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 .
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 taught 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Maizels et al. (US 20240073219) (hereinafter Maizels) in view of Moodie et al. (US 20250095385) (hereinafter Moodie).
Regarding claim 1, Maizels teaches A network video recorder server comprising at least one processor, a database, and at least one memory including computer program code (see Maizels paragraph 262), the at least one memory and the computer program code configured to, with the processor, cause the network video recorder server to at least:
wherein the localized one or more objects of interest comprises one or more indications; gather the one or more indications into a scene contextualization corresponding to the at least one first scene representation associated with the data source; generate, based at least in part on the scene contextualization, one or more intrinsic feature representations associated with the one or more indications; identify one or more data signatures associated with the at least one first scene representation, which corresponds to a second moment in time or a second one or more scene representation, enabling the network video recorder device to associate the one or more objects of interest across the first and second at least one moments in time or the first and second at least one scene representations, the one or more data signatures based at least in part on the one or more intrinsic feature representations; and store, via the database, the one or more data signatures, for applying the one or more intrinsic feature representations to at least one new moment in time or at least one new scene representation (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie below, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
However, Maizels does not explicitly teach preprocessing and localization as needed for the limitations of claim 1.
Moodie, in a similar field of endeavor, teaches receive a data source, comprising at least one first moment in time and at least one first scene representation associated with a scene from a physical location corresponding to the moment in time; preprocess the data source to transform the at least one scene representation into a representation suitable for analysis by the at least one processor; localize one or more objects of interest from the transformed scene representation (see Moodie paragraphs 30, 33, 47, 69, 78, 87, 96, 101 regarding receiving video data of a scene during a moment in time, preprocessing the data with a transformation in order for a machine algorithm to be able to interpret it and localizing the data using the features- in combination with Maizels, which teaches object detection, contextualization and feature representation, the object detection and recognition of Maizels may include the preprocessing and localization of Moodie),
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to modify the teaching of Maizels to include the teaching of Moodie so that in combination with Maizels, which teaches object detection, contextualization and feature representation, the object detection and recognition of Maizels may include the preprocessing and localization of Moodie.
One would be motivated to combine these teachings in order to enhance the breadth and usefulness of data associated with an identified object (see Moodie paragraphs 30, 33, 47, 69, 78, 87, 96, 101).
Regarding claim 2, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 1, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the at least one memory and the computer program code are further configured to, with the processor, cause the network video recorder server to: determine if the one or more data signatures corresponds to a new object of interest associated with the at least one new moment in time or the at least one new scene representation (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 3, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 1, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more intrinsic features are based at least in part on one or more hierarchal features generated via one or more neural networks (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 4, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 2, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the at least one memory and the computer program code are further configured to, with the processor, cause the network video recorder server to: generate a notification to a user interface if the one or more data signatures is determined to correspond to the new object of interest (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 5, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 3, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more hierarchal features further comprises one or more object attributes associated with the one or more objects of interest and one or more feature embeddings associated with the one or more objects of interest (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 6, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 5, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more object attributes further comprises a) an object unique serial code, b) object model data, c) object maker data, and d) object color data (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 7, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 5, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more object attributes further comprises a) upper apparel data, b) lower apparel data, c) gender data, d) facial data, e) hair data, and f) object color data (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Independent claim(s) 8 is/are analogous in scope to claim(s) 1, albeit in method form, and is/are rejected according to the same reasoning.
Dependent claim(s) 9-14 is/are analogous in scope to claim(s) 2-7, and is/are rejected according to the same reasoning.
Independent claim(s) 15 is/are analogous in scope to claim(s) 1, albeit regarding a computer program product, non-transitory computer readable storage medium as taught by Maizels paragraph 262, and is/are rejected according to the same reasoning.
Regarding claim 16, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 15, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more intrinsic features are based at least in part on one or more hierarchal features generated via one or more neural networks, the computer program product further comprising: program code instructions configured to determine if the one or more data signatures corresponds to a new object of interest associated with the at least one new moment in time or the at least one new scene representation (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 17, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 16, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches further comprising: program code instructions configured to generate a notification to a user interface if the one or more data signatures is determined to correspond to the new object of interest (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 18, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 16, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more hierarchal features further comprises one or more object attributes associated with the one or more objects of interest and one or more feature embeddings associated with the one or more objects of interest (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 19, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 18, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more object attributes further comprises a) an object unique serial code, b) object model data, c) object maker data, and d) object color data (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Regarding claim 20, the combination of Maizels and Moodie teaches all aforementioned limitations of claim 18, and is analyzed as previously discussed.
Furthermore, the combination of Maizels and Moodie teaches wherein the one or more object attributes further comprises a) upper apparel data, b) lower apparel data, c) gender data, d) facial data, e) hair data, and f) object color data (see Maizels paragraphs 223, 240, 296, 318, 332, 560 988-990, 1280, 1338, and 1423 regarding objects of interest being recognized in images by a hierarchical neural network where indications are interpreted from the data in order to contextualize a scene and feature representations are inferred in order to identify data signatures that can be traced and tracked across multiple instances of time in the video data, where new representations and data may be detected and stored and new objects entered into the database, features may be based on hierarchical organization, a notification of a new object is given to a user [rendered obvious in paragraph 332 in the case where there is a notification triggered by a data mismatch, combined with later teachings of entering and creating new data], and hierarchical features include object model and maker data, serial code, color, clothing, gender, facial data, hair data, and color - in combination with Moodie, which teaches localization and preprocessing, the object recognition process of Maizels may include localization and preprocessing).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Matthew D Kim whose telephone number is (571)272-3527. The examiner can normally be reached Monday - Friday: 9:30am - 5:30pm 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, Joseph Ustaris can be reached at (571) 272-7383. 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.
/MATTHEW DAVID KIM/Primary Examiner, Art Unit 2483