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 .
Response to Arguments
Applicant's arguments filed 01/09/2026 have been fully considered but they are not persuasive. It is important to note that claims are broader than Applicants argument.
Prior art D1 explicitly teach as initial step on page 2 “That is to correctly associate a new detection with an existing track, while not being distracted by clutter or noise. This is also referred to as observation-to-track assignment. Association keeps a track alive.”
Then on page 10 D1 also teaches combining separate pieces to form complex target page 10 “The separate pieces can be combined to form a more complete picture of the target. Target kinematics and desert location tell the ATR that a ground vehicle or low-flying helicopter will be kicking up dust from the desert floor. This changes the types of algorithms best-suited for detection, recognition and video enhancement”. Although it does not explicitly say that it associates tracklets to the single track, it is implicit as complex object has its own track and therefore pieces movement is associated with movement of the whole object. As evidence of such transformation (and evidence that the procedure is known in the art) Examiner added reference by D0 US 20120093359 A1 which in paragraph [0067] explicitly teaches “In some embodiments, the batch detection processor 320 includes a track cluster module. The track cluster module 350 further processes the tracks, enhanced or otherwise, to determine whether one or more of the tracks are associated with a common object. If so, the independent tracks can be replaced by a single track. The single track can be one of the two or more individual tracks, or some combination, such as a composite, of the two or more individual tracks. One such composite track includes an averaged position track determined as an algebraic average of the two or more tracks. Other composites may include further processing, such as filtering to remove detected rotation. Ultimately, the clustered tracks are available as output indicative of detected objects. In at least some embodiments, the output includes a respective state vector for each object. The state vectors may include six degrees of freedom (e.g., position (x,y,z) and velocity (V.sub.x, V.sub.y, V.sub.z)).”
Prior art references
D1 SCHACHTER BRUCE J: "Unification of automatic target tracking and automatic target recognition"(cited in IDS and has been attached in its entirety)
D2 VEIT LEONHARDT ET AL: "A region-growing based clustering approach for extended object tracking", (cited in IDS)
D3 Yaakov Bar-Shalom ET AL: "Tracking in a Cluttered Environment with Probabilistic Data Association", (cited in IDS)
D4 POWER C MET AL: "Context-based methods for track association", (cited in IDS)
D5 US 20200377124
D6 JABBARIAN M ET AL: "Target tracking in pulse-doppler MIMO radar by extended kalman filter using velocity vector", (cited in IDS)
D0 US 20120093359 A1
Claim Rejections - 35 USC § 102
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.
Claim(s) 1-6, 10-12 and 19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by D1 as evidenced by D0.
Regarding claims 1, 19 D1 teaches
Tracking computation unit (introduction radar processes data and therefore processor is implicit)
detecting detection points in the radar (introduction radar in page 1) frames ;(abstract “detection”)
associating the detection points of a present radar frame with a plurality of tracklets, (abstract “classification”, page 2 “Target tracking algorithms have one overriding objective. That is to correctly associate a new detection with an existing track, while not being distracted by clutter or noise. This is also referred to as observation-to-track assignment. Association keeps a track alive. Traditional trackers only track moving point-like objects. Trackers tied to EO/IR ATRs commonly track both stationary and moving objects, from stationary or moving platforms, where the object is more substantially represented than just a point. ATRs that process just single frame imagery, like with a step-stare EO/IR sensor or conventional SAR, don’t have trackers”)
wherein each tracklet is a track of at least one detection point observed over multiple radar frames; and (implicit page 1 introduction “locates objects of possible interest in successive frames of imagery”)
associating the tracklets based on at least one feature-parameter with at least one object-track. (fig. 1 “merge/split/ group” page 5 and 6, and page 10 “separate pieces can be combined to form a more complete picture of the target”)
2. D1 (page 4 Kalman filter and Gausian Markov using kinematic tracking model) discloses subject matter of claim 2, wherein obtaining and/or maintaining the tracklets and the object-tracks is based on at least one dynamical system model.
Regarding claim 3 D1 teaches
3. (Currently Amended) The method according to claim 1 further comprising:
predicting one or a plurality of parameters of each tracklet for the present radar frame by propagating the dynamical system model, wherein the parameters of each tracklet include at least one of a position or a velocity or an acceleration, and (page 3, 4 section tracking, page 5 fig 1 Track filtering prediction)
a covariance of the tracklet in a radar frame(implicit each target is tracked and hence covariance of target in different frames is also taken into account to make sure that the it is the same target in different frames); and
correcting the parameters of each tracklet based on the detection points that are associated with a corresponding tracklet,(page 4 eq 1 state vector xk+1 obtained from state vector xk, fig. 5 Detection track association + track management)
wherein the predicting is performed before the associating of the detection points with the tracklets and the correcting is performed after the associating of the detection points with the tracklets.(fig. 5 track filtering/prediction is fed into Detection track association and then track management is used after track association)
4. D1 (figure 1: gating, spatial primacy; page 6: 2. Gating; page 5: a. Track Initiation) discloses the subject-matter of claim 4, wherein in the associating of the detection points to tracklets, a detection point is associated with a tracklet, if a position of the detection point is within a gate of a tracklet, wherein new tracklets are initialized from the detection points whenever a criterion for assignment of a detection is not met for any existing tracklets.
5. D1 (page 6: 2. Gating : "rectangular"; "kinematic gates") discloses the subject- matter of claim 5, wherein a gate for each tracklet is either fixed in size or is adaptive in size, wherein the size of the gate correlates with a covariance of the tracklet, in particular such that the size of the gate is increased if the covariance increases, or vice versa.
6. D1 (page 6: "nearest neighbor assignment) discloses the subject-matter of claim 6, wherein in the associating of the detection points with the tracklets, a detection point is associated with the tracklet having a position closest to the detecting point.).
10. D1 (figure 1: Track Filtering; page 6) discloses implicitly the subject-matter of claim 10, wherein the method further comprises correcting parameters of an object-track by updating the parameters of the object-track based on a predicted velocity, as this process is inherent to the Kalman filtering process.).
11. D1 (page 6: “track record") discloses the subject-matter of claim 11, wherein each tracklet comprises metadata including at least one of a status of the tracklet.).
12. D1 (page 5: "track initiation", figure 1 : initiate, track files) discloses the subject- matter of claim 12, wherein the method further comprises: updating the metadata of the tracklets; and initializing detection points as new tracklets that are not associated toexisting tracklets, wherein the updating of the metadata and the initializing of detection points as new tracklets are performed after the associating of the detection points with the tracklets.).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically 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.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 in view of D3.
Regarding claim 7 D1 teaches
7. (Currently Amended) The method according to claim 1,
wherein in the associating of the detection points with tracklets, a detection point is probabilistically associated with multiple tracklets,(page 5 probabilistic data association filter)
but does not teach while D3 teaches
wherein probabilistic values determining a probability that a detection point is associated with a tracklet are increased if a distance between a position of the detection point and a predicted position of the tracklet decreases, or vice versa.(fig. 5 and fig. 6)
It would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 with invention by D3 in order to identify the cluster of points associated with single target.
Claim(s) 8-9 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 in view of D4.
Regarding claims 8-9 D1 does not teach but D4 teaches
8. (Currently Amended) The method according to claim 1,
wherein a feature-parameter for grouping of the tracklets, based on which the tracklets are clustered into the object-tracks, comprises an overlap of gates of individual tracklets in at least the present radar frame and/or a summed overlap of the gates of the individual tracklets in multiple previous radar frames.(page 1136 “nearest neighbor algorithm”)
9. (Currently Amended) The method according to claim 1, wherein grouping of the tracklets is performed by a clustering method. (page 1136 “Mahalonobis distance”)
It would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 with invention by D4 in order to identify the cluster of points associated with single target.
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1.
Regarding claim 13 D1 teaches
Kalman filter is used for modelling the dynamics of the object-tracks
But does not explicitly teach
13. (Currently Amended) The method according to claim 1,
wherein an alpha-beta filter is used for modelling dynamics of the tracklets and a or, wherein an alpha-beta filter is used for modelling the dynamics of the tracklets and the object-tracks.
One of ordinary skills in the art knows that alpha betta filters closely related to Kalman filters and to linear state observers used in control theory. Its principal advantage is that it does not require a detailed system model. And therefore, it would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 to use alpha beta filter for modeling dynamics of the tracklet in order to avoid detailed system model.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 in view of D5.
Regarding claim 14 D1 teaches using Kalman filter but does not teach while D5 teaches
Using multiple models .[0002,0005, 0044, fig. 1A,b]
And therefore limitation
wherein an object model is inferred from a library of object models for each object-track and a switching Kalman filter is used for modelling the object-tracks, wherein a switch state of the switching Kalman filter represents an object class is just obvious known modification (as evidenced by https://en.wikipedia.org/wiki/Switching_Kalman_filter) in order to increase robustness of the result.
Claim(s) 15-18, 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 in view of D6.
Regarding claim 15 D1 teaches
15. (Currently Amended) The method according claim 1, for tracking at least one object in measurement data of a radar system including a plurality of, in particular consecutive, radar frames acquired by a radar system, comprising:
detecting detection points in the radar frames; (introduction)
wherein the plurality of radar frames comprised in the measurement data is a first plurality of radar frames acquired by a first radar unit; (introduction)
wherein the radar frames contain range, doppler and angle measurements, (Section 1.0, 2.0)
wherein a multidimensional velocity vector is determined from the doppler measurements for at least one detection point that is detectable in synchronized radar frames of the first and the second plurality of radar frames, wherein the determining of the multidimensional velocity vector is based on the corresponding doppler measurements of the first and the second radar units(Section 1.0, 2.0)
D1 also teaches
16. (Currently Amended) The method according to claim 15,
wherein the multidimensional velocity vectors(section 3.0. 3D system x is a vector and hence x dot is also vector in 3D) are used in a correcting of parameters of a track, in particular in the correcting of the parameters of the tracklet.(eq. 1)
17. (Currently Amended) The method according to claim 15,
wherein the multidimensional velocity vectors are used in an updating of metadata of a track and in an initializing of detection points as new tracks, in particular in the updating of the metadata of the tracklets and in the initializing of detection points as new tracklets.(Section 3.0 eq.1)
but does not teach which D6 teaches
wherein the measurement data further includes a second plurality of radar frames acquired by a second radar unit that is non-colocated to the first radar unit,(fig. 1)
wherein the first and the second plurality of radar frames are synchronized and at least partially overlap, (fig. 1)
20. (Currently Amended) The radar system according to claim 19, further comprising:
a second radar unit configured to acquire a plurality of radar frames by transmitting and receiving radar signals reflected on potential objects to be tracked in a field-of-view of the second radar unit,(fig 1)
wherein the field of view of the first radar unit and the field-of-view of the second radar unit at least partially overlap.(fig. 1)
It would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 with invention by D6 in order triangulate the position of the target and based on obtained position to track the target.
Regarding 18 D1 also teaches
18. (Currently Amended) The method according to claim 15,
wherein a status of a track is changed immediately from a tentative state to a tracked state if the track is inside an area around a position of a detection point for which a multidimensional vector is determined, and if a comparison measure, of the multidimensional velocity vector and multidimensional velocity vectors of a detection point's neighboring multidimensional velocity vectors is equal or greater than a predetermined threshold (page 6 gating).
if not explicit then ant least It would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 in order to perform greedy nearest neighbor algorithm and match not only positions but velocities and other parameters.
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1.
Although does not explicitly teach
21. (Currently Amended) A vehicle in which a radar system according to claim 19 is mounted, wherein the vehicle is an aircraft or watercraft or land vehicle, wherein the vehicle is either manned or unmanned.
It would be obvious to one of ordinary skills in the art at the time of the filing to modify invention by D1 in order to create mobile radar system which can change the position and therefore get radar data in different regions.
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 HELENA SERAYDARYAN whose telephone number is (571)270-0706. The examiner can normally be reached on M-T, 7:30-5pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Resha Desai can be reached on (571) 270-7792. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/HELENA H SERAYDARYAN/ Examiner, Art Unit 3648C
/RESHA DESAI/Supervisory Patent Examiner, Art Unit 3648