DETAILED ACTION
Claims 1-3, 6-8, 10-15 are pending in this action. Claims 1-3, 6-8 and 10-15 have been given the priority date of 04/26/2022 in accordance with applicant’s claim for foreign priority. Claims 1-3, 6-8 and 10-13 have amended in this application, claims 4-5, and 9 have been canceled and claims 14 and 15 have been newly added.
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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. JP 2022-072623.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/19/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
35 U.S.C. 101
Applicant’s arguments, see Remarks, filed 09/13/2025, with respect to 35 U.S.C. 101 have been fully considered and are persuasive. The previous rejections under 35 U.S.C. 101 have been withdrawn.
35 U.S.C 112(b)
Applicant’s arguments, see Remarks, filed 09/13/2025, with respect to 35 U.S.C. 112(b) have been fully considered and are persuasive. The previous rejections under 35 U.S.C. 112(b) have been withdrawn.
35 U.S.C. 102(a)(1)
Applicant’s arguments, see Remarks, filed 09/13/2025, with respect to 35 U.S.C. 102 (a)(1) have been fully considered and are not persuasive. The arguments made by the applicant assert that Tsuji does not teach the newly added limitations of claims 1, 12 and 13, the examiner respectfully disagrees. The newly added limitations are fully presented and discussed below, and in view of these reasons the examiner respectfully maintains the rejections under 35 U.S.C. 1012(a)(1).
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-3, 6-8 and 10-15 are rejected under 35 U.S.C. 102(a) as being anticipated by Tsuji (US 20180053314 A1).
Regarding claim 1 Tsuji discloses; An object tracking apparatus for tracking an object depicted in a sequence of images, the apparatus;
comprising at least one processor (Tsuji, claim 8, a processor is used);
and memory storing instructions,
wherein the instructions, when executed by the at least one processor (Tsuji, claim 8, a processor is used) cause the object tracking apparatus to:
extract an image from the sequence of images, the image comprising a depiction of an object from among a person, an animal or a vehicle (Tsuji, [0027] multiple images are captured on multiple image capture devices [0036] the device ID and the image frame are acquired from the captured images from the device, [0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images);
detect at least one object region (Tsuji, [0038] the tracking device extracts a region from the image) surrounding based on at least one model (Tsuji, [0038], the region includes a crowd of people which is the tracked object of interest);
calculate an evaluation value (Tsuji, [0050] a color information value is calculated for each object region) indicating how reliably the object is included in the at least one object region ([0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images),
wherein a larger evaluation value indicates that the at least one object is more likely to include the object (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity, [0052] the highest value indicates the highest degree of similarity),
and wherein the evaluation value is based on at least one of an output value from the at least one model, a calculated degree that the object is hidden, a calculated degree of overlap of a plurality of object regions in the image, relationship between a detected foreground and a detected background ([0058] the feature extraction section computed the similarity based on degree of overlap between regions/frames);
decide, in accordance with the evaluation value, a first weight of an appearance similarity from among a plurality of types of similarity which are used to associate the at least one object region with a tracking target in the image sequence (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity), wherein the plurality of types of similarity comprises at least one of: the appearance similarity, a moving speed similarity, a feature point similarity, a size similarity, or a position similarity in three dimensional space (Tsuji, [0033] feature and color information appearance similarity) is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity),
wherein the appearance similarity is calculated a cosine similarity between extracted appearance features of the object and the tracking target (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity, the cosine similarity formula is computed by taking the sum of the vector similarities divided by the square root of the sums of the vector similarities, per Tsuji [0051] and equation 1, the computation of the similarity values are computed functionally equivalent to this), the first weight being decided for each of the at least one objection regions such that a higher evaluation value is associated with a higher first weight, and the one object regions being associated with one tracking target (Tsuji, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value);
at least one object region and the tracking target based on the first weight and at least of the plurality of types of similarity (Tsuji, [0028] The feature information between regions is compared to determine if the person in the two regions is the same person, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value, [0079] the comparison unit performs weighting on the similarities to determine whether the similarity is associated with an overlapped region)
and based on the correspondence, add the at least one object region as the new tracking target or delete tracking information for a tracking target (Tsuji, [0054]-[0055] the tracking target flows are determined based upon the similarity/correspondence).
Regarding claim 2 Tsuji discloses; The object tracking apparatus according to the object tracking apparatus according to wherein:
the plurality of types of similarity further include positional similarity which is based on a position of the at least one object region in the image and on a position of a tracking target region that is associated with the tracking target (Tsuji, [0028] two people captured in an image have position information calculated to help verify that they are the same person between images, where the first person/region of the first image containing the person is the object region and the target region is the second image region containing a person who the system is attempting to verify is the same as in for the first image).
Regarding claim 3 Tsuji discloses; The object tracking apparatus according to claim 1 wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
in a case where there are two or more object regions and two or more tracking targets (Tsuji, [0058] features of a collection of regions in one captured image can be compared with a collection of regions of other frames, where the region(s) of one frame are the object regions and the regions of subsequent frames are tracking targets), decide that an object region having an evaluation value equal to or higher than a first threshold is regarded as a first object region and that an an objection region having an evaluation value less than a first threshold regions is regarded as a second object region (Tsuji, [0054]-[0056] the regions are determined/collected based upon values of vectors representing the flow (threshold values of the vectors), the flow is related to the order/direction of the frames ([0047]), so regions are selected based upon vector values detailing the order(flow) of the frames based upon features),
the first object region being an object region having a first weight higher than zero (Tsuji, [0037] color features (appearance similarity) is determined for regions (at least one) in an image, [0077]-[0080] the weights are determined based on similarity, so when the similarity is higher and the region size is larger, the weight is higher), and the second object region being an object region having a first weight equal to zero (Tsuji, [0039], positional relationships are determined from images, where the positional relationship is being interpreted as a type of similarity of an object region, [0077]-[0080] the weights are determined based on similarity, so when the similarity is higher and the region size is larger, the weight is higher, conversely, a very small region would not be weighted or would be weighted significantly less); and
perform a first correspondence identification process and a second correspondence identification process, (Tsuji, [0028]-[0029] people are detected in images, and then regions in multiple images are compared to verify that the person in the images is the same person in both, Examiner is interpreting this as a first correspondence., [0069] multiple people can be detected across frames (second correspondence id process)), the first correspondence identification process being a process of identifying a correspondence between the first object region and each of the two or more tracking targets (Tsuji, [0028]-[0029] people are detected in images, and then regions in multiple images are compared to verify that the person in the images is the same person in both, Examiner is interpreting this as a first correspondence.),
and the second correspondence identification process being a process of identifying a correspondence between the second object region and each tracking target for which a correspondence is not identified in the first correspondence identification process ([0069] multiple people can be detected across frames (second correspondence id process), where multiple people, not just a first person, are identified across images, since the first embodiment only goes one person at a time, the process discussed in paragraph [0069] would reasonably identify a second object region (area in an image containing multiple people), and then compare and identify that region with multiple tracking targets who have yet to be identified (multiple people in the images)).
(Claim 4 canceled)
(Claim 5 canceled)
Regarding claim 6 Tsuji discloses; The object tracking apparatus according to claim 2, wherein the instructions, when executed by, the at least one processor, cause the object tracking apparatus to:
in a case where the first weight is equal to zero for the least one object region, identify, the correspondence by using at least the position similarity ( Examiner is interpreting this as meaning when appearance similarity is not used, the position is used in identifying the target object/region, Tsuji, [0029] in situations where little feature information can be determined, the person being tracked can be associated across images/image capture devices using position, given that [0077]-[0080] states that weighting is only performed in certain cases based on similarity and region size, in a case or embodiment where there is not enough similarity information than weighting is not performed (weight = 0, therefore the process above would be performed).
Regarding claim 7 Tsuji discloses; The object tracking apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
Calculate the evaluation value based on (i) how reliably the object is included in the at least one object or region or (ii) a degree that the object is hidden in the at least one object region (Tsuji, [0030]-[0033] the evaluation values (moving group tracking value) can be determined in cases in which a portion of the object is hidden, by using other data in the image to tracking the person or group of interest).
Regarding claim 8 Tsuji discloses; The object tracking apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
Predict an appearance feature for the tracking target in the image and use the precited appearance feature to calculate the appearance similarity (Examiner is interpreting this as the appearance feature predicted for the tracking target is used as the appearance feature of the tracking target used in calculating the similarity, Tsuji, [0072] averages of the color values (predicated feature) is used as the color obtained degree of similarity (obtained feature), which is then used to compute the associated color regions from this (similarity computation)).
Regarding claim 10 Tsuji discloses; The object tracking apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
perform a management process for managing the tracking target (Tsuji, [0067] and [0068] setting the region/range to be tracked in the images);
and in the management process, adding to a plurality of management targets as another tracking target in accordance with the evaluation value, an object included in[0069] multiple people can be detected across frames (setting a region/target of interest), where multiple people, not just a first person, are identified across images, since the first embodiment only goes one person at a time, the process discussed in paragraph [0069] would reasonably identify a second object region (area in an image containing multiple people), and then compare and identify that region with multiple tracking targets who have yet to be identified (multiple people in the images)).
Regarding claim 11 Tsuji discloses; The object tracking apparatus according to claim 1, wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
performs a management process for managing the tracking target (Tsuji, [0067] and [0068] setting the region/range to be tracked in the images);
and in the management process, deleting from among a plurality of management targets in accordance with a continuous period, a tracking target for which a correspondence with the at least one object region has not been identified in a plurality of successive images included in the of images (Tsuji, [0055] when an object/section cannot determine a degree of similarity and identify something, a label is not assigned, [0063] when it is determined that the region selected is not suitable for similarity associated, a new region is selected).
Regarding claim 12 Tsuji discloses;
An object tracking method, comprising:
acquiring an image from aof images, the image comprising a depiction of an object from among a person, an animal or a vehicle (Tsuji, [0027] multiple images are captured on multiple image capture devices [0036] the device ID and the image frame are acquired from the captured images from the device, [0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images);
detecting at least one object region (Tsuji, [0038] the tracking device extracts a region from the image) surrounding based on at least one model (Tsuji, [0038], the region includes a crowd of people which is the tracked object of interest);
and calculating an evaluation value (Tsuji, [0050] a color information value is calculated for each object region) indicating how reliably the object is included in the at least one object region ([0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images),
wherein a larger evaluation value indicates that the at least one object is more likely to include the object (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity, [0052] the highest value indicates the highest degree of similarity),
and wherein the evaluation value is based on at least one of an output value from the at least one model, a calculated degree that the object is hidden, a calculated degree of overlap of a plurality of object regions in the image, relationship between a detected foreground and a detected background ([0058] the feature extraction section computed the similarity based on degree of overlap between regions/frames);
deciding, in accordance with the evaluation value, a first weight of an appearance similarity from among a plurality of types of similarity which are used to associate the at least one object region with a tracking target in the image sequence (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity), wherein the plurality of types of similarity comprises at least one of: the appearance similarity, a moving speed similarity, a feature point similarity, a size similarity, or a position similarity in three dimensional space (Tsuji, [0033] feature and color information appearance similarity) is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity),
wherein the appearance similarity is calculated a cosine similarity between extracted appearance features of the object and the tracking target (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity, the cosine similarity formula is computed by taking the sum of the vector similarities divided by the square root of the sums of the vector similarities, per Tsuji [0051] and equation 1, the computation of the similarity values are computed functionally equivalent to this ), the first weight being decided for each of the at least one objection regions such that a higher evaluation value is associated with a higher first weight, and the one object regions being associated with one tracking target (Tsuji, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value);
identifying a correspondence between the at least one object region and the tracking target based on the first weight and at least of the plurality of types of similarity (Tsuji, [0028] The feature information between regions is compared to determine if the person in the two regions is the same person, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value, [0079] the comparison unit performs weighting on the similarities to determine whether the similarity is associated with an overlapped region)
and based on the correspondence, add the at least one object region as the new tracking target or delete tracking information for a tracking target (Tsuji, [0054]- [0055] the tracking target flows are determined based upon the similarity/correspondence).
Regarding claim 13 Tsuji discloses; A non-transitory storage medium storing a program for causing a computer to function as an object tracking apparatus, the program causing the computer to (Tsuji, claim 8, a processor is used):
acquire an image from a sequence (Tsuji, [0027] multiple images are captured on multiple image capture devices [0036] the device ID and the image frame are acquired from the captured images from the device);
of images, the image comprising a depiction an object from among a person, an animal or a vehicle (Tsuji, [0027] multiple images are captured on multiple image capture devices [0036] the device ID and the image frame are acquired from the captured images from the device, [0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images);
detect at least one object region (Tsuji, [0038] the tracking device extracts a region from the image) surrounding based on at least one model (Tsuji, [0038], the region includes a crowd of people which is the tracked object of interest);
calculate an evaluation value (Tsuji, [0050] a color information value is calculated for each object region) indicating how reliably the object is included in the at least one object region ([0033] feature and color information is compared for people in the image regions to verify similarity meaning a person is detected in the images),
wherein a larger evaluation value indicates that the at least one object is more likely to include the object (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity, [0052] the highest value indicates the highest degree of similarity),
and wherein the evaluation value is based on at least one of an output value from the at least one model, a calculated degree that the object is hidden, a calculated degree of overlap of a plurality of object regions in the image, relationship between a detected foreground and a detected background ([0058] the feature extraction section computed the similarity based on degree of overlap between regions/frames);
decide, in accordance with the evaluation value, a first weight of an appearance similarity from among a plurality of types of similarity which are used to associate the at least one object region with a tracking target in the image sequence (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, [0050] color evaluation values are determined for regions to compare similarity), wherein the plurality of types of similarity comprises at least one of: the appearance similarity, a moving speed similarity, a feature point similarity, a size similarity, or a position similarity in three dimensional space (Tsuji, [0033] feature and color information appearance similarity) is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity),
wherein the appearance similarity is calculated a cosine similarity between extracted appearance features of the object and the tracking target (Tsuji, [0033] feature and color information is compared for people in the image regions to verify similarity, both feature and color information are appearance features of the objects (people in the image regions) and they are used to verify similarity/identity, the cosine similarity formula is computed by taking the sum of the vector similarities divided by the square root of the sums of the vector similarities, per Tsuji [0051] and equation 1, the computation of the similarity values are computed functionally equivalent to this), the first weight being decided for each of the at least one objection regions such that a higher evaluation value is associated with a higher first weight, and the one object regions being associated with one tracking target (Tsuji, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value);
at least one object region and the tracking target based on the first weight and at least of the plurality of types of similarity (Tsuji, [0028] The feature information between regions is compared to determine if the person in the two regions is the same person, [0077]-[0078] weighting of regions is determined based on the similarity values of the features, such that the higher degree of similarity indicated the higher the value, [0079] the comparison unit performs weighting on the similarities to determine whether the similarity is associated with an overlapped region)
and based on the correspondence, add the at least one object region as the new tracking target or delete tracking information for a tracking target (Tsuji, [0054]-[0055] the tracking target flows are determined based upon the similarity/correspondence).
Regarding claim 14, Tsuji discloses; The object tracking apparatus according to claim 2, wherein the instructions, when executed by the at least one processor, cause the object tracking apparatus to:
identify the correspondence by using a total similarity corresponding to a weighted average of the appearance similarity and the positional similarity, wherein the total similarity uses the first weight as a weight for the appearance similarity (Tsuji, [0077]-[0080] to determine the similarity such that it can be verified that a person in one image corresponds to the person across images, weighting is performed based upon regional overlap in features and the region size and position in the images, [0072] averages of the color similarity and positional similarity are used in correspondence computations).
Regarding claim 15, Tsuji discloses; The object tracking apparatus according to claim 1, wherein the at least one model comprises at least one from among a You Only Look Once (YOLO) model, an EfficientDet model, a CenterNet model, a segmentation-type model, or a feature point model (Tsuji, [0028] the model extracts feature information making it analogous to a feature point model, being that a feature point model is simply a type of model that takes data points and extracts features from them).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. For a listing of analogous prior art as cited by the examiner, please see the attached PTO-892, Notice of References Cited form.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JORDAN M ELLIOTT whose telephone number is (703)756-5463. The examiner can normally be reached M-F 8AM-5PM ET.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/J.M.E./Examiner, Art Unit 2666 /EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666