Ex Parte Kiryati et alDownload PDFPatent Trial and Appeal BoardJan 28, 201410930254 (P.T.A.B. Jan. 28, 2014) 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. 10/930,254 08/31/2004 Nahum Kiryati 0001828USU/4269 9708 27623 7590 01/28/2014 OHLANDT, GREELEY, RUGGIERO & PERLE, LLP ONE LANDMARK SQUARE, 10TH FLOOR STAMFORD, CT 06901 EXAMINER WERNER, DAVID N ART UNIT PAPER NUMBER 2487 MAIL DATE DELIVERY MODE 01/28/2014 PAPER 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. PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE ____________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________ Ex parte NAHUM KIRYATI, TAMAR RIKLIN-RAVIV, YAN IVANCHENKO, SHAY ROCHEL, IGAL DVIR, and DANIEL HARARI, ____________ Appeal 2011-007346 Application 10/930,254 Technology Center 2400 ____________ Before ST. JOHN COURTENAY III, THU A. DANG, and CARL W. WHITEHEAD JR., Administrative Patent Judges. COURTENAY, Administrative Patent Judge. DECISION ON APPEAL Appeal 2011-007346 Application 10/930,254 2 STATEMENT OF THE CASE The Examiner finally rejected claims 1, 8, 11, 14, 15, 17-19, 23-25, 32, 35, 38, 39, 41-43, 46, 47, 49, and 50. Appellants appeal therefrom under 35 U.S.C. § 134(a). We have jurisdiction under 35 U.S.C. § 6(b). We affirm-in-part. INVENTION This invention relates to detection of abnormal motion in a video stream. Claim 1, reproduced below, is representative of the claimed subject matter: 1. An apparatus for detection of abnormal activity in a video stream, the video stream having video frames, the apparatus comprising: [a] a system maintenance and setup module; [b] a module that extracts motion vectors, from each of the video frames, that represent an approximate common movement direction of a predetermined sub-part of each of said frames; [c] a system training module that creates at least one statistical model representing usual activity based on said motion vectors or on at least one motion feature generated from said motion vectors; and [d] a motion detection module that detects abnormal activity by determining according to the at least one statistical model, that a probability of [d1] at least one motion vector of said motion vectors associated with said predetermined sub-part or [d2] said at least one motion feature extracted from the at least one motion vector associated with said predetermined subpart, is below a predetermined threshold when compared to the said at least one statistical model, [e] wherein said predetermined sub-part is a macro-block. Appeal 2011-007346 Application 10/930,254 3 (Disputed limitations emphasized, elements lettered; paragraph returns added). REJECTIONS R1. Claims 1, 8, 11, 18, 19, 23-25, 32, 35, 42, 43, 46, 47, 49, and 50 stand rejected under 35 U.S.C. §103(a) as being unpatentable over the combined teachings and suggestions of US 6,028,626 ("Aviv"), US 4,737,847 ("Araki") and US Application Pub. 2003/0095602 A1 ("Divakaran"). R2. Claims 14, 15, 38, and 39 stand rejected under 35 U.S.C. §103(a) as being unpatentable over the combined teachings and suggestions of Aviv, Araki, Divakaran, and US 6,067,367 ("Nakajima"). R3. Claims 17 and 41 stand rejected under 35 U.S.C. §103(a) as being unpatentable over the combined teachings and suggestions of Aviv, Araki, Divakaran, and Nakajima, and further in view of John Y. A. Wang and Edward H. Adelson, Representing Moving Images with Layers, IEEE Trans. On Images Processing, Vol. 3, No. 5, 625-638 (Sept. 1994). GROUPING OF CLAIMS Based on Appellants' arguments, we decide the appeal of the rejection R1 of: (a) claims 1, 11, 18, 19, 25, 35, 42, 43, 49, and 50 on the basis of representative claim 1, (b) claims 23, 24, 46, and 47 on the basis of representative claim 23, and (c) claims 8 and 32 on the basis of representative claim 8. Appeal 2011-007346 Application 10/930,254 4 See 37 C.F.R. § 41.37(c)(1)(vii)(2004). 1 We address the rejections R2 and R3 separately, infra. ANALYSIS We disagree with Appellants' contentions regarding the Examiner's obviousness rejection R1. Regarding rejection R1, we adopt as our own: (1) the findings and reasons set forth by the Examiner in the action from which this appeal is taken, and (2) the reasons set forth by the Examiner in the Answer in response to arguments made in Appellants' Appeal Brief. (Ans. 12-25). However, we reverse rejections R2 and R3 for the reasons advanced by Appellants. We highlight and address specific findings and arguments below: R1. CLAIM 1 A. Regarding the claim 1 limitation [b] "a module that extracts motion vectors, from each of the video frames, that represent an approximate common movement direction of a predetermined sub-part of each of said frames (emphasis added)," Appellants contend, "Aviv does not teach 1 Appellants filed a Notice of Appeal on Aug. 13, 2010. The date of filing the Notice of Appeal determines which set of rules applies to an Ex Parte appeal. If a notice of appeal is filed prior to January 23, 2012, then the 2004 version of the Board Rules last published in the 2011 edition of Title 37 of the Code of Federal Regulations (37 C.F.R. § 41.1 et seq.) applies to the appeal. See also MPEP Rev. 8, July 2010. Appeal 2011-007346 Application 10/930,254 5 collecting a database of activity based on motion vectors or motion features of predetermined sub-parts, but rather collects characteristics of particular movements indicative of criminal intent (i.e., abnormal motions)." (App. Br. 7). Appellants' contentions are not persuasive. The Examiner finds, and we agree that Aviv's disclosure of "using motion vectors to track each moving object in a frame" would have taught or suggested the limitation "extracts motion vectors, from each of the video frames, that represent an approximate common movement direction . . . ." (Ans. 13, Aviv, col. 6, ll. 62-65). Appellants fail to address and rebut the Examiner's specific findings. (App. Br. 7-8). For these reasons, on this record, we are not persuaded the Examiner erred. B. Regarding the claim 1 limitation "[c] . . . at least one statistical model representing usual activity . . . ," Appellants contend, "Aviv teaches creating a database of movements indicative of criminal intent." (Emphasis added; App. Br. 8). Appellants' contention is not persuasive. We find Aviv's disclosure of statistical models including signature movement files for "normal," "neutral," and "friendly" activities would have taught or suggested the claimed "usual activity." (Ans. 5; Aviv col. 13, ll. 34-38; col. 15, ll. 18-22; col. 10, ll. 63-67). C. Regarding the combination of Aviv, Araki, and Divakaran in the obviousness rejection R1, Appellants contend: Appeal 2011-007346 Application 10/930,254 6 Aviv identifies motion of segments within the whole scene, while Araki splits the scene into pre-determined areas that depend on the scene having warning levels (doors, attic, etc.), and Divakaran discloses identifying motion in pre-determined macro blocks that do not depend on the scene. Thus, Aviv, Araki, and Divakaran are mutually exclusive and cannot be combined. (App. Br. 11-12). The Supreme Court guides “‘rejections on obviousness grounds cannot be sustained by mere conclusory statements; instead, there must be some articulated reasoning with some rational underpinning to support the legal conclusion of obviousness.”’ KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 418 (2007) (quoting In re Kahn, 441 F.3d 977, 988 (Fed. Cir. 2006)). Appellants' contentions are not persuasive. First, we find the Examiner did set forth articulated reasoning with some rational underpinning supporting the proffered combination of references. (Ans. 6-8). Appellants failed to address and rebut the Examiner's specific factual findings and ultimate legal conclusion of obviousness. (App. Br. 11-12). Specifically, Appellants' contention that "Aviv, Araki, and Divakaran are mutually exclusive and cannot be combined" is merely conclusory. (App. Br. 12). In particular, we find Appellants fail to present substantive arguments and supporting evidence rebutting the Examiner's reasoning to combine the references. (Id.). D. In the Reply Brief Appellants present new arguments regarding improper combination of references that were not raised in the Appeal Brief. (Reply Br. 4-6). However, Appellants’ new arguments in the Reply Brief are untimely. See Ex parte Borden, 93 USPQ2d 1473, 1474 (BPAI 2010) Appeal 2011-007346 Application 10/930,254 7 (Informative) (“[T]he reply brief [is not] an opportunity to make arguments that could have been made in the principal brief on appeal to rebut the Examiner's rejections, but were not”). See also Optivus Tech., Inc. v. Ion Beam Applications S.A., 469 F.3d 978, 989 (Fed. Cir. 2006) (“[A]n issue not raised by an appellant in its opening brief . . . is waived.”) (citation and internal quotation marks omitted). E. For these reasons, on this record, we are not persuaded the Examiner erred. Accordingly, we sustain the rejection of claim 1, and of claims 11, 18, 19, 25, 35, 42, 43, 49, and 50, which fall therewith. R1. CLAIM 23 Regarding the claim 23 limitation "a grading unit for grading the severity of abnormal motions detected by the at least two instances of the apparatus of claim 1," Appellants contend, "Aviv relates to detecting only a single unusual motion and does not teach two or more unusual activities, or grading of such." (App. Br. 13). Appellants' contention is not persuasive. The Examiner finds, and we agree: Claims 23 and 46 do not strictly require two or more separate or distinct unusual motions, only two or more instances of video streams, each of which may contain an unusual motion. It is respectfully submitted that the configuration of Aviv in which two streams record the same event at different angles, thereby registering two different motions that may have different severity levels, is within the broadest reasonable scope of the claims. Appeal 2011-007346 Application 10/930,254 8 (Ans. 20-21). For these reasons, on this record, we are not persuaded the Examiner erred. Accordingly, we sustain the rejection of claim 23, and of claims 24, 46, and 47, which fall therewith. R1. CLAIM 8 Regarding the dependent claim 8 limitation "wherein the at least one motion feature comprises any one of the following: sum of absolute value of motion over the sub-parts within the at least one video frame . . . " (emphasis added), Appellants' contend Aviv's "output of the differencing is a collection of differencing signals for each moved object, and not a numeric characteristic of the whole frame." (App. Br. 15). Appellants' contentions are not persuasive. As an initial matter of claim construction, independent claim 1, from which claim 8 depends, recites alternative language (“or”): “[c] a system training module that creates at least one statistical model representing usual activity based on said motion vectors or on at least one motion feature generated from said motion vectors.” (Claim 1; emphasis added). Thus, claim 1 [c] merely requires a teaching or suggestion of "said motion vectors or on at least one motion feature." (Emphasis added). In the review of claim 1 supra, we found the combination of references would have taught or suggested at least the recited "motion vectors." (Claim 1). Because dependent claim 8 does not further limit the "motion vectors" of claim 1, we sustain the rejection of claim 8 for the same reasons discussed above regarding claim 1. Second, we agree with the Examiner that Aviv's description of "[t]he resulting difference signal (outputted from the differencing sub-section 12) of each image indicates all the changes that have occurred from one frame Appeal 2011-007346 Application 10/930,254 9 to the next" (col. 6, ll. 56-58; emphasis added) would have taught or suggested the claimed"[M]otion over the sub-parts within the at least one video frame. . . ." (Claim 8; see also Ans. 22). For these reasons, on this record, we are not persuaded the Examiner erred. Accordingly, we sustain the rejection of claim 8 and of claim 32, which falls therewith. R2. CLAIMS 14, 15, 38, AND 39 Regarding the claim 14 limitation "wherein the at least one statistical model is represented as a one dimensional histogram representing the distribution of values of one of the at least one motion feature," and the commensurate language recited in claims 15, 38, and 39, the Examiner finds "in Nakajima 'each correlation peak in the histogram represents the leading end of a motion vector (col. 17: lines 57-66), the positions of the peaks inherently represent motion vector distribution.'" (Ans. 23). Appellants' contend: Nakajima teaches the usage of histograms for representing the intensities of correlation components of pixels. See for example Nakajima at col. 16 lines 59-16: "to obtain the histogram of the intensities of the correlation components of the respective pixels." Nakajima's discussion of histograms of mere correlation components does not teach or suggest histograms that represent distribution of motion vectors or features. Even if Nakajima teaches the deduction of motions from the peak of a histogram, this does not imply that the histogram represents value distributions of motion features. (App. Br. 16). We are persuaded by Appellants' contentions. We agree with Appellants that Nakajima's disclosure that the histograms represent a Appeal 2011-007346 Application 10/930,254 10 distribution of "intensities of the correlation components of the respective pixels" (Nakajima col. 16, ll. 59-60) would not have reasonably taught or suggested the claimed "one dimensional histogram representing the distribution of values of one of the at least one motion feature." (Emphasis added; Ans. 23-24). Specifically, the Examiner has not shown how Nakajima 's distribution of "intensities of the correlation components of the respective pixels" would have taught or suggested the claimed "least one motion feature." (Ans. 23-24). For essentially the same reasons advanced by Appellants, on this record, we are persuaded the Examiner erred. Accordingly, we reverse the rejection of claim 14, and of claims 15, 38, and 39, which recite commensurate limitations. R3. CLAIMS 17 AND 41 Regarding the claim 17 limitation "wherein the statistical model representing the distribution of an at least one motion feature is created using a k-means method," (emphasis added) and the commensurate language of claim 41 Appellants contend: Appellants submit that in Wang, the K-means algorithm is used for motion segmentation in a video sequence, i.e., for grouping together the similar motion of parts of the same object. Aviv uses segmentation as part of the motion classification and not as part of constructing the database. Thus, it would not be obvious for a person skilled in the art to combine Aviv and Wang by applying the K-means method used by Wang for classifying input motions, with constructing the statistical model, which is the preparatory stage as arguendo taught by Aviv. (App. Br. 17). Appeal 2011-007346 Application 10/930,254 11 We are persuaded by Appellants' contentions. The Examiner findings fail to show how the combination of Wang's and Aviv’s segmentation process for determining the motion vectors using k-means, which precedes creating a statistical model, would have taught or suggested creating the statistical model using a k-means method. (Ans. 24-25; App. Br. 17). For essentially the same reasons advanced by Appellants, on this record, we are persuaded the Examiner erred. Accordingly, we reverse the rejection of claim 17 and of claim 41, which recites commensurate limitations. DECISION We affirm the Examiner's rejection R1 of claims 1, 8, 11, 18, 19, 23-25, 32, 35, 42, 43, 46, 47, 49, and 50 under § 103. We reverse the Examiner's rejection R2 of claims 14, 15, 38, and 39 under § 103. We reverse the Examiner's rejection R3 of claims 17 and 41 under § 103. No time for taking any action connected with this appeal may be extended under 37 C.F.R. § 1.136(a)(1). See also 37 C.F.R. § 41.50(f). AFFIRMED-IN-PART kis Copy with citationCopy as parenthetical citation