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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after allowance or after an Office action under Ex Parte Quayle, 25 USPQ 74, 453 O.G. 213 (Comm'r Pat. 1935). Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, prosecution in this application has been reopened pursuant to 37 CFR 1.114. Applicant's submission filed on May 29, 2026 has been entered.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Response to Amendment
Claims 3-4 stand cancelled. Claims 1, 11 and 13 is currently amended. Claims 1-2 and 5-13 are pending.
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) 1-2, 5-6 and 9-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over WO 2018/163555 A1 to Yamato et al. hereinafter, “Yamato” in view of US 2022/0019807 A1 to Carreira et al., hereinafter, “Carreira”.
Claim 1. Yamato teaches An action recognition apparatus, [0022] The action recognition system
comprising at least one processor, the at least one processor carrying out: [0027] …a central processing unit (CPU) 101
a first calculation process of calculating, based on a first partial sequence in an image sequence constituting a time series, [0085] the action determination unit 60 determines (calculating) the action class of the person appearing in the image on the basis of the time series data (sequence constituting a time series) of the data D3 of the posture feature of the person and the data D4a of the filtered peripheral feature.
first action feature information that indicates a feature of an action of a person who is included as a subject in an image included in the first partial sequence; [0085] the action determination unit 60 determines the action class of the person appearing in the image on the basis of the time series data of the data D3 of the posture feature (first action feature) of the person (subject in an image) and the data D4a of the filtered peripheral feature.
a second calculation process of calculating, based on past feature information, second action feature information obtained by correcting the first action feature information,
[0034] The peripheral feature extraction unit 40 extracts a peripheral feature (second action feature information) of a peripheral object of a person reflected in the image on the basis of the image data D1 and the data D2 indicating the person region.
[0035] The peripheral feature filter unit 50 performs filtering (correcting) of the data D4 of the peripheral feature on the basis of the data D3 of the posture feature
(first action feature – past feature information is understood to be first action feature information sequence, spec [0059]) and the data Da of the importance of the peripheral feature set in association with the posture feature.
the past feature information having been calculated based on a plurality of second partial sequences including at least one past image which is prior to the first partial sequence in the image sequence; [0086] Since the behavior of a person has a temporal continuity and a time-series deep association between behaviors, it is desirable to consider not only a single image data for each frame but also time-series data indicating a temporal change such as a positional relationship between a person's posture and an object when the behavior class of a person is determined. In addition, in determining the behavior class of a person, it is desirable to consider not only the behavior between consecutive frames but also the behavior of the past (for example, one minute before) separated to some extent.
[0087] the action determination unit 60 according to the present embodiment performs time-series analysis using a hierarchical LSTM (Long Short-Term Memory), which is a type of recurrent neural network.
and an action recognition process of recognizing an action of the person based on the second action feature information, [0085] the action determination unit 60 determines the action class of the person appearing in the image on the basis of the time series data of the data D3 of the posture feature of the person and the data D4a of the filtered peripheral feature (interpreted as the second action feature).
wherein in the first calculation process, the at least one processor stores, in association with information identifying a partial sequence, the first action feature information,
[0085] the action determination unit 60 determines (calculates) the action class of the person appearing in the image on the basis of the time series data (sequence) of the data D3 of the posture feature (first action feature) of the person (subject in an image) and the data D4a of the filtered peripheral feature.
[0028] Each function described later of the image processing apparatus 100 is realized by, for example, the CPU 101 (processor) referring to a control program (for example, an image processing program) stored in the ROM 102
and in the second calculation process, [0034] The peripheral feature extraction unit 40 extracts a peripheral feature (second action feature information) of a peripheral object of a person reflected in the image on the basis of the image data D1 and the data D2 indicating the person region.
the at least one processor: [0028] Each function described later of the image processing apparatus 100 is realized by, for example, the CPU 101 (processor)
obtains, as the past feature information, a plurality of pieces of first action feature information previously calculated for the person based on a plurality of second partial sequences, calculates, for each of the plurality of pieces of past feature information,
[0086] Since the behavior of a person has a temporal continuity and a time-series deep association between behaviors, it is desirable to consider not only a single image data for each frame but also time-series data indicating a temporal change such as a positional relationship between a person's posture and an object when the behavior class of a person is determined. In addition, in determining the behavior class of a person, it is desirable to consider not only the behavior between consecutive frames but also the behavior of the past (for example, one minute before) separated to some extent.
[0085] a peripheral feature filter unit that filters the peripheral feature on the basis of the posture feature and the importance (understood to be the relevance) of a peripheral feature set in association with the posture feature
Yamato teaches [0085] a peripheral feature filter unit that filters the peripheral feature on the basis of the posture feature and the importance (understood to be the relevance) of a peripheral feature set in association with the posture feature
but fails to explicitly teach a weight derived from a relevance between that past feature information and the first action feature information. Carreira, in the field of action classification using a neural network, teaches a weight derived from a relevance between that past feature information and the first action feature information, [0050] In softmax attention, dot-product attention is applied over the key features to generate a respective weight for each of the features in the value features.
[0016] the feature representation 112 includes multiple frames that each correspond to a different respective time period
the relevance representing a temporal dependence, [0016] the feature representation 112 includes multiple frames that each correspond to a different respective time period
and calculates the second action feature information by combining the first action feature information with an aggregate of the plurality of pieces of past feature information weighted by the calculated weights. [0046] the input query features 212 can be a concatenation of the output query features (combining the first action feature information)
[0050]The value features are then summed, weighted by their respective probabilities to generate the initial updated query features (understood to be the section action feature).
Claim 2. (original): Yamato teaches wherein: the image sequence includes an image that includes an object as a subject; and in the first calculation process, the at least one processor calculates the first action feature information based on a relevance between the person who is included as a subject in the image included in the first partial sequence and the object. [0016]… an image generated by the imaging apparatus is acquired,a posture feature of a person reflected in the image is extracted,a peripheral feature indicating a shape, a position, or a type of a surrounding object of a person reflected in the image is extracted,filter the peripheral feature based on the pose feature and a degree of importance (understood to be the relevance) of a peripheral feature set in association with the pose feature;
[0085] a peripheral feature filter unit that filters the peripheral feature on the basis of the posture feature and the importance (understood to be the relevance) of a peripheral feature set in association with the posture feature
Claim 5. (original): Yamato teaches wherein: in the action recognition process, the at least one processor recognizes an action of the person by further referring to the first action feature information, [0085] The behavior determination unit 60 acquires the data D3 of the posture feature (interpreted as the first action feature) of the person from the human body feature extraction unit 30…
in addition to the second action feature information. [0085] the data D4a of the filtered peripheral feature (interpreted as the second action feature).
Claim 6. (original): Yamato teaches wherein: in the action recognition process, the at least one processor recognizes an action of the person with use of a learned model which has been trained by machine learning. [0075] machine learning (learning unit 70 to be described later) for each action class by using, as training data in which a posture feature and a peripheral feature to be focused are associated with each other.
[0102] machine learning (a learning unit 70 described later) for each action class
[0105] The learning unit 70 executes machine learning using the teacher data
Claim 9. (original): Yamato teaches A training apparatus comprising at least one processor, the at least one processor carrying out: a training process of training an action recognition apparatus recited in claim 1 with use of a training data set in which an image sequence constituting a time series is associated with action information that indicates an action of a person who is included as a subject in an image included in the image sequence. [0044] The human region detection unit 20 may also use a learned neural network
[0085] … determines the action class of the person appearing in the image on the basis of the time series data
[0125] …100 (human region detection unit 20) detects a person region from the acquired image of the image data…
Claim 10. (original): Yamato teaches wherein: in the training process, the at least one processor trains the action recognition apparatus based on a loss that is obtained by inputting the first action feature information in the action recognition process, and on a loss that is obtained by inputting the second action feature information in the action recognition process. [0114-0116] when input to the hierarchical LSTM is performed using both the time-series data D6a of the posture features of the person and the time-series data D6a of the posture features of the person and the time-series data D6b of the peripheral features
Claim 11. Reviewed and analyzed in the same way as claim 1. See the above analysis and rationale.
Claim 12. (original): Yamato teaches A training method comprising: a training process in which at least one processor trains an action recognition apparatus recited in claim 1 with use of a training data set in which an image sequence constituting a time series is associated with action information that indicates an action of a person who is included as a subject in an image included in the image sequence. [0044] The human region detection unit 20 may also use a learned neural network
[0085] … determines the action class of the person appearing in the image on the basis of the time series data
[0125] …100 (human region detection unit 20) detects a person region from the acquired image of the image data…
Claim 13. (currently amended): Reviewed and analyzed in the same way as claim 1. See the above analysis and rationale.
Claim(s) 7-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over WO 2018/163555 A1 to Yamato et al. hereinafter, “Yamato” in view of US 2022/0019807 A1 to Carreira et al., hereinafter, “Carreira” and US 2022/0354387 A1 to Ogasawara et al., hereinafter, “Ogasawara”.
Claim 7. (original): Yamato fails to explicitly teach in the action recognition process, the at least one processor recognizes an action of a subject who is in a medical facility. Ogasawara, in the field of monitoring the action of a person in image data, teaches wherein: in the action recognition process, the at least one processor recognizes an action of a subject who is in a medical facility, [0003] In a case where a patient (subject) has a possibility of physical injury due to a fall (action), there is a need for a means to immediately notify a healthcare professional or a caregiver in charge of the patient (alert).
[0044] detects that a user undergoing rehabilitation at a nursing facility, a patient in hospital, or the like has fallen, for example, while sleeping at night or while being active alone in the daytime… in a rehabilitation room, a hospital room
and outputs an alert based on a recognition result. [0003] there is a need for a means to immediately notify a healthcare professional or a caregiver in charge of the patient (alert).
Yamato is in the field of action recognition using neural network. Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Yamato with the teachings of Ogasawara [0008] to perform monitoring with a reduced burden on the user.
Claim 8. (original): Yamato fails to explicitly teach in the action recognition process, the at least one processor recognizes an action of a subject who is in a medical facility. Ogasawara, in the field of monitoring the action of a person in image data, teaches the at least one processor recognizes an action of a subject who is in a medical facility, [0003] In a case where a patient (subject) has a possibility of physical injury due to a fall (action), there is a need for a means to immediately notify a healthcare professional or a caregiver in charge of the patient (alert).
[0044] detects that a user undergoing rehabilitation at a nursing facility, a patient in hospital, or the like has fallen, for example, while sleeping at night or while being active alone in the daytime… in a rehabilitation room, a hospital room
and outputs information for supporting decision making of a health professional based on a recognition result. [0209] Thus, the medical staff or nursing care staff who is in charge of treatment or nursing care of the user can immediately take appropriate measures in response to the occurrence of an abnormality.
Yamato is in the field of action recognition using neural network. Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Yamato with the teachings of Ogasawara [0008] to perform monitoring with a reduced burden on the user.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DELOMIA L GILLIARD whose telephone number is (571)272-1681. The examiner can normally be reached 8am-5pm.
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.
/DELOMIA L GILLIARD/Primary Examiner, Art Unit 2661
Prosecution Insights