THE BOEING COMPANYDownload PDFPatent Trials and Appeals BoardMar 8, 20212019004832 (P.T.A.B. Mar. 8, 2021) Copy Citation UNITED STATES PATENT AND TRADEMARK OFFICE UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www.uspto.gov APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 15/474,275 03/30/2017 Jan Wei Pan B86918 2540US.1 (0169.2) 1317 128836 7590 03/08/2021 WOMBLE BOND DICKINSON (US) LLP/BOEING Attn: IP Docketing P.O. Box 7037 Atlanta, GA 30357-0037 EXAMINER BERNARDI, BRENDA C ART UNIT PAPER NUMBER 2667 NOTIFICATION DATE DELIVERY MODE 03/08/2021 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address(es): ipdocketing@wbd-us.com patentadmin@Boeing.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE ____________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________ Ex parte JAN WEI PAN, HIEU TAT NGUYEN, ZACHARY JORGENSEN, and YURI LEVCHUK Appeal 2019-004832 Application 15/474,275 Technology Center 2600 ____________ Before JOHN A. EVANS, JOYCE CRAIG, and SCOTT E. BAIN, Administrative Patent Judges. EVANS, Administrative Patent Judge. DECISION ON APPEAL1 Appellant appeals under 35 U.S.C. § 134(a) from the Examiner’s Final decision to reject Claims 1–21. Appeal Br. 5. We have jurisdiction under 35 U.S.C. § 6. We REVERSE.2 1 We use the word “Appellant” to refer to “applicant” as defined in 37 C.F.R. § 1.42. Appellant identifies The Boeing Company, as the real party in interest. Appeal Br. 1. 2 Throughout this Decision, we refer to the Appeal Brief filed March 1, 2019 (“Appeal Br.”); the Reply Brief filed June 3, 2019 (“Reply Br.”); the Final Office Action mailed October 19, 2018 (“Final Act.”); the Examiner’s Answer mailed April 1, 2019 (“Ans.”); and the Specification filed March 30, 2017 (“Spec.”). Appeal 2019-004832 Application 15/474,275 2 STATEMENT OF THE CASE CLAIMED SUBJECT MATTER The claims relate to automated object tracking in a video feed. See Abstract. CLAIMS Claims 1, 8, and 15 are independent. Claim 1 is illustrative and reproduced below: 1. A method for automated object tracking in a video feed, the method comprising: receiving a video feed including a plurality of frames; sequentially processing each frame of the plurality of frames, including at least: detecting a plurality of objects in the frame, and for each object of the plurality of objects, assigning the object to a track fragment for the object in the frame, wherein the plurality of objects are detected and assigned using computer vision, machine learning, and a catalog of kinematic, visual, temporal or machine learning-based features of identifiable objects; and identifying a kinematic, visual, temporal or machine learning-based feature of the object, and storing the kinematic, visual, temporal or machine learning-based feature in metadata associated with the track fragment to which the object is assigned; and further for at least some of the plurality of frames, identifying a track fragment for the object in one or more earlier frames based on a comparison of the kinematic, visual, temporal or machine learning-based feature of the object and a corresponding kinematic, visual, temporal or machine learning-based feature in metadata associated with the track fragment for the object in the one or more earlier frames; and Appeal 2019-004832 Application 15/474,275 3 linking the track fragment for the object in the frame and the track fragment for the object in the one or more earlier frames to form a longer track fragment that is a track of the object; and for each object of the plurality of objects, transforming the track of the object to a common frame of reference to generate a common reference frame having the tracks of the plurality of objects mapped thereto; and outputting the video feed with the common reference frame and the mapped tracks of the plurality of objects as an overlay thereon. REFERENCES Name3 Reference Date Han US 2005/0104727 A1 May 19, 2005 Yang US 2009/0002489 A1 Jan. 1, 2009 Jamtgaard US 2012/0046044 A1 Feb. 23, 2012 Divakaran US 2014/0347475 A1 Nov. 27, 2014 REJECTIONS4 AT ISSUE 1. Claims 1, 3, 6–8, 10, 13–15, 17, 20, and 21 stand rejected under 35 U.S.C. § 103 as obvious over Divakaran. Final Act. 4–16. 2. Claims 2, 9, and 16 stand rejected under 35 U.S.C. § 103 as obvious over Divakaran and Yang. Final Act. 17. 3. Claims 4, 11, and 18 stand rejected under 35 U.S.C. § 103 as obvious over Divakaran and Han. Final Act. 18–20. 4. Claims 5, 12, and 19 stand rejected under 35 U.S.C. § 103 as 3 All citations herein to the references are by reference to the first named inventor/author only. 4 The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Final Act. 2. Appeal 2019-004832 Application 15/474,275 4 obvious over Divakaran and Jamtgaard. Final Act. 20–22. ANALYSIS We have reviewed the rejections of Claims 1–21 in light of Appellant’s arguments that the Examiner erred. We are persuaded of error. We provide the following explanation to highlight and address specific arguments and findings primarily for emphasis. We consider Appellant’s arguments as they are presented in the Appeal Brief and the Reply Brief. CLAIMS 1, 3, 6–8, 10, 13–15, 17, 20, AND 21: OBVIOUSNESS OVER DIVAKARAN. Appellant argues these claims as a group specifically over the recitations of Claim 1. Appeal Br. 6 (“Independent claims 8 and 15 recite substantially similar limitations as independent claim 1.”). Therefore, we decide the appeal of the § 103 rejections on the basis of Claim 1 and refer to the rejected claims collectively herein as “the claims.” See 37 C.F.R. § 41.37(c)(1)(iv); In re King, 801 F.2d 1324, 1325 (Fed. Cir. 1986). Independent Claim 1 recites, inter alia, “identifying a kinematic, visual, temporal or machine learning-based feature of the object, and storing the kinematic, visual, temporal or machine learning-based feature in metadata associated with the track fragment to which the object is assigned.” The Examiner finds Divakaran’s “learned appearance model 616” and “observation-based motion model 618” teaches this limitation. Final Act. 7 (emphasis omitted) (citing Divakaran, ¶¶ 27, 29, 57, 60, 64, 69, 98). According to Appellant, Divakaran’s learned appearance model 616 is embodied “as descriptive appearance model that uses a spatially encoded color histogram to represent the appearance of a human person” and the Appeal 2019-004832 Application 15/474,275 5 observation-based motion model 618 is used to generate “a motion prediction.” Appeal Br. 6 (citing Divakaran, ¶¶ 60, 66, FIG. 6). Appellant contends, however, “nowhere does Divakaran teach or suggest that the learned appearance model 616 and the observation-based motion model 618 store the features in metadata associated with the track fragment to which the object is assigned, as stated in independent claims 1, 8 and 15.” Id. (emphasis omitted). Appellant further argues, contrary to the Examiner’s findings, the kinematics model 618 is not an example of metadata. Id. Appellant argues rather, kinematic features are examples of information that can be stored in metadata. Id. For storing metadata, the Examiner cites non-specifically to the rejection of dependent Claim 5: storing the kinematic, visual, temporal or machine learning- based feature in metadata associated with the track fragment to which the object is assigned are inclusive of (“learned appearance model 616” and “observation-based motion model 618”; par. [0027], [0029], [0057], [0060], [0064], [0069], [0098]; see rejection of dependent claim 5). Ans. 3. Appellant reiterates: Nowhere does Divakaran teach or suggest that the learned appearance model 616 and the observation-based motion model 618 store the kinematic, visual, temporal or machine learning- based feature in metadata associated with the track fragment to which the object is assigned, as stated in independent claims 1, 8 and 15. Reply Br. 2–3 (emphasis omitted). To rebut Appellant’s contention, the Examiner cites generally, but without providing any specifics, to seven paragraphs of the Divakaran Appeal 2019-004832 Application 15/474,275 6 disclosure. See Ans. 3 (citing generally Divakaran, ¶¶ 27, 29, 57, 60, 64, 69, 98). The Answer implies that Divakaran may teach or suggest the disputed limitation and leaves to this Panel of the Board the burden to formulate the details of the obviousness rejection. However, “[i]t is not the Board’s burden or the burden of any panel of this Board to initially assert and to even formulate the details of a prima facie case of obviousness within 35 U.S.C. 103. This burden of proof rests solely upon the examiner.” Ex parte Forest, 2002 WL 33951036, at *2 (BPAI May 30, 2002) (citing In re Oetiker, 977 F.2d 1443, 1445 (Fed. Cir. 1992)). It is the policy of the USPTO: for the examiner to compare the rejected claims feature-by- feature or limitation-by-limitation with each of the references relied upon in the rejection. This comparison should map the language of the claims to the specific page number, column number, line number, drawing number, drawing reference number, and/or quotation from each reference relied upon. Note MPEP § 706.02(j) and MPEP § 1208 for the correct methodologies. Ex parte Forest, 2002 WL 33951036, at *2. The Examiner does not draw our attention specifically to where the prior art discloses or teaches that kinematic, visual, temporal or machine learning-based features are stored in metadata associated with the track fragment to which the object is assigned, as recited in independent Claims 1, 8, and 15. In view of the foregoing, we decline to sustain the rejection of Claims 1, 3, 6–8, 10, 13–15, 17, 20, and 21 under 35 U.S.C. § 103 as obvious over Divakaran. Appeal 2019-004832 Application 15/474,275 7 CLAIMS 2, 9, AND 16: OBVIOUSNESS OVER DIVAKARAN AND YANG. Appellant contends Yang fails to complete Divakaran with respect to the limitation disputed above. Appeal Br. 9. The Examiner does not apply Yang to teach the disputed limitation. See Ans. 7. In view of the foregoing, we decline to sustain the rejection of Claims 2, 9, and 16 under 35 U.S.C. § 103 as obvious over Divakaran and Yang. CLAIMS 4, 11, AND 18: OBVIOUSNESS OVER DIVAKARAN AND HAN. Appellant contends Han fails to complete Divakaran with respect to the limitation disputed above. Appeal Br. 10. The Examiner does not apply Han to teach the disputed limitation. See Ans. 7. In view of the foregoing, we decline to sustain the rejection of Claims 4, 11, and 18 under 35 U.S.C. § 103 as obvious over Divakaran and Han. CLAIMS 5, 12, AND 19: OBVIOUSNESS OVER DIVAKARAN AND JAMTGAARD. Appellant contends Jamtgaard fails to complete Divakaran with respect to the limitation disputed above. Appeal Br. 11. The Examiner does not apply Jamtgaard to teach the disputed limitation. See Ans. 8. Appeal 2019-004832 Application 15/474,275 8 In view of the foregoing, we decline to sustain the rejection of Claims 5, 12, and 19 under 35 U.S.C. § 103 as obvious over Divakaran and Jamtgaard. CONCLUSION In summary: Claim(s) Rejected 35 U.S.C. § Reference(s)/Basis Affirmed Reversed 1, 3, 6–8, 10, 13–15, 17, 20, 21 103 Divakaran 1, 3, 6–8, 10, 13–15, 17, 20, 21 2, 9, 16 103 Divakaran, Yang 2, 9, 16 4, 11, 18 103 Divakaran, Han 4, 11, 18 5, 12, 19 103 Divakaran, Jamtgaard 5, 12, 19 Overall Outcome 1–21 REVERSED Copy with citationCopy as parenthetical citation