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 .
All amendments to the claims as filed on 1/16/26 have been entered and action follows:
Response to Arguments
Applicant’s arguments with respect to claim(s) have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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, 3-5, 9-11, 13-15 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kuo et al (US 9,396,412) in view of Zhang (US Pub. 2016/0125232), Al Amour (US Pub. 2020/0232797) and Okumura et al (US Pub. 2016/0284098).
With respect to claim 1, Kuo discloses A hybrid approach for object tracking (see Abstract, …person re-identification…), said method comprising the steps of:
detecting a reference object in a received first video and/or image frame (v/i) based on a pre-defined feature-based characteristic, (see col. 4, lines 26-31, wherein …The images are from … a same camera at different times. The obtained images represent one or more people “a reference object” in a field of view of the respective camera…; and lines 34-35, wherein …a person having attributes “a pre-defined feature-based characteristic” of male, short brown hair, short sleeves, long pants, checkered grey top, and black pants…);
[populating a feature gallery] with feature-based characteristics of the detected reference object, (see col. 4, lines 34-35, wherein …a person having attributes “feature-based characteristic” of male, short brown hair, short sleeves, long pants, checkered grey top, and black pants…);
detecting an updated object in a received second v/i with feature-based characteristics, (see col. 4, lines 26-31, wherein …The images are from … a same camera at different times. The obtained images represent one or more people in a field of view of the respective camera. As a person traverses through a video surveyed region, typically along a common travel path, … the same camera at a different time capture the same person “an updated object”);
predicting a bounding box around the updated object based on the populated [feature gallery] and the detected updated object, (see col. 4, lines 55-57, wherein …images may be of a region or may be cropped. For matching, a rectangular box “a bounding box” fit to just surround a person may be used. Any people in the image of the region are cropped so that the resulting person image represents, at least mostly, just one person…); and
matching the bounding box prediction with the detection characteristics for validating the updated object and
[updating the feature gallery] for subsequent tracking of the updated object [only if the updated object includes at least an appearance and a position on the received first video and/or image frame that differ from the feature-based characteristics already stored in the feature gallery, but otherwise discarding the updated object], (see col. 4, line 65 to col. 5 line 5, wherein …. For re-identification of one person from an image as being the person in another image, features are used. The same features are extracted from all of the images to be compared “matching”. For example, a person of interest is identified in an image…),
[wherein the feature gallery includes at least one feature selected from the group comprising a size, aspect ratio, location, color, Histogram of Oriented Gradient (HOG), Scale- invariant feature transform (SIFT), HAAR like features and Local Binary Pattern (LBP) of the object], as claimed.
However, Kuo fails to disclose populating a feature gallery, and updating the feature gallery for subsequent tracking of the updated object only if the updated object includes at least an appearance and a position on the received first video and/or image frame that differ from the feature-based characteristics already stored in the feature gallery, but otherwise discarding the updated object, and wherein the feature gallery includes at least one feature selected from the group comprising a size, aspect ratio, location, color, Histogram of Oriented Gradient (HOG), Scale- invariant feature transform (SIFT), HAAR like features and Local Binary Pattern (LBP) of the object, as claimed.
Zhang in the same field of tracking the person teaches populating a feature gallery and updating the feature gallery, (see paragraph 0023, wherein …for example, having an entry within the static image gallery. In either case, the dynamic collection may collect images into clusters for each tracking target identified by computer 120; and paragraph 0032, wherein …Method 200 also includes updating the set of clusters in the dynamic collection at 230. The set of clusters may be updated using the query face. In one example, updating the set of clusters may include modifying a member of the set of clusters…), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the two references as they are analogous because they are solving similar problem of tracking person using the image analysis. The teaching of Zhang to use a memory “feature gallery” can be incorporated in to Kuo’s system memory (see figure 6 numerical 16), for suggestion, and modifying the system yields a quick tracking of the individuals (see Zhang paragraph 0017), for motivation.
Al Amour in tracking apparatus teaches updating the feature gallery for subsequent tracking of the updated object only if the updated object includes at least an appearance and a position on the received first video and/or image frame that differ from the feature-based characteristics already stored in the feature gallery, but otherwise discarding the updated object, (see paragraph 0046, wherein …When a product is scanned with the drone at a particular vehicle location, the product identifier “an appearance” and associated product location “a position” can be stored if the product location is new, updated if the product location has changed, or discarded if the product location is already known), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of tracking person using the image analysis. The teaching of Al Amour to update the information regarding the target object after the initial information has changes can be incorporated in to Kuo’s system memory (see figure 6 numerical 16), for suggestion, and modifying the system yields a tracking of the objects, for motivation.
Also, Okumura teaches wherein the feature gallery includes at least one feature selected from the group comprising a size, aspect ratio, location, color, Histogram of Oriented Gradient (HOG), Scale- invariant feature transform (SIFT), HAAR like features and Local Binary Pattern (LBP) of the object, (see paragraph 0077, wherein …the observed value “feature” extractor 123 is the observed value corresponding to the feature value the distribution of which is stored in the distribution storage 125a “memory”. The feature value includes at least one of the height, an aspect ratio, a moving speed, an operation cycle, a unit operation interval, and a color of the target object (image of the target object) in the frame image, for example…), as claimed.
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of tracking person using the image analysis. The teaching of Okumura to have various features as disclose can be incorporated in to Kuo’s system memory (see figure 1 numerical 42), for suggestion, and modifying the system yields an object tracking (see Okumura paragraph 0022), for motivation.
With respect to claim 3, combination of Kuo, Zhang, Al Amour and Okumura further discloses the feature-based characteristics are based on at least one feature of the reference object, (see Kuo col. 5, line 37-40, …Histogram of gradient (HOG) features are collected …), as claimed.
With respect to claim 4, combination of Kuo, Zhang, Al Amour and Okumura further discloses wherein the feature-based gallery is populated based on at least one feature of the reference object and updated based on the features of the updated object, (see Zhang paragraph[0037, wherein …Face detection logic 420 may update the set of tracking targets 412 by identifying faces within frames 499 of a video feed…), as claimed.
With respect to claim 5, combination of Kuo, Zhang, Al Amour and Okumura further discloses a tracker wherein, the tracker matches the available detections and predictions between the bounding box position and the feature gallery of the updated object via a matching algorithm, (see Kuo col. 4, lines 55-57, wherein …images may be of a region or may be cropped. For matching, a rectangular box “a bounding box” fit to just surround a person may be used. Any people in the image of the region are cropped so that the resulting person image represents, at least mostly, just one person…; and see col. 4, line 65 to col. 5 line 5, wherein …. For re-identification of one person from an image as being the person in another image, features are used. The same features are extracted from all of the images to be compared “matching”. For example, a person of interest is identified in an image “bounding box position”…), as claimed.
With respect to claim 9, combination of Kuo, Zhang, Al Amour and Okumura further discloses wherein updating the feature gallery depends on the similarity of the features between the updated object and existing sample features in the gallery, (see Zhang paragraph 0018, wherein ….These images may contain more up-to-date images of the person than the static gallery, including current features of the person (e.g., clothing, makeup, hairstyle) that may be changed easily over time…), as clamed.
With respect to claim 10, combination of Kuo, Zhang, Al Amour and Okumura further discloses a predictor, wherein the predictor uses samples from the feature gallery to match patterns between the updated object and samples in the feature gallery to specify the position of the updated object in the next frame for subsequent tracking of the updated object, (see Zhang paragraph 0037 …detection logic 420 may update the set of tracking targets 412 by identifying faces within frames 499 of a video feed (not shown). Face detection logic 420 may be periodically run to ensure tracking targets' locations in a space captured by the video feed are maintained. Face detection logic 420 may also be employed to identify new tracking targets 412 who appear within frames 499 of the video feed), as claimed.
Claim 11 is rejected for the same reasons as set forth in the rejections for claims 1+10, because claim 11 is claiming subject matter of similar scope as claimed in claims 1+10.
Claims 13-15 and 19 are rejected for the same reasons as set forth in the rejections for claims 3-5 and 9, because claims 13-15 and 19 are claiming subject matter of similar scope as claimed in claims 3-5 and 9 respectively.
Claim 20 is rejected for the same reasons as set forth in the rejections for claims 1+10, because claim 20 is claiming subject matter of similar scope as claimed in claims 1+10.
Claims 2, 6-8, 12 and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Kuo et al (US 9,396,412) in view of Zhang (US Pub. 2016/0125232), Al Amour (US Pub. 2020/0232797) and Okumura et al (US Pub. 2016/0284098) as applied to claim 1 above, and further in view of Srinivasa et al (US 7,227,893).
With respect to claim 2, combination of Kuo, Zhang, Al Amour and Okumura discloses all the elements as claimed and as rejected in claim 1 above. However, they fail to explicitly disclose wherein the reference object detection is achieved by performing semantic segmentation of the reference object using any kind of object detection CNN, wherein said CNN is trained on a dataset of images with object annotated using at least one of the bounding box or pixel-wise mask, as claimed.
Srinivasa in the same field teaches wherein the reference object detection is achieved by performing semantic segmentation of the reference object using any kind of object detection CNN, wherein said CNN is trained on a dataset of images with object annotated using at least one of the bounding box or pixel-wise mask, (see col. 26, lines 20-45, wherein …Both the subclassifiers and the fusion engine can be implemented according to the disclosed embodiment of the present invention as statistical classifiers, which, e.g., can be trained using examples of typical situations and objects of interest, e.g., intruders. (Examples of suitable statistical classification algorithms include neural networks, decision trees, support vector machines, k-nearest neighbor classifier, etc.)…), as claimed
It would have been obvious to one ordinary skilled in the art at the effective date of invention to combine the references as they are analogous because they are solving similar problem of tracking person using the image analysis. The teaching of Srinivasa to use a neural network can be incorporated in to Kuo’s system memory (see col. 5, lines 46-47, …machine-learnt classifiers…), for suggestion, and modifying the system yields a quick tracking of objects (see Srinivasa col. 3, lines 21-25), for motivation.
With respect to claim 6, the same reasons to combine Kuo, Zhang, Al Amour, Okumura and Srinivasa, the combination further discloses wherein the matching algorithm calculates a new object position on a current frame based on each object on a previous frame by at least one of a velocity vector, cam/median shift, optical flow, or CNN-based predictions, (see Srinivasa col. 12, lines 35-55 wherein, …. a matching apparatus adapted to match the location of an object segment in the current frame to one of a plurality of projected locations of the object segment in the current frame, which projections are based upon the location of the respective object segment in at least one prior frame; and, a track provider adapted to receive and store the location of an object segment in the current frame and over a plurality of prior frames and adapted to provide the projections of the location of the object segment in a subsequent frame based upon the locations of the object segments in the current frame and the plurality of prior frames…), as claimed.
With respect to claim 7, the same reasons to combine Kuo, Zhang, Al Amour, Okumura and Srinivasa, the combination further discloses wherein the tracker validates the features of the updated object with the feature gallery and the reference object, (see Kuo col. 5 lines 52-58, wherein …comparison indicate the same person…), as claimed.
With respect to claim 8, the same reasons to combine Kuo, Zhang, Al Amour, Okumura and Srinivasa, the combination further discloses wherein the tracker validates by indicating an object loss when the features of the updated object and the reference object are measurably different from the prediction on several consequent frames, (see Srinivasa col. 9, lines 35-45, wherein … Target tracking can then be done by matching blobs in a current frame with existing tracks using, e.g., a cost function “an object loss” based on blob features such as for size, color histogram, centroid and/or shape. Tracking can persist even when targets become…), as claimed.
Claims 12, and 16-18 are rejected for the same reasons as set forth in the rejections for claims 2 and 6-8, because claims 12 and 16-18 are claiming subject matter of similar scope as claimed in claims 2 and 6-8 respectively.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VIKKRAM BALI whose telephone number is (571)272-7415. The examiner can normally be reached Monday-Friday 7:00AM-3:00PM.
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, Gregory Morse can be reached at 571-272-3838. 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.
/VIKKRAM BALI/Primary Examiner, Art Unit 2663