Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on May 26, 2026 has been entered.
Status of Claims
Claims 1 – 3, 6 – 12, 14 and 16 – 20 remain pending.
Claims 1, 6 – 9, 14 and 16 are amended
Response to Arguments
Applicant's arguments filed 05/26/2026 with respect to claims 1 – 3, 6 – 12, 14 and 16 – 20 have been considered but are moot because the new grounds of rejection do 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, 9 and 10 are rejected under 35 U.S.C 103 as being unpatentable over Peng “State-Aware Re-Identification Feature for Multi-Target Multi-Camera Tracking" (hereinafter Peng) in view of Barburescu US Patent Application Publication No. US-20230245460-A1 (hereinafter Barburescu) and Ma US Patent Application Publication No. US-20080123900-A1 (hereinafter Ma).
Regarding claim 1, Peng discloses a method for multi-target multi-camera tracking (Peng in [Abstract] discloses, “Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras”), comprising: performing multi-target single-camera tracking on an image sequence captured by each of a plurality of cameras that respectively capture different scenes (Peng in [Section – 3] discloses, ““The proposed tracking framework consists of two parts: single camera tracking (SCT) and multiple camera tracking (MCT). In our work, the SCT tracker is utilized to generate trajectories in a single camera. Then a similar strategy as [59] is adopted to cluster in camera trajectories, and the final trajectories are obtained across multiple cameras”), extracting a feature for each of the plurality of tracklets (Peng in [Section – 3.2, Paragraph – 2] discloses, “The fused tracking feature
F
t
r
a
c
k
of the tracklet is composed of five types of features as
F
t
r
a
c
k
= {
F
c
u
r
r
e
n
t
,
F
o
r
i
e
n
t
a
t
i
o
n
,
F
c
l
u
s
t
e
r
,
F
i
n
v
a
l
i
d
,
F
a
v
g
}
); calculating a similarity between any two of the plurality of tracklets based on the extracted features, to establish a similarity matrix Peng in [Section – 3.2, Paragraph – 7] discloses, “A Nc × Nc distance matrix Mcluster is computed to obtain the distance dcluster between fcluster from two tracklets. Specifically, the value in i-th row and j-th column is the Euclidean distance between the i-th cluster center and j-th cluster center from two tracklets”); performing clustering based on the similarity matrix so that tracklets potentially related to a target are aggregated in a set, wherein the tracklets in the set are captured by the same camera or different cameras (Peng in [Section – 3.3.4, Paragraph – 7] discloses, “Tracklet clustering aims to associate all the tracklets except the Disappeared ones. We follow the same strategy as tracklet rectifying. At first, distance matrix MT −cluster is constructed, then a greedy algorithm is adopted to associate the tracklets with the distance threshold
θ
c
l
u
s
t
e
r
”); sorting the tracklets in the set in a temporal order to generate a tracklet sequence (Peng in [Section – 3.3.4, Paragraph – 4-5] discloses, “Given two tracklets, we first sort them by time. The distance between the last detection of the former tracklet and the first detection from the latter one should be less than a maximum distance due to the constraint of velocity ... so two tracklets cannot be associated if the interval between two tracklets is larger than a threshold”).
Ma discloses filtering the tracklets in the set based on at least one of a similarity, a time distance, and a space distance between the tracklets; and using the tracklets in the filtered set as tracking information for the corresponding target (Ma in [0021] discloses about selecting (filtering) based on distance (similarities), “After the tracklets are formed, they may be grouped. Here, a distance may be defined between two tracklets for selecting the tracklets representing the same object in the scene. Both kinematics and appearance constraints may be considered for determining the similarity of two tracklets).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Ma into the system of Peng because it would allow the system to improve the accuracy of tracking by also taking similarity, time, space distance into consideration to determine which tracklet belong to same object.
Peng and Ma in the combination doesn’t disclose about the following limitation as further recited in the claim.
Barburescu discloses extract a tracklet for each target appearing in the image sequence, wherein a plurality of tracklets are extracted for a plurality of targets appearing in a plurality of image sequences captured by the plurality of cameras (Barburescu in [0097] discloses, “The cropped regions in the ReID dataset are also sorted into tracklets each representing regions extracted from video frames belonging to the received video footage”); wherein the tracklet extracted for each target appearing in the image sequence is a set of target boxes that identify the target in a plurality of frames of the image sequence respectively (Barburescu in [0084] discloses, “The track path T.sub.ID={(x.sub.1, y.sub.1), (x.sub.2, y.sub.2), . . . } will represent a vector of spatial coordinates of the centers of the bounding boxes corresponding to the person ID”), wherein the feature extracted for the tracklet is a set of features that are extracted for the target boxes respectively (Barburescu in [0090] discloses, “The VKD neural network learns a numeric appearance descriptor of a person ...The VKD architecture consists of a Resnet feature extractor e.g. Resnet50 or Resnet101 and a classification head”), and wherein a space distance between two tracklets at different times is an Euclidean distance between a certain position on a target box in an end frame of the earlier one of the two tracklets and a corresponding position on a target box in a start frame of the later one of the two tracklets (Barburescu in [0155] discloses, “The Euclidean distances are calculated between the center of the bounding box encompassing a currently detected pallet and the centers of the bounding boxes surrounding each of the most recently previously detected pallets whose ... A currently detected pallet is assigned to a Track of a previously detected pallet for which there is a minimum Euclidean distance between the most recent previous detection of the pallet thereof and the currently detected pallet”), and a time distance between the two tracklets is an absolute value of a difference between a start time of the later tracklet and an end time of the earlier tracklet (Barburescu in [0129 – 0130] discloses about current sampling time and previous sampling time. The system have the information to calculate the temporal difference (“The time interval Δt between the capture of successive video frames”) between an earlier tracked portion and later tracked portion. Therefore, the cited prior arts broadly interpret calculating the time gap between two temporally separated tracked portion, “The time interval Δt between the capture of successive video frames of the video footage will be referred to henceforth as the sampling interval ... the said video frame being captured at a time τ+iΔt, which is henceforth known as the sampling time of the video frame ... a current sampling time tk is given by tk =τ+NΔt, where N<n. A previous sampling time tp is a sampling time that precedes the current sampling time tk and is given by tp =DΔt where 0<D<N. A current video frame Fr(tk ) is a video frame captured at a current sampling time tk . A previous video frame Fr(tp ) is a video frame captured at a previous sampling time tp”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Barburescu into the system of Peng in view of Ma because it would allow the system to improve the accuracy in multi-target system in plurality of camera tracking.
Summary of Citations (Peng)
[Abstract]; “Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras”.
[Section – 3]; “The proposed tracking framework consists of two parts: single camera tracking (SCT) and multiple camera tracking (MCT). In our work, the SCT tracker is utilized to generate trajectories in a single camera. Then a similar strategy as [59] is adopted to cluster in camera trajectories, and the final trajectories are obtained across multiple cameras”.
[Section – 3.2, Paragraph – 2]; “The fused tracking feature
F
t
r
a
c
k
of the tracklet is composed of five types of features as
F
t
r
a
c
k
= {
F
c
u
r
r
e
n
t
,
F
o
r
i
e
n
t
a
t
i
o
n
,
F
c
l
u
s
t
e
r
,
F
i
n
v
a
l
i
d
,
F
a
v
g
}
.
[Section – 3.2, Paragraph – 7]; “A Nc × Nc distance matrix Mcluster is computed to obtain the distance dcluster between fcluster from two tracklets. Specifically, the value in i-th row and j-th column is the Euclidean distance between the i-th cluster center and j-th cluster center from two tracklets”.
[Section – 3.3.2]; “Process the tracklet clustering for every K frames in the current tracklet set, and generate the tracking result from the recent K frames after clustering”.
[Section – 3.3.4, Paragraph – 4-5]; “Given two tracklets, we first sort them by time. The distance between the last detection of the former tracklet and the first detection from the latter one should be less than a maximum distance due to the constraint of velocity ... so two tracklets cannot be associated if the interval between two tracklets is larger than a threshold”.
[Section – 3.3.4, Paragraph – 7]; “Tracklet clustering aims to associate all the tracklets except the Disappeared ones. We follow the same strategy as tracklet rectifying. At first, distance matrix MT −cluster is constructed, then a greedy algorithm is adopted to associate the tracklets with the distance threshold θcluster”.
Summary of Citations (Barburescu)
Paragraph [0084]; “the Person Tracker 402c uses the person detector 402b to establish bounding boxes around every person detected in every image of captured video footage. Related to these bounding boxes, unique IDs will be assigned to each detected person. The track path T.sub.ID={(x.sub.1, y.sub.1), (x.sub.2, y.sub.2), . . . } will represent a vector of spatial coordinates of the centers of the bounding boxes corresponding to the person ID”.
Paragraph [0090]; “The VKD neural network learns a numeric appearance descriptor of a person ...The VKD architecture consists of a Resnet feature extractor e.g. Resnet50 or Resnet101 and a classification head”.
Paragraph [0097]; “The cropped regions in the ReID dataset are also sorted into tracklets each representing regions extracted from video frames belonging to the received video footage”.
Paragraph [0129 – 0130]; “The time interval Δt between the capture of successive video frames of the video footage will be referred to henceforth as the sampling interval ... the said video frame being captured at a time τ+iΔt, which is henceforth known as the sampling time of the video frame ... a current sampling time tk is given by tk =τ+NΔt, where N<n. A previous sampling time tp is a sampling time that precedes the current sampling time tk and is given by tp =DΔt where 0<D<N. A current video frame Fr(tk ) is a video frame captured at a current sampling time tk . A previous video frame Fr(tp ) is a video frame captured at a previous sampling time tp”.
Paragraph [0155]; “The Euclidean distances are calculated between the center of the bounding box encompassing a currently detected pallet and the centers of the bounding boxes surrounding each of the most recently previously detected pallets whose Track status variables have a value of “not assigned” ... A currently detected pallet is assigned to a Track of a previously detected pallet for which there is a minimum Euclidean distance between the most recent previous detection of the pallet thereof and the currently detected pallet”.
Regarding claim 9, apparatus claim 9 corresponds to method claim 1. Therefore, the rejection analysis and motivation to combine of claim 1 is applicable to claim 9.
Regarding claim 10, claim 10 is a computer-readable storage medium claim which
correspond to claim 1. Therefore, claim 10 is rejected for the same reason provided above for
claim 1.
Claims 2, 3, 11 and 12 are rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Barburescu and further in view of Jeon Patent Application Publication No. KR-20180086716-A (hereinafter Jeon) and Johann Patent Application Publication No. GB-2557316-A (hereinafter Johann).
Regarding claims 2, 3, the combination of Peng in view of Ma and Barburescu as a whole teaches claim 1 but fails to teach the further limitations as recited in claims 2, 3. Jeon and Johann teaches claims 2, 3 for the same grounds of rejection and motivation established in the Final Office Action of 02/24/2026
Regarding claim 11, apparatus claim 11 corresponds to method claim 2. Therefore, the rejection analysis and motivation to combine of claim 2 is applicable to claim 11 as set forth in the last Office Action (Final Office Action, 02/24/2026).
Regarding claim 12, apparatus claim 12 corresponds to method claim 3. Therefore, the rejection analysis and motivation to combine of claim 3 is applicable to claim 12 as set forth in the last Office Action (Final Office Action, 02/24/2026).
Claim 6 is rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Barburescu and Ma and further in view of Fisher US Patent Publication No. US-11948313-B2 (hereinafter Fisher).
Regarding claim 6 the combination of Peng in view of Ma and Barburescu as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 6. Fisher teaches claim 6 for the same grounds of rejection and motivation established in the Final Office Action of 02/24/2026
Claims 7 and 14 are rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Ma and Barburescu and further in view of Zhang “ByteTrack: Multi-Object Tracking by Associating Every Detection Box” (hereinafter Zhang) and Tran “Robust Traffic-Aware CityScale Multi-Camera Vehicle Tracking Of Vehicles” (hereinafter Tran).
Regarding claim 7 the combination of Peng in view of Barburescu and Ma as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 7. Zhang and Tran teaches claim 7 for the same grounds of rejection and motivation established in the Final Office Action of 02/24/2026.
Regarding claim 14, Peng in the combination discloses the device according to claim 9.
Zhang further discloses the set of features extracted for target boxes is extracted only from a subset of target boxes that satisfy a plurality of quality conditions (Zhang in [Page – 2; Paragraph – 1 (right side)] discloses, “The similarity can be computed by the IoU or Re-ID feature distance of the predicted box and the detection box”. Furthermore, Zhang in [Page – 4; Paragraph – 3 (left side)] discloses, “We separate all the detection boxes into two parts Dhigh and Dlow according to the detection score threshold τ”), the quality conditions including (Zhang in [Page – 4; Paragraph – 4 (right side)] discloses, “We find it important to use IoU alone as the Similarity#2 in the second association because the low score detection boxes usually contains severe occlusion or motion blur and appearance features are not reliable”).
Tran further discloses at least a size of the target box (Tran in [Section – 3.5.1, Paragraph - 1] discloses, “We calculate the features by using the bounding boxes that size is bigger than ψb”).
Summary of Citations (Tran)
[Section – 3.5.1, Paragraph - 1]; “We calculate the features by using the bounding boxes that size is bigger than ψb”
Summary of Citations (Zhang)
[Page – 2; Paragraph – 1 (right side)]; “The similarity can be computed by the IoU or Re-ID feature dis tance of the predicted box and the detection box”.
[Page – 4; Paragraph – 3 (left side)]; “We separate all the detection boxes into two parts Dhigh and Dlow according to the detection score threshold τ”.
[Page – 4; Paragraph – 4 (right side)]; “We find it important to use IoU alone as the Similarity#2 in the second association because the low score detection boxes usually contains severe occlusion or motion blur and appearance features are not reliable”.
Claims 8 and 20 are rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Barburescu and Ma and further in view of Zhimeng “Multi-Target, Multi-Camera Tracking by Hierarchical Clustering” (hereinafter Zhimeng).
Regarding claim 8 the combination of Peng in view of Barburescu and Ma as a whole teaches claim 1 but fails to teach the further limitations as recited in claim 8. Zhimeng teaches claim 8 for the same grounds of rejection and motivation established in the Final Office Action of 02/24/2026.
Regarding claim 20, Peng in the combination discloses the method according to claim 1.
Zhimeng discloses the feature extracted for each of the plurality of tracklets is extracted using a pedestrian re-identification neural network model (Zhimeng in [Section – 3.2] discloses, “In order to combine the bounding boxes together with their appearance, we trained a person re-identification network to give an appearance feature for each bounding box”).
Summary of Citations (Zhimeng)
[Section – 3.2]; “In order to combine the bounding boxes together with their appearance, we trained a person re-identification network to give an appearance feature for each bounding box”.
Claim 16 is rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Ma, Barburescu and Zhimeng and further in view of Zhang and Tran.
Regarding claim 16, Zhimeng in the combination discloses method according to claim 8.
The combination of Peng, Ma, Barburescu and Zhimeng doesn’t disclose about the following limitations as further recited in the claim.
Zhang discloses the set of features extracted for the target boxes is extracted only from a subset of target boxes that satisfy a plurality of quality conditions (Zhang in [Page – 2; Paragraph – 1 (right side)] discloses, “The similarity can be computed by the IoU or Re-ID feature distance of the predicted box and the detection box”. Furthermore, Zhang in [Page – 4; Paragraph – 3 (left side)] discloses, “We separate all the detection boxes into two parts Dhigh and Dlow according to the detection score threshold τ”), the quality conditions including (Zhang in [Page – 4; Paragraph – 4 (right side)] discloses, “We find it important to use IoU alone as the Similarity#2 in the second association because the low score detection boxes usually contains severe occlusion or motion blur and appearance features are not reliable”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Zhang into the system of Peng in view of Barburescu, Ma and Zhimeng because it would allow the system to accurately do the similarity comparison.
The combination of Peng, Ma, Barburescu, Zhimeng and Zhang doesn’t disclose about the following limitations as further recited in the claim.
Tran further discloses at least a size of the target box (Tran in [Section – 3.5.1, Paragraph - 1] discloses, “We calculate the features by using the bounding boxes that size is bigger than ψb”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Tran into the system of Peng in view of and Ma, Barburescu, Zhimeng and Zhang because it would allow the system to improve the quality and consistency of tracklet feature extraction.
Summary of Citations (Tran)
[Section – 3.5.1, Paragraph - 1]; “We calculate the features by using the bounding boxes that size is bigger than ψb”
Summary of Citations (Zhang)
[Page – 2; Paragraph – 1 (right side)]; “The similarity can be computed by the IoU or Re-ID feature dis tance of the predicted box and the detection box”.
[Page – 4; Paragraph – 3 (left side)]; “We separate all the detection boxes into two parts Dhigh and Dlow according to the detection score threshold τ”.
[Page – 4; Paragraph – 4 (right side)]; “We find it important to use IoU alone as the Similarity#2 in the second association because the low score detection boxes usually contains severe occlusion or motion blur and appearance features are not reliable”.
Claim 17 is rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Ma and Barburescu, Jeon and Johann and further in view of Tran.
Regarding claim 17, Peng in the combination discloses the method according to claim 3.
The combination of Peng, Ma and Barburescu, Jeon and Johann doesn’t disclose about the following limitations as further recited in the claim.
Tran discloses the first similarity between the feature of the tracklet and the average feature of the tracklets currently included in the corresponding candidate set is a cosine similarity between a feature vector of the tracklet and an average feature vector of the tracklets currently included in the corresponding candidate set (Tran in [Section – 3.5.1, Paragraph - 1]; “We compute trajectory features represented by averaged features of bounding boxes of all frames. We calculate the features by using the bounding boxes that size is bigger than ψb. The similarity of tracklets Ti and Tj can be computed using cosine similarity of average feature of trajectory F_i and F_j”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Tran into the system of Peng in view of and Ma, Barburescu, Jeon and Johann because using the cosine similarity between the tracklet feature the system can more accurately determine to keep or reject a tracklet.
Summary of Citations (Tran)
[Section – 3.5.1, Paragraph - 1]; “We compute trajectory features represented by averaged features of bound ing boxes of all frames. We calculate the features by using the bounding boxes that size is bigger than ψb. The similarity of tracklets Ti and Tj can be computed using cosine similarity of average feature of trajectory
F
i
a
n
d
F
j
”.
Claim 19 is rejected under 35 U.S.C 103 as being unpatentable over Peng in view of Ma and Barburescu and further in view of Saleemi US Patent Application Publication No. US-20190206066-A1 (hereinafter Saleemi).
Regarding claim 19, Peng in the combination discloses the method according to claim 1.
The combination of Peng, Barburescu and Ma doesn’t disclose the following limitations as further recited in the claim.
Saleemi discloses the certain position on the target box is a midpoint of a bottom edge of the target box (Saleemi in [0069] discloses, “Mahalanobis distance: The ML detections represented as bounding boxes are converted to points, using either the bounding box center or middle of the bottom edge”).
It would have been obvious to one with one having an ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Saleemi into the system of Peng in view of Ma and Barburescu would help the system in removing incorrectly associated tracklets and improve accuracy of final tracking.
Summary of Citations (Saleemi)
Paragraph [0069]; “Mahalanobis distance: The ML detections represented as bounding boxes are converted to points, using either the bounding box center or middle of the bottom edge”.
Allowable Subject Matter
Claim 18 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter.
Regarding claim 18, the prior art references taken individually or in combination fail to particularly disclose, fairly suggest, or render obvious the limitations as further recited. The applied prior arts Peng, Ma, Barburescu, Jeon and Johann doesn’t disclose the limitation, the conditions are evaluated in sequence such that whether the tracklet satisfies the space distance condition is determined only when the tracklet does not satisfy the first similarity condition, and whether the tracklet satisfies the second similarity condition is determined only when the tracklet satisfies neither the first similarity condition nor the space distance condition. Zhimeng in [Section – 3.3] discloses, “the distance between a trajectory and a tracklet is comprised of three parts: The distance for appearance similarity, the distance of the separation part and the distance of the overlapping part”. Zhimeng discloses about similarity appearance and space distance condition but it doesn’t disclose about sequence of checking the tracklet satisfies the space distance only when the first similarity condition fails and using second similarity condition if both fails.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to ZAID MUHAMMAD SALEH whose telephone number is (703)756-1684.
The examiner can normally be reached M-F 8 am - 5 pm 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, Vu Le can be
reached on (571)272-7332. 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.
/ZAID MUHAMMAD SALEH/
Examiner, Art Unit 2668
06/30/2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights