical to claim 1 (as described above).
Claim 12 recites the storage medium according to claim 11, with further limitations identical to claim 2 (as described above).
Claim 13 recites the storage medium according to claim 11, with further limitations identical to claim 3 (as described above).
Claim 14 recites the storage medium according to claim 11, with further limitations identical to claim 4 (as described above).
The limitations of analyzing a pose and comparing the pose to a reference and classifying the pose are processes that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, regarding the apparatus, other than reciting generic placeholder-related computer components, such as a memory and processor, nothing in the claim elements precludes the steps from practically being performed in the mind. For example in the independent claims, language of “acquire” is generic pre-processing data gathering of visual information (see MPEP 2106.05(g)); “estimate” is broadly claimed to evaluate the visual pose; “classify” is to organize the visual poses; and “output” is generic post-processing data output (see MPEP 2106.05(g)). If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, these claims each recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the method claims do not recite any elements which could not be performed in the mind and the claims only recite generic placeholder-related computer components, including a memory and processor. The computer components are recited at a high-level of generality (i.e., generic memory and processor for performing pose evaluation and classification, which is described with a high level of generality of automating a manual operation) such that it amounts to no more than mere instructions to apply the exception using a generic computer component. Accordingly, the computer components do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Therefore, the aforementioned claims are directed to abstract ideas.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a generic placeholder-related computer components, the memory and processor, used to evaluate and classify pose positions amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an invention concept. The claims are not patent eligible.
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.
Claims 1, 3-6, 8-11, 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over Rezaei et al (Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video) in view of official notice of facts.
Regarding Claim 1, Rezaei et al teach a pose analyzing apparatus (human pose estimation network and classification network; Fig 3-4 and 2.2.1 Short term tracking based on temporal association, 2.2.2 Long term tracking using tracklet fusion) comprising:
at least one memory that is configured to store instructions; and at least one processor that is configured to execute the instructions (method to implement human pose estimation network and classification network; Fig 3-4 and 2.2.1 Short term tracking based on temporal association, 2.2.2 Long term tracking using tracklet fusion) to:
acquire a target image on which two or more persons are captured (raw video frames are acquired using an RGB video camera, which first detects multiple persons in the pose estimation network; Fig 3 and 2.1 Human Pose Estimation, 4.1 Dataset ¶ 2);
estimate a pose for each one of the persons (human pose estimation is performed using the Mask R-CNN network, which may be tracked for each person using a multi-person pose tracking method; Fig 3-4 and 2.1 Human Pose Estimation, 2.2 tracking based temporal association;
classify the persons into two or more pose groups based on the poses of the persons (pose evolution (tracked pose) is classified for the non-target and target person based on the keypoints (to identify the target), and the target is classified based on time into distinct groups for actions with 3 distinct action behaviors annotated (postures, transitions and cued behaviors), with each action including multiple sub-classifications ; Fig 5-7, 11 and 3.2 Classification Network, 4.1 Dataset ¶ 3); and
output group information indicating at least one of the pose groups (the action classification model output includes classification accuracy (Table 1, Fig 9) and confusion matrix for accuracy of the action recognition network for comparing predicted to true class (Fig 10-11); 4.3 Action Classification ¶ 3, 5. Discussion ¶ 1-2).
Rezaei et al does not explicitly disclose a memory or processor. However, Rezaei et al teaches the hierarchical pose estimation network for the target-specific action classification method (Fig 2) to be performed using a neural network, which is known in the art to be based on a computer with a memory storing instructions executed on and processor (Fig 3, 4 and 2.2.1 Short term tracking based on temporal association, 2.2.2 Long term tracking using tracklet fusion) and applied to computer vision applications (1. Introduction ¶ 2). Therefore official notice of facts is taken that the classification method described by Rezaei et al is based on instructions stored on a computer memory and executed with a computer processor.
Regarding Claim 3, Rezaei et al in view of official notice of facts teach the pose analyzing apparatus according to claim 1 (as described above), wherein the classification of the persons includes performing clustering on the persons based on their poses to divide the persons into two or more clusters, thereby obtaining clusters as the pose groups (Rezaei et al, the target and non-target persons identified based on pose in the image data are classified and clustered into the groups as different tracklets; Fig 4 and 2.2.1 Short term tracking).
Regarding Claim 4, Rezaei et al in view of official notice of facts teach the pose analyzing apparatus according to claim 1 (as described above), wherein the classification of the persons includes: classifying the persons into two or more type groups based on types of the poses of the person, the type groups being associated with different types of poses from each other (Rezaei et al, a person is classified as a target or non-target based on the pose evolution keypoints, and the target is further classified based on action behaviors (postures, transitions and cued behaviors); Fig 5-7, 11 and 3.2 Classification Network, 4.1 Dataset ¶ 3) ; and for each one of the type groups, classifying the persons in the type group into the pose groups (Rezaei et al, the target person is classified into an action sub-classification (sitting, sit-to-stand, standing, walking, stand-to-sit) based on the tracked pose; Table 1, Fig 10, 11 and 4.3 Action Classification ¶ 1, 5. Discussion ¶ 2).
Regarding Claim 5, Rezaei et al in view of official notice of facts teach the pose analyzing apparatus according to claim 1 (as described above), wherein the group information includes an output image that is generated by modifying the target image to show common marks for the persons that belong to a same pose group as each other (Rezaei et al, the pose evolution feature of the skeleton are estimated with joint heatmaps based on time encoding for the given pose, with the different joint markers represented in different groups dependent on the identified pose (shown as the sit-to-stand class); Fig 5 and 3.1 Pose Evolution Representation).
Regarding Claim 6, Rezaei et al in view of official notice of facts teach a pose analyzing method (Rezaei et al, method to implement human pose estimation network and classification network; Fig 3-4 and 2.2.1 Short term tracking based on temporal association, 2.2.2 Long term tracking using tracklet fusion) performed by a computer (Official Notice of Facts, as described in claim 1), comprising: steps identical to claim 1 (as described above).
Regarding Claim 8, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 6, with further limitations claimed identical to claim 2 (as described above).
Regarding Claim 9, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 6, with further limitations claimed identical to claim 2 (as described above).
Regarding Claim 10, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 6, with further limitations claimed identical to claim 2 (as described above).
Regarding Claim 11, Rezaei et al in view of official notice of facts teach a non-transitory computer-readable storage medium storing a program that causes a computer (Official Notice of Facts, as described in claim 1) to execute: steps identical to claim 1 (as described above).
Regarding Claim 13, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 11, with further limitations claimed identical to claim 3 (as described above).
Regarding Claim 14, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 11, with further limitations claimed identical to claim 4 (as described above).
Regarding Claim 15, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 11, with further limitations claimed identical to claim 5 (as described above).
Claims 2, 7, 12 are rejected under 35 U.S.C. 103 as being unpatentable over Rezaei et al (Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video) in view of official notice of facts and Rogez et al (LCR-Net: Localization-Classification-Regression for Human Pose).
Regarding Claim 2, Rezaei et al in view of official notice of facts teach the pose analyzing apparatus according to claim 1 (as described above), including classification of the persons (Rezaei et al, the target and non-target persons identified based on pose in the image data are classified into different groups (target and non-target and action behaviors); Fig 4 and 2.2.1 Short term tracking).
Rezaei et al in view of official notice of facts does not teach for each one of the persons, computing a similarity score that represents a degree of similarity between the pose of the person and a reference pose; and assigning each person to the pose group corresponding to the similarity score of the person, the pose groups being associated with different ranges of the similarity score from each other.
Rogez et al is analogous art pertinent to the technological problem addressed in the current application and teaches for each one of the persons, computing a similarity score that represents a degree of similarity between the pose of the person and a reference pose (pose proposals are obtained for each person with a determination of the best representation based on the pose (error) score; Fig 2-7 and 3.1 Localization: pose proposals network); and assigning each person to the pose group corresponding to the similarity score of the person, the pose groups being associated with different ranges of the similarity score from each other (the anchor-pose for each person is classified based on the closest anchor-pose and associated probability distribution; Fig 4 and 3.2. Classification).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to combine the teachings of Rezaei et al in view of official notice of facts with Rogez et al including for each one of the persons, computing a similarity score that represents a degree of similarity between the pose of the person and a reference pose; and assigning each person to the pose group corresponding to the similarity score of the person, the pose groups being associated with different ranges of the similarity score from each other. By analyzing the pose of the individual as compared to a ground-truth reference, body parts may be localized to understand the typical poses, which provides for standardization of 3D pose estimation and may be applied to a controlled (computer vision) system, as recognized by Rogez et al (Abstract, 1. Introduction).
Regarding Claim 7, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 6, with further limitations claimed identical to claim 2 (as described above).
Regarding Claim 12, Rezaei et al in view of official notice of facts teach the pose analyzing method of claim 11, with further limitations claimed identical to claim 2 (as described above).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kinger et al (Deep Learning Based Yoga Pose Classification) teach a method and system for detecting and classifying yoga poses based on machine learning techniques.
Kawai et al (US 2025/0355925, application 18/854,600), from the same applicant and co-inventors, teach a system for analyzing pose information of a single person using a model that analyzes elements of the person’s pose, which is distinct from the current application that claims identification and analysis of multiple individuals and estimating pose and associated quality metrics for each person.
Zhang et al (US 2022/0080260) teach a method and system for pose comparison including receiving a frame of a user video and comparing the pose of the user in the frame to a reference pose to determine quality of the pose.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATHLEEN M BROUGHTON whose telephone number is (571)270-7380. The examiner can normally be reached Monday-Friday 8:00-5:00.
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, John Villecco can be reached at (571) 272-7319. 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.
/KATHLEEN M BROUGHTON/ Primary Examiner, Art Unit 2661
Prosecution Insights