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 .
Application has canceled claims 2-3, 7-8, 11, and 13-14. Thus, application has pending claims 1, 3-6, 9-10, 12, and 15-16.
Response to Arguments
Applicant’s arguments, “In ZHU, the so-called ‘weighted average similarity distance’ is calculated…” beginning on page 9 filed 10/24/2025, with respect to claim 1 has been fully considered but the Examiner respectfully disagrees. As Applicant has pointed out, ZHU does use HSV color channels for the feature distances. ZHU then uses the feature distances to check the match between the M and N objects between the current frame and subsequent frame, i.e., L images, as disclosed in ¶126. The feature similarity distance uses a weighted average which is then used to perform a matching judgment. While ZHU uses a minimum threshold, it would have been obvious to one of ordinary skill in the art to modify ZHU’s threshold to be a maximum threshold, as ZHU’s minimum threshold still refers to the second object that has the greatest similarity corresponding to the first object. Additionally, based on broadest reasonable interpretation, the “weighted movement average” can be interpreted as a different weight of the subsequent frames to the original/target frame. Of all the reference images, i.e., multiple frames / subsequent frames, in ZHU, the image with the minimum similarity distance is selected for matching, wherein the similarity distance is calculated using the weighted average as disclosed in FIG. 4 and ¶121-129. It would have been obvious for one of ordinary skill in the art to understand that the weighted average of ZHU would be accurate to the “weighted movement average,” as ZHU’s, especially in combination with GUAN, weighted average would meet the limitation of different weights across a sequence of frames, wherein the most similar would be the frame with the smallest similarity difference (or closest features) to the target frame. Therefore, ZHU at least uses a weighted movement average according to (note, the broadest reasonable interpretation of according to means “in a manner most conforming with”) calculating feature distances between each second object and the first objects.
Additionally, Applicant arguments, “In contrast, ZHANG addresses…” beginning on page 11 filed 10/24/2025, with respect to amended claim 1 has been fully considered by the Examiner respectfully disagrees. Applicant alleges that ZHANG is using a loss function weighting mechanism used during neural network training. Examiner agrees that ZHANG’s loss function is used for training initially, however, once the training is complete in ZHANG, the loss detection in the Tracklets, which includes the exponential function
e
-
s
b
, is used to acquire the candidate tracked target of the current and previous frames. The Trackles does use a loss function and the detection is directly used for the object identification as disclosed in page 10-11/30 and FIG. 4. Based on the broadest reasonable interpretation, the use of the exponential in the loss function does disclose the varying matching weights between frames, wherein the frames used in the Tracklets module are also temporally different from the target frame as disclosed in ZHANG page 7/30. The target relevance determination takes the temporal difference into consideration for the distance calculation.
In addressing the actual combination and motivations of record, Applicant contends on page 12 that the motivation to combine ZHANG with GUAN, in combination with ZHU, “would not be straightforward for a person skilled in the art to combine,” is technically unsound and legally unsupported. However, the motivation statement was legally supported by citing GUANT, the cited art reference, per MPEP 2143(I)(G), that finds that the motivation to lead one of ordinary skill in the art to modify the references can come from the prior art itself. On the other hand, Applicant cites to no authority for the contention that a motivation to combine must be directly related to a primary reference’s stated “problem” being addressed by the primary reference. Based on these facts, this action is made FINAL.
Examiner would like to note that the Applicant is attempting to include a temporal calculation in the weighted movement average. However, in the claim language, only the matching weight uses the time interval. If the Applicant were to amend that the claim to include a temporal calculation or timestamp (for example, “calculating a weighted movement average of the feature distances between each second object and the first objects at the time point t” as seen in the Specification, filed 06/27/2022, ¶57 and ¶64-66), this would overcome the prior art and move prosecution forward.
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, 4-6, 8-10, 12, and 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Shuo-sen GUAN CN-111402294-A, hereinafter GUAN, in further view of HONG ZHU CN-102592288-B, hereinafter ZHU, and KUI ZHANG CN-111681264-A, hereinafter ZHANG.
As per claim 1, GUAN discloses an object identification and tracking method, comprising:detecting M first objects in a target image, M being a positive integer (see GUAN page 5/56 step S204, wherein the candidate area has the area of each to-be-tracked target in a video frame. The to-be-tracked target can be one or more);obtaining N second objects in tracking data in first video data, the first video data comprising L images before the target image, N and L being both positive integers, and L being determined in accordance with a matching weight of each second object with each first object (see GUAN page 5/56 step 206, wherein the to-be-tracked target in the history track, i.e., N second objects, and the historic video frame set, i.e., L images before the target image, are disclosed. See further GUAN page 7/56, wherein the matching weight is disclosed; the smaller the weight, the larger the time distance is to the first object. See also GUAN page 15/56, wherein the weight is used to determine the historical target track);matching the M first objects with the N second objects to determine a correspondence between each first object and each second object, the matching weight of each second object with the first object varying with a time interval between a current image where the second object is located and the target image (see GUAN page 6-7/56 step S210, wherein the first and second motion characteristic sets correspond to the history and target area respectively, i.e., N and M objects, and a computer device is capable of calculating the target history track with the candidate area. See further GUAN lower page 7/56, wherein the varying matching weight is disclosed; the smaller the weight, the larger the time distance is to the first object);and tracking each first object in accordance with matching results of the M first objects and the N second objects (see GUAN lower page 7/56 and 8/56, wherein the history track is matched to the target candidate according to the matching result);the matching weights of each second object with the first objects increasing as the time interval between the current image where the second object is located and the target image decreases (see GUAN bottom of page 7/56 and 15/56, wherein the weight is larger when the time distance is shorter);
However, GUAN fails to explicitly disclose where ZHU teaches:wherein the matching the M first objects with the N second objects to determine the correspondence between each first object and each second object comprises:calculating feature distances between a feature vector of each of the N second objects in each of the L images and feature vectors of the M first objects (see ZHU ¶109-111, wherein the feature similarity distance is disclosed between the target and the to be matched, i.e., M and N first and second objections, using HSV color components, i.e., feature vectors. See prior ¶72, wherein the current and subsequent frames are disclosed, i.e., L images); calculating a weighted movement average of the feature distances between each second object and the first objects in turn (see ZHU ¶117-120, wherein the similar distance is used to calculate weighted average of the targets as disclosed in ¶109); and enabling the first object and the second object whose weighted movement average is less than a predetermined threshold and is smallest to correspond to each other (see ZHU ¶127-128, wherein if the average d is less than the threshold, the target and target to be matched, i.e., first and second objects, are determined to match. See also ¶129 and FIGS. 2-4).
While ZHU uses a minimum threshold, it would have been obvious to one of ordinary skill in the art to modify ZHU’s threshold to be a maximum threshold. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify GUAN’s method by using ZHU’s teaching by including the weighted average threshold to the first and second object correspondence in order to guarantee the match between the first and second object by using a weighted threshold.
However, GUAN, in combination with ZHU, fails to explicitly disclose where ZHANG teaches:The object identification and tracking method according to claim 1, wherein the matching weights of the second objects with the first objects vary exponentially as the time intervals between the images where the second objects are located and the target image decrease (see ZHANG page 7-8/30 and more specifically 12/30 step s323, wherein the Tracklets module is continuously updated a number of times using a loss. The frames used in the Tracklets module are temporally offset, and is used in the target relevance determination, which includes the weight values and distance, in step s3. See additionally ZHANG page 10/30, wherein the loss function used in the Tracklets module utilizes the exponential
e
-
s
b
for the matching weight for object identification).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify GUAN’s, in combination with ZHU, method by using ZHANG’s teaching by including the variability to the matching weights between the first and second objects in order to more accurately account for situations where the object matching may not be clear.
As per claim 4, GUAN discloses the object identification and tracking method according to claim 1, wherein the detecting the M first objects in the target image comprises extracting feature vectors of the M first objects in the target image, wherein the obtaining the N second objects in the tracking data in the first video data comprises generating a feature vector corresponding to each tracked second object in the first video data, wherein the matching the M first objects with the N second objects comprises:calculating a feature distance between the feature vector of each first object and the feature vector of each second object (see GUAN page 6-7/56 step S10, wherein feature distance is calculated using the target history track and the optical flow motion features candidate area tracks);and determining a maximum match of the feature vector of each first object with the feature vectors of the N second objects in accordance with the feature distances, and taking the maximum match as the first object and the second object corresponding to each other (see GUAN page 12/56, wherein the history track and each target candidate area are matched using the first and second correlation matrices, i.e., the feature vectors of the first and second objects. Fusion is also disclosed to obtain a higher matching accuracy, i.e., maximum match).
As per claim 5, GUAN discloses the object identification and tracking method according to claim 1, wherein the tracking the first objects in accordance with the matching results of the M first objects and the N second objects comprises:when there is a first object matching a second object, tracking the first object and the second object as a same object (see GUAN upper page 12/56, wherein the history track, i.e., the target area of the second object, and the target candidate area, i.e., the target area of the first object, are disclosed);and when there is no first object matching a second object, adding a new tracking object in accordance with the second object (see GUAN lower page 12/56 step S502, wherein the consecutive frame matching failure occurs when trying to achieve the target track, i.e., target area of the first object, then obtain a plurality of candidate historical track set, i.e., a new track object in accordance with the second object).
As per claim 6, the rationale provided in claim 1 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses an electronic apparatus, comprising a processor, a memory, and a program stored in the memory (GUAN page 22/56, wherein a computer device comprising a memory and processor is disclosed).
As per claim 8, the rationale provided in claim 3 is incorporated herein. In addition, GUAN, in combination with ZHU and ZHANG, discloses an electronic apparatus, comprising a processor, a memory, and a program stored in the memory (GUAN page 22/56, wherein a computer device comprising a memory and processor is disclosed).
As per claim 9, the rationale provided in claim 4 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses an electronic apparatus, comprising a processor, a memory, and a program stored in the memory (GUAN page 22/56, wherein a computer device comprising a memory and processor is disclosed).
As per claim 10, the rationale provided in claim 5 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses an electronic apparatus, comprising a processor, a memory, and a program stored in the memory (GUAN page 22/56, wherein a computer device comprising a memory and processor is disclosed).
As per claim 12, the rationale provided in claim 1 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses a non-transitory computer-readable storage medium (GUAN page 22/56, wherein a computer-readable storage medium storing a program is disclosed).
As per claim 15, the rationale provided in claim 4 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses a non-transitory computer-readable storage medium (GUAN page 22/56, wherein a computer-readable storage medium storing a program is disclosed).
As per claim 16, the rationale provided in claim 5 is incorporated herein. In addition, GUAN, in combination with ZHU, discloses a non-transitory computer-readable storage medium (GUAN page 22/56, wherein a computer-readable storage medium storing a program is disclosed).
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 Bradley Obas Felix whose telephone number is (703)756-1314. The examiner can normally be reached M-F 8-5 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, Vincent Rudolph can be reached at 5712728243. 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.
/BRADLEY O FELIX/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671