CareView Communications, Inc.

Patent Trials and Appeals Board

Feb 3, 2022

2020005782 (P.T.A.B. Feb. 3, 2022)

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. 15/364,872 11/30/2016 Steven Gail Johnson 5024-20 9157 61834 7590 02/03/2022 Meister Seelig & Fein LLP 125 Park Avenue 7th Floor NEW YORK, NY 10017 EXAMINER HESS, MICHAEL J ART UNIT PAPER NUMBER 2481 NOTIFICATION DATE DELIVERY MODE 02/03/2022 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): patents@msf-law.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte STEVEN GAIL JOHNSON and DEREK DEL CARPIO Appeal 2020-005782 Application 15/364,872 Technology Center 2400 Before ELENI MANTIS MERCADER, JUSTIN BUSCH, and BETH Z. SHAW, Administrative Patent Judges. SHAW, Administrative Patent Judge. DECISION ON APPEAL STATEMENT OF THE CASE Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the Examiner’s decision to reject claims 1-6, 8-16, and 18-20. We have jurisdiction under 35 U.S.C. § 6(b). We AFFIRM. 1 We use the word Appellant to refer to “applicant” as defined in 37 C.F.R. § 1.42(a). Appellant identifies the real party in interest as CareView Communications, Inc. Appeal Br. 2. Appeal 2020-005782 Application 15/364,872 2 CLAIMED SUBJECT MATTER The claims are directed to systems and methods for predicting patient falls. Claim 1, reproduced below, is illustrative of the claimed subject matter: 1. A surveillance system for detecting a fall risk condition for a patient on a bed within a patient area, the system comprising: a surveillance camera configured to generate a plurality of frames showing a surveillance viewport of an area including the patient area; and a computer system comprising memory and logic circuitry configured to: identify a first set of frames from the plurality of frames; generate motion images for the first set of frames; determine features from the motion images, the features including a centroid area and a bed motion percentage, wherein the centroid area represents a count of motion pixels in a given one of the motion images and the bed motion percentage represents a ratio of motion pixels to total pixels within a virtual bed zone in the given one of the motion images, wherein the virtual bed zone is delineated by virtual bed rails defined at one or more sides of the bed; train a classifier using the extracted features by executing machine learning that labels one or more of the first set of frames as causing a patient fall alarm based on motion images that correspond to the one or more of the first set of frames including the bed motion percentage being less than a given ratio value of motion pixels to total pixels and the centroid area being greater than a given centroid area value; receive a second set of frames from the plurality of frames; Appeal 2020-005782 Application 15/364,872 3 detect, by using the classifier, that at least one frame of the second set of frames triggers an alarm associated with a fall risk event; and issue a fall alert based on the detection, the fall alert comprising one or both of a visual indication and an audible indication. REFERENCES The prior art relied upon by the Examiner is: Name Reference Date Chuang US 2012/0169842 Al July 5, 2012 Maslan US 2013/0083198 Al Apr. 4, 2013 Archibald US 2014/0368688 Al Dec. 18, 2014 Fleming US 2006/0279628 Al Dec. 14, 2006 Cherchi US 2016/0302658 Al Oct. 20, 2016 Gao US 2015/0178953 Al June 25, 2015 Haritaoglu US 2011/0122255 Al May 26, 2011 Cisco’s White Paper, titled “Virtual Patient Observation: Centralize Monitoring of High-Risk Patients with Video,” 2013 (“Cisco”). REJECTIONS Claims 1-5, 11-15 are rejected under 35 U.S.C. § 103 as being unpatentable over Cisco, Chuang, Maslan, Archibald, and Fleming. Claims 6 and 16 are rejected under 35 U.S.C. § 103 as being unpatentable over Cisco, Chuang, Maslan, Archibald, Fleming, and Cherchi. Claims 8 and 18 are rejected under 35 U.S.C. § 103 as being unpatentable over Cisco, Chuang, Maslan, Archibald, Fleming, and Gao. Claims 9, 10, 19, 20 are rejected under 35 U.S.C. § 103 as being unpatentable over Cisco, Chuang, Maslan, Archibald, Fleming, Gao, and Haritaoglu. Appeal 2020-005782 Application 15/364,872 4 OPINION We have reviewed the Examiner’s rejections in light of Appellant’s arguments that the Examiner has erred. On this record, we see no error in the Examiner’s reliance on the cited references for collectively teaching or suggesting the elements recited in the claims. We agree with and adopt as our own the Examiner’s findings and conclusions in the Final Rejection and Answer. See Final Act. 2-17; Ans. 14-28. Claim 1 Appellant directs us to the Specification to clarify the meaning of “centroid area.” The Specification, in paragraph 49, states: A second motion feature that may be detected is a ‘centroid area’ feature. In one embodiment, the centroid area feature is the count of all motion pixels in the image. Thus, the centroid area feature represents that total movement between frames. A small centroid area feature indicates little movement, while a large centroid area feature indicates substantial movement. In one embodiment, a number of pixels in a motion image (e.g., as illustrated in Figures 4 and 5) may be counted. Spec. ¶ 49. Appellant argues that the Examiner errs by equating a “centroid” in the prior art with the claimed “centroid area.” Appellant argues that the claimed “centroid area” may be used to measure movement between frames based on motion pixels, which is a functionality that a centroid cannot provide. Appellant argues that the “centroid area” provides an aggregation of movement that can indicate overall levels of activity within a motion image. Claim 1 recites “the centroid area represents a count of motion pixels in a given one of the motion images.” Giving claim 1 its broadest, reasonable construction, the “centroid area” requires a representation of a count of motion pixels in an image. Appeal 2020-005782 Application 15/364,872 5 We are not persuaded of error for the following reasons. Apart from referring to a paragraph in the Specification, Appellant provides insufficient evidence that the Specification or claims limit “centroid area” in a way that, under a broad but reasonable interpretation, is not encompassed by the teachings of the prior art references, as explained by the Examiner. The prior art (e.g., Chuang and Haritaoglu) detects activity, groups the activity using connected component analysis (CCA), and defines centroids of pixel blobs (regions) for tracking centroid (object) movement. See Ans. 17; Haritaoglu ¶ 90; Chuang ¶¶ 127-137. Moreover, we agree with the Examiner that when the cited prior art teaches a centroid, a “centroid area” is also taught or at least suggested. See id. at 18. Haritaoglu, for example, selects the most “significant motion energy regions” for future motion magnitude analysis on these selected regions. Haritaoglu ¶ 90 (emphasis added). In Haritaoglu, “[o]nly the regions with significant motion magnitude are selected and information regarding their 2D location, size, and motion magnitude and direction are stored in the perceptual video fingerprint unit.” Haritaoglu ¶ 90 (emphasis added). As the Examiner explains, and we agree, Haritaoglu’s “2D location (i.e., centroid of the segmented region)” teaches the centroid of the segmented region, and Haritaoglu’s “size (i.e., area of the segmented region)” teaches an area of the segmented region. Ans. 18. “Therefore, as evidenced in Haritaoglu, when the prior art teaches a centroid, an area or region around the centroid is also implicated.” Id. We also find unavailing Appellant’s arguments that the cited references do not teach the claimed “bed motion percentage.” As the Examiner explains, and we agree, Fleming teaches determining a percentage of motion in a region, which reasonably teaches or at least suggests Appeal 2020-005782 Application 15/364,872 6 determining a percentage as a ratio of motion pixels to total pixels. Ans. 20; Fleming ¶¶ 960-961. As the Examiner explains, a skilled artisan would have understood a ratio of active pixels to total pixels for a region of interest, expressed as a percentage, to be obvious in view of Chuang and Fleming. Id. Appellant does not persuasively rebut the Examiner’s mapping of Fleming’s determining of a percentage of motion in a region in paragraph 90 to the recited bed motion percentage. We also find unavailing Appellant’s arguments that the cited references do not teach the claimed “train a classifier using the extracted features by executing machine learning that labels one or more of the first set of frames as causing a patient fall alarm based on motion images that correspond to the one or more of the first set of frames including the bed motion percentage being less than a given ratio value of motion pixels to total pixels and the centroid area being greater than a given centroid area value.” As the Examiner explains, and we agree, Maslan teaches a classifier as being capable of automatically labeling the video frames. Ans. 22; Maslan ¶¶ 22, 38. Chuang teaches determining the size and motion profile of centroid areas using CCA, as well as comparing the size to a threshold size because Chuang discloses determining the largest object. Ans. 22; Chuang ¶ 137. Additionally, Fleming teaches, or at least suggests, determining a percentage of motion in a region with respect to total pixels. Ans. 22; Fleming ¶¶ 960-961. Thus, the combination of cited references teaches or suggests this disputed claim element. We find unavailing Appellant’s various arguments against the combination of references, for the reasons explained in the comprehensive Final Rejection and the Answer (see Ans. 23-27), which we agree with and adopt as our own. The Examiner’s proposed combination of the cited Appeal 2020-005782 Application 15/364,872 7 teachings of the prior art references is no more than a simple arrangement of old elements with each performing the same function it had been known to perform, yielding no more than one would expect from such an arrangement. KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 416 (2007). The ordinarily skilled artisan, being “a person of ordinary creativity, not an automaton,” would be able to fit the teachings of the cited references together like pieces of a puzzle to predictably result in a surveillance system for detecting a fall risk condition for a patient on a bed within a patient area. Id. at 420-21. Because Appellant has not demonstrated that the Examiner’s proffered combination would have been “uniquely challenging or difficult for one of ordinary skill in the art,” we agree with the Examiner that the proposed modification would have been within the purview of the ordinarily skilled artisan. Leapfrog Enters., Inc. v. Fisher-Price, Inc., 485 F.3d 1157, 1162 (Fed. Cir. 2007) (citing KSR, 550 U.S. at 418). Accordingly, we sustain the rejection of independent claim 1. We also sustain the rejections of claims 2-5 and 11-15, which were argued together with claim 1. We also sustain the Examiner’s obviousness rejections of claims 6, 8, 9, 16, 18, and 19. Despite nominally arguing these claims separately, Appellant reiterates similar arguments made in connection with claim 1, and alleges that the additional cited prior art fails to cure those purported deficiencies. We are not persuaded by these arguments for the reasons previously discussed. Appeal 2020-005782 Application 15/364,872 8 Dependent Claims 10 and 20 With respect to dependent claims 10 and 20, Appellant argues that Haritaoglu fails to teach or suggest “the computer system to determine an unconnected motion by calculating an amount of motion pixels in the area of the centroid that is unrelated to connected motion pixels within and near the virtual bed zone.” In particular, Appellant argues that Haritaoglu “arbitrarily” segments an image and does not distinguish unconnected pixels from connected motion pixels in a centroid. We find this argument unavailing because Haritaoglu teaches connected component analysis, where components are connected or sorted by motion similarity. Haritaoglu ¶ 90. Pixels with motions or locations that are not deemed similar enough to a defined group are not connected, and therefore, are considered to belong to a separate object. Id.; Ans. 28. Accordingly, we sustain the rejection of dependent claims 10 and 20. CONCLUSION We affirm the Examiner’s rejections. Appeal 2020-005782 Application 15/364,872 9 DECISION SUMMARY In summary: Claims Rejected 35 U.S.C. § Reference(s)/Basis Affirmed Reversed 1-5, 11-15 103 Cisco, Chuang, Maslan, Archibald, Fleming 1-5, 11-15 6, 16 103 Cisco, Chuang, Maslan, Archibald, Fleming, Cherchi 6, 16 8, 18 103 Cisco, Chuang, Maslan, Archibald, Fleming, Gao 8, 18 9, 10, 19, 20 103 Cisco, Chuang, Maslan, Archibald, Fleming, Gao, Haritaoglu 9, 10, 19, 20 Overall Outcome 1-6, 8-16, 18-20 TIME PERIOD FOR RESPONSE No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R. § 1.136(a)(1)(iv). AFFIRMED