Target Tracking Or Detecting Patents (Class 382/103)
  • Patent number: 9842398
    Abstract: In accordance with the teachings described herein, systems and methods are provided for generating images for use in systems, e.g., imaging systems. The method includes receiving at least a first set of images, providing a first registration, providing a display, and displaying a first image on said display. Further, the method includes providing a user interface, providing a second registration, and displaying a second image in said user interface. Further, the systems include an image database, a display, and a registration engine. The registration engine includes software instructions stored in at least one memory device and executable by one or more processors.
    Type: Grant
    Filed: April 10, 2015
    Date of Patent: December 12, 2017
    Assignee: MIM SOFTWARE INC.
    Inventors: Jerimy Brockway, Jonathan William Piper
  • Patent number: 9842254
    Abstract: The systems and/or processes described herein may calibrate an inertial measurement unit (IMU) of an electronic device in part by using images captured by one or more cameras of the electronic device. In this regard, an IMU of an electronic device may comprise a gyroscope, an accelerometer, a magnetometer, or any other type of motion sensor or rotational sensor.
    Type: Grant
    Filed: September 28, 2015
    Date of Patent: December 12, 2017
    Assignee: Amazon Technologies, Inc.
    Inventors: Ilya Vladimirovich Brailovskiy, Ilia Vitsnudel
  • Patent number: 9841490
    Abstract: A system and method are provided for detecting direction of movement. The system includes at least two radio frequency identification (RFID) readers arranged in different locations. The RFID readers transmit respective location signals from their locations and receive corresponding response signals from a portable electronic device (PED) when the PED is within range to receive the corresponding location signals, respectively. The system includes a controller configured to determine whether the individual response signals received by the RFID readers respectively satisfy a predetermined condition at a first time and a second time subsequent to the first time. The controller is also configured to determine a direction of movement of the portable electronic device relative to the locations of the RFID readers during the first and second times based on whether the response signals respectively satisfy the predetermined condition at the first and second times.
    Type: Grant
    Filed: January 17, 2017
    Date of Patent: December 12, 2017
    Assignee: BOOZ ALLEN HAMILTON INC.
    Inventors: John C. Swartz, Anthony Hefner, Charles W. Richards, IV, Gary Jason Myers, Matthias Welsh
  • Patent number: 9842257
    Abstract: A pill identification system identifies a pill type for a pharmaceutical composition from images of the pharmaceutical composition. The system extracts features from images taken of the pill. The features extracted from the pill image include color, size, shape, and surface features of the pill. In particular, the features include rotation-independent surface features of the pill that enable the pill to be identified from a variety of orientations when the images are taken. The feature vectors are applied to a classifier that determines a pill identification for each image. The pill identification for each image is scored to determine identification for the pharmaceutical composition.
    Type: Grant
    Filed: January 23, 2013
    Date of Patent: December 12, 2017
    Assignee: PerceptiMed, Inc.
    Inventors: Eugene Gershtein, Alan Jeffrey Jacobs, Alexander Gebala
  • Patent number: 9842399
    Abstract: A device includes a memory configured to store map point information including a first map point group indicating a three-dimensional position of an object measured by a distance sensor and a second map point group indicating a three-dimensional position of the object determined based on captured images and a processor configured to compare a first projection point group of the first map point group with a feature point group extracted from a new captured image, create pairs of a feature point in the feature point group and a first projection point that is similar to the feature point, when the number of the pairs is less than or equal to a threshold, compare a second projection point group of the second map point group with the feature point group, create other pairs of the feature point and a second projection point, and estimate a position and attitude of a camera.
    Type: Grant
    Filed: April 26, 2016
    Date of Patent: December 12, 2017
    Assignee: FUJITSU LIMITED
    Inventor: Nobuyasu Yamaguchi
  • Patent number: 9836853
    Abstract: A three-dimensional convolutional neural network may include a preliminary layer group, one or more intermediate layer groups, a final layer group, and/or other layers/layer groups. The preliminary layer group may include an input layer, a preliminary three-dimensional padding layer, a preliminary three-dimensional convolution layer, a preliminary activation layer, a preliminary normalization layer, and a preliminary downsampling layer. One or more intermediate layer groups may include an intermediate three-dimensional squeeze layer, a first intermediate normalization layer, an intermediate three-dimensional padding layer, a first intermediate three-dimensional expand layer, a second intermediate three-dimensional expand layer, an intermediate concatenation layer, a second intermediate normalization layer, an intermediate activation layer, and an intermediate combination layer.
    Type: Grant
    Filed: September 6, 2016
    Date of Patent: December 5, 2017
    Assignee: GoPro, Inc.
    Inventor: Tom Médioni
  • Patent number: 9837051
    Abstract: An electronic device and a method generate a first model and a second model when the images presented by the electronic device are viewed by a user located at a reference location. The electronic device obtains an image of the user captured by a camera of the electronic device when the user views the images presented by the electronic device. The electronic device generates a third model according to the image of the user. The electronic device adjusts the images presented by the electronic device when the third model does not match the first model.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: December 5, 2017
    Assignees: Fu Tai Hua Industry (Shenzhen) Co., Ltd., HON HAI PRECISION INDUSTRY CO., LTD.
    Inventors: Jun Chen, Cheng-Ching Chien, Po-Hua Lin, Jun-Jin Wei
  • Patent number: 9838657
    Abstract: A system, method and program product that provides projection enhancement. A system is described that includes: a digital projector for generating an image projection onto a surface; a spatial sensor configured to sense and locate a blocking object in a light field associated with the digital projector; a masking system that masks a portion of the image projection corresponding to the blocking object; and an enhancement system that generates an enhancement projection onto the blocking object.
    Type: Grant
    Filed: January 7, 2016
    Date of Patent: December 5, 2017
    Assignee: International Business Machines Coporation
    Inventors: Michael Sean Brown, Stefan Harrer, Christopher J. Pavlovski, Laurence J. Plant
  • Patent number: 9838635
    Abstract: Techniques describe computing computer vision (CV) features based on sensor readings from a sensor and detecting macro-features based on the CV features. The sensor may include a sensor element array that includes a plurality of sensor elements. The sensor may also include in-pixel circuitry coupled to the sensor elements, peripheral circuitry and/or a dedicated microprocessor coupled to the sensor element array. The in-pixel circuitry, the peripheral circuitry or the dedicated microprocessor may include computation structures configured to perform analog or digital operations representative of a multi-pixel computation for a sensor element (or block of sensor elements), based on sensor readings generated by neighboring sensor elements in proximity to the sensor element, and to generate CV features. The dedicated microprocessor may process the CV features and detect macro-features.
    Type: Grant
    Filed: September 23, 2015
    Date of Patent: December 5, 2017
    Assignee: QUALCOMM Incorporated
    Inventors: Evgeni Petrovich Gousev, Alok Govil, Soo Youn Kim, Nelson Rasquinha, Venkat Rangan
  • Patent number: 9836642
    Abstract: Approaches are described which enable a computing device (e.g., mobile phone, tablet computer) to utilize one or more facial recognition techniques to control access to the device and to detect when artificial representations of a user, such as a picture or photograph, are being used in an attempt to gain access to the device. Evidence indicative of artificial representations may include lack of changes in facial skin color between multiple images captured by a camera, ability to track one or more features of the human face while the camera is rotated or moved, presence of secular reflections caused by an illumination device, absence of shadows in the image, and others.
    Type: Grant
    Filed: January 4, 2016
    Date of Patent: December 5, 2017
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventor: Sharadh Ramaswamy
  • Patent number: 9838595
    Abstract: The present invention belongs to the technical field of video recording and provides a video generating method and apparatus of a video generating system, the video generating system comprises a system target orientating camera, a target tracking camera and a panorama camera, the method comprises: when it is judged that a target object included in the image collected by the target tracking camera is a person, and the person lies within a scope of a lens of the target tracking camera, switching the target tracking camera such that it serves as a video generating source and generating a video according to images collected by the target tracking camera; when it is judged that the target object included in an image collected by the target tracking camera is a person, and the person lies out of the scope of the lens of the target tracking camera, or it is judged that the target object included in an image collected by the target tracking camera is not a person, switching the panorama camera such that it serves as
    Type: Grant
    Filed: November 10, 2014
    Date of Patent: December 5, 2017
    Assignee: SZ REACH TECH CO., LTD.
    Inventors: Xin Qu, Hai Liao, Xinglei Sun, Jie Yuan, Chong Xu, Zhen Qian
  • Patent number: 9830715
    Abstract: The specification relates to determining either or both of the pose of a camera with respect to a real object or a three dimensional structure of the real object. In some of the described embodiments, a captured image including the real object is analyzed with respect to a reference image that also includes the real object. A parameter set is estimated by using a homography between the reference image and the captured image. An update to the parameter set is made by using an iterative minimization process that includes comparing a first set of pixels in the reference image with a computed set of pixels in the captured image, where the computed set of pixels used for comparison varies in different iterations of the iterative minimization process.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: November 28, 2017
    Assignee: Apple Inc.
    Inventors: Selim Benhimane, Sebastian Lieberknecht
  • Patent number: 9829995
    Abstract: The present disclosure is directed to a method for managing a location of a cursor on a display. The method may include the step of receiving an input from a user. The method may also include the step of detecting a gaze of the user within the display. The method may also include the step of displaying the cursor on the display within the gaze of the user.
    Type: Grant
    Filed: April 28, 2014
    Date of Patent: November 28, 2017
    Assignee: Rockwell Collins, Inc.
    Inventors: Colin D. Reed, Bryan C. Schultz, Timothy J. Wittkop, David L. Leedom
  • Patent number: 9830512
    Abstract: A method for tracking a gaze includes determining a position of a first center point of a cornea by using at least two lighting reflection points detected from an eyeball area of a first face image of a user and calculating a first vector connecting at least two first image feature points detected from the first face image to the position of the first center point of the cornea. A position of a second center point of the cornea is determined using the first vector and a position of the feature point detected from the second face image. A second vector is determined using the position of the second center point of the cornea and a position of a center point of a pupil. The gaze of the user is tracked by using the second vector. An apparatus for tracking a gaze is also disclosed.
    Type: Grant
    Filed: December 11, 2014
    Date of Patent: November 28, 2017
    Assignee: HYUNDAI MOTOR COMPANY
    Inventors: Jae Ho Lee, Seon A Kim
  • Patent number: 9830728
    Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.
    Type: Grant
    Filed: December 23, 2014
    Date of Patent: November 28, 2017
    Assignee: Intel Corporation
    Inventors: Yikai Fang, Yangzhou Du, Qiang Eric Li, Xiaofeng Tong, Wenlong Li, Minje Park, Myung-Ho Ju, Jihyeon Kate Yi, Tae-Hoon Pete Kim
  • Patent number: 9826276
    Abstract: A method and computing device are provided for performing virtual camera functions during playback of media content. In the method, the computing device selects a region of interest (RoI) during a playback of media content, and represents the RoI as an ensemble of disparate hypotheses. Then the computing device identifies the RoI in a frame sequence sampled according to the hypotheses, performs a virtual camera action on the identified RoI, and plays the RoI with a virtual camera.
    Type: Grant
    Filed: January 15, 2014
    Date of Patent: November 21, 2017
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ravindra Guntur, Ravikiran Patil, Mahesh Krishnananda Prabhu
  • Patent number: 9824565
    Abstract: A smoke detector system functionally integrates several systems into a common housing, including smoke/carbon monoxide detection, motion sensing, camera, lighting and audio systems.
    Type: Grant
    Filed: September 14, 2015
    Date of Patent: November 21, 2017
    Inventor: Ricky Patel
  • Patent number: 9824260
    Abstract: Embodiments described herein can be used to detect holes in a subset of pixels of a depth image that has been specified as corresponding to a user, and to fill such detected holes. Additionally, embodiments described herein can be used to produce a low resolution version of a subset of pixels that has been specified as corresponding to a user, so that when an image including a representation of the user is displayed, the image respects the shape of the user, yet is not a mirror image of the user. Further, embodiments described herein can be used to identify pixels, of a subset of pixels specified as corresponding to the user, that likely correspond to a floor supporting the user. This enables the removal of the pixels, identified as likely corresponding to the floor, from the subset of pixels specified as corresponding to the user.
    Type: Grant
    Filed: July 7, 2015
    Date of Patent: November 21, 2017
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Anis Ahmad, Jonathan Hoof, Daniel Kennett
  • Patent number: 9824281
    Abstract: A system and method are provided for tracking objects in a scene from a sequence of images captured by an imaging device. The method includes processing the sequence of images to generate sequential images at a plurality of hierarchical levels to generate a set of regions of interest; and, at each of the hierarchical levels: examining pairs of sequential images to link pixels into short tracklets; and grouping short tracklets that indicate similar motion patterns to generate representative tracklets. The representative tracklets are grouped to generate a tracking result for at least one object.
    Type: Grant
    Filed: May 15, 2015
    Date of Patent: November 21, 2017
    Assignee: Sportlogiq Inc.
    Inventors: Mehrsan Javan Roshtkhari, Martin D. Levine
  • Patent number: 9819911
    Abstract: A system is provided that includes a security system that protects a secured geographic area including at least a building, a wireless helicopter drone, a camera carried by the drone and a processor of the security system that controls a geographic location of the drone based upon threats detected within the secured area and that records video via the camera from the controlled location.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: November 14, 2017
    Assignee: HONEYWELL INTERNATIONAL INC.
    Inventors: Vijaya Krishna K V, Bharat Balaso Khot, Eric Oh, Bikram Swain
  • Patent number: 9814909
    Abstract: During a focused-ultrasound or other non-invasive treatment procedure, the motion of the treatment target or other object(s) of interest can be tracked in real time based on the comparison of treatment images against a reference library of images that have been acquired prior to treatment for the anticipated range of motion and have been processed to identify the location of the target or other object(s) therein.
    Type: Grant
    Filed: February 6, 2013
    Date of Patent: November 14, 2017
    Assignee: INSIGHTEC, LTD.
    Inventors: Yoav Levy, Yoav Medan, Kobi Vortman
  • Patent number: 9819872
    Abstract: A processing apparatus includes an acquisition unit that acquires a captured image obtained by capturing, by an image capturing unit, a target object to which a projection unit has emitted pattern light. A derivation unit derives a distance from the image capturing unit to the target object by using the captured image. An adjustment unit adjusts, in accordance with the derived distance, at least one of a first parameter for controlling brightness of the pattern light emitted from the projection unit, and a second parameter for controlling an exposure amount of the image capturing unit.
    Type: Grant
    Filed: October 21, 2014
    Date of Patent: November 14, 2017
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroshi Yoshikawa, Shinji Uchiyama
  • Patent number: 9816863
    Abstract: Techniques are provided for an image processing device to receive image information comprising image data for a plurality of mid-wave infrared region (MWIR) channels, where the image data is obtained during a first imaging period and during a second imaging period temporally different from the first imaging period. A plurality of sets of atmospheric wind vectors are calculated using differences between image data obtained during the first imaging period and the image data obtained during the second imaging period for corresponding sets of MWIR channels. An altitude is assigned to the plurality of atmospheric wind vectors in each set based on a brightness temperature of each wind vector and a pre-computed atmospheric temperature profile to generate a set of two-dimensional wind fields comprising one two-dimensional wind field for each set of MWIR channels.
    Type: Grant
    Filed: September 26, 2014
    Date of Patent: November 14, 2017
    Assignee: Harris Corporation
    Inventors: Christopher E Lietzke, Ronald J Glumb
  • Patent number: 9818038
    Abstract: An image recognition apparatus includes a memory, an interface and a processor. The memory stores identification information obtained from code information attached to the objects and image information on the objects used for object recognition, the storage storing the identification information and the image information for each of objects to be recognized. The processor which controls to: extract a target object region including an object therein from a photographed image; extract code information in the target object region and recognize the identification information based on extracted code information; and recognize the object based on an image of the target object region and image information on each object, if the processor fails to recognize the object based on the code information.
    Type: Grant
    Filed: January 6, 2016
    Date of Patent: November 14, 2017
    Assignee: TOSHIBA TEC KABUSHIKI KAISHA
    Inventor: Masaaki Yasunaga
  • Patent number: 9818022
    Abstract: At least one example embodiment discloses a method of detecting an object in an image. The method includes receiving an image, generating first images for performing a first classification operation based on the received image, reviewing first-image features of the first images using a first feature extraction method with first-type features, first classifying at least some of the first images as second images, the classified first images having first-image features matching the first-type features, reviewing second-image features of the second images using a second feature extraction method with second-type features, second classifying at least some of the second images as third images, the classified second images having second-image features matching the second-type features and detecting an object in the received image based on results of the first and second classifying.
    Type: Grant
    Filed: December 10, 2015
    Date of Patent: November 14, 2017
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Irina Kim, Woong-hee Lee, Byeoung-su Kim
  • Patent number: 9811760
    Abstract: An image processing system includes a processing device having a memory device for storing computer-executable instructions. The processing device is programmed to define a first descriptor in a first image, generate a mask from the first descriptor, and define a second descriptor in a second image. The processing device is further programmed to compare the first descriptor to the second descriptor to define a first error vector, determine a second error vector by applying a mask, and compute the total error of the second error vector to determine an error between the first descriptor and the second descriptor.
    Type: Grant
    Filed: July 31, 2015
    Date of Patent: November 7, 2017
    Assignees: FORD GLOBAL TECHNOLOGIES, LLC, THE REGENTS OF THE UNIVERSITY OF MICHIGAN
    Inventors: Andrew Richardson, Edwin Olson
  • Patent number: 9810709
    Abstract: Systems and methods for monitoring athletic performances include determining “flight time,” e.g., the amount of time both feet are off the ground, and optionally “flight time” resulting from different types of activities, such as jogging, running, sprinting, jumping, etc. “Flight time” may help a player or coach better understand the effort the athlete is putting out, compare efforts of two or more players, gauge the athlete's performance change over time, and/or identify conditioning needs and/or areas for improvement. Such systems and methods also may generate and display various athletic performance metrics, such as: instantaneous flight time; average flight time; cumulative flight time during an athletic performance or other time period; instantaneous jump height; average jump height; cumulative jump height during an athletic performance or other time period; and comparisons of any flight time and/or jump height metric(s) of one player against another player and/or against himself/herself; etc.
    Type: Grant
    Filed: May 28, 2015
    Date of Patent: November 7, 2017
    Assignee: Nike, Inc.
    Inventors: Santoshkumar Balakrishnan, Robert M. Bruce, Justin Fraga, Paul James Francis
  • Patent number: 9811718
    Abstract: Disclosed are a method and an apparatus for face verification. The apparatus comprises a feature extracting unit configured to extract HIFs (Hidden Identity Features) for different regions of faces by using differently trained ConvNets, wherein last hidden layer neuron activations of said ConvNets are considered as the HIFs. The apparatus further comprises a verification unit configured to concatenate the extracted HIFs of each of the faces to form a feature vector, and then compare two of the formed feature vectors to determine if they are from the same identity or not.
    Type: Grant
    Filed: April 11, 2014
    Date of Patent: November 7, 2017
    Assignee: Beijing Sensetime Technology Development CO., LTD
    Inventors: Yi Sun, Xiaogang Wang, Xiaoou Tang
  • Patent number: 9813619
    Abstract: An apparatus for correcting image distortion of a camera in a vehicle includes: a camera mounted in the vehicle; a camera characteristic extractor configured to extract camera characteristic parameters of the camera based on a preset mathematical model; a tilt angle calculator configured to calculate tilt angles of a virtual camera corresponding to the camera in each photographing region using the camera characteristic parameters; a yaw angle calculator configured to calculate yaw angles of the virtual camera in each photographing region; an image corrector configured to view-transform a photographed image photographed by the camera by adjusting angles of the virtual camera based on a correction model in order to secure a view region of the photographed image and create a corrected image depending on the view-transform; and a display configured to display the corrected image output from the image corrector.
    Type: Grant
    Filed: December 9, 2014
    Date of Patent: November 7, 2017
    Assignee: Hyundai Motor Company
    Inventors: Jun Sik An, Joong Ryoul Lee, Kap Je Sung, Eu Gene Chang
  • Patent number: 9813698
    Abstract: There is provided an image processing device including an analysis unit configured to analyze contrast according to a spatial frequency of an input image, a parallax transition information acquisition unit configured to acquire a relation of a crosstalk aggravation amount and a parallax transition corresponding to the contrast according to the spatial frequency of the input image with reference to a database in which the relation of the crosstalk aggravation amount and the parallax transition is stored in association with contrast according to spatial frequencies of various images, and a parallax computation unit configured to compute parallax corresponding to a predetermined threshold value set for the crosstalk aggravation amount in the acquired relation of the crosstalk aggravation amount and the parallax transition.
    Type: Grant
    Filed: October 30, 2014
    Date of Patent: November 7, 2017
    Assignee: Sony Corporation
    Inventors: Yasuhide Hyodo, Keita Ishikawa
  • Patent number: 9813601
    Abstract: Imaging systems and methods for imaging of scenes in apparent motion are described. A multi-axis positioning mechanism is operable to move an area imaging device along a tracking axis. A control module directs the multi-axis positioning mechanism to set the tracking axis to be substantially parallel with the apparent motion, and directs the multi-axis positioning mechanism to move the area imaging device in one or more cycles such that the area imaging device moves, in each of the one or more cycles, forward along the tracking axis at a tracking speed that compensates for the apparent motion. The control module directs the area imaging device to take at least one exposure during each of the one or more cycles to generate one or more exposures. An imaging module forms an image of the scene based on the one or more exposures.
    Type: Grant
    Filed: May 5, 2015
    Date of Patent: November 7, 2017
    Assignee: Urugus S.A.
    Inventors: Gerado Gabriel Richarte, Emiliano Kargieman, Juan Manuel Vuletich
  • Patent number: 9811911
    Abstract: A method for generating virtual reality (VR) content includes obtaining source information from original media content. retrieving characteristic information stored in a first memory based on the obtained source information wherein the retrieved characteristic information related to the original media content, generating the VR content by combining the retrieved characteristics information and the obtained source information, wherein at least one feature of the retrieved characteristic information is mapped to a corresponding at least one feature of the obtained source information, and outputting the generated VR content and the original media content to be reproduced to a viewer.
    Type: Grant
    Filed: December 29, 2014
    Date of Patent: November 7, 2017
    Assignee: NBCUniversal Media, LLC
    Inventor: Thomas Bause Mason
  • Patent number: 9813708
    Abstract: According to one to one exemplary embodiment, the disclosure provides a method of coding prediction for screen video. The method classifies a plurality of coding blocks into a plurality of block types by using a classifier; and uses a computing device to filter at least one candidate block from the plurality of coding blocks, according to the plurality of block types of the plurality of coding blocks, and compute a first candidate motion vector set of a type-based motion merge mode and a second candidate motion vector set of a type-based advanced motion vector prediction mode, wherein each of the at least one candidate block has a block-type different from that of a current coding block.
    Type: Grant
    Filed: April 17, 2014
    Date of Patent: November 7, 2017
    Assignee: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
    Inventors: Chun-Lung Lin, Pei-Hsuan Tsai
  • Patent number: 9811755
    Abstract: First imaging means 60 creates a state image by capturing a state occurring in a first range. Second imaging means 70 creates a monitoring target image by capturing a monitoring target present in a second range. Specific state detection means 81 detects a specific state from the state image. Monitoring target analysis means 82 analyzes a status of a monitoring target, using the state image from which the specific state is detected. Monitoring target feature extraction means 85 extracts, from the monitoring target image, a feature used for specifying the monitoring target, based on the status of the monitoring target.
    Type: Grant
    Filed: February 25, 2014
    Date of Patent: November 7, 2017
    Assignee: NEC Corporation
    Inventor: Hiroyoshi Miyano
  • Patent number: 9813907
    Abstract: Systems and techniques for user authentication are described. A portable electronic device can include an imaging sensor and a motion sensor. Multiple images of a face of a user can be acquired by using an imaging sensor. Motion information can be obtained by using a motion sensor. Next, a first motion vector can be determined based on the multiple images, and a second motion vector can be determined based on the motion information. The user can then be authenticated based on (1) determining a similarity measure between the first motion vector and the second motion vector, and (2) performing facial recognition on at least one of the multiple images. Note that the similarity measure can be used to detect a virtual-camera attack. Specifically, authentication can fail if the similarity measure is less than a threshold.
    Type: Grant
    Filed: June 29, 2016
    Date of Patent: November 7, 2017
    Assignee: The Regents of the University of California
    Inventors: Shaxun Chen, Amit Pande, Prasant Mohapatra
  • Patent number: 9811744
    Abstract: A system and method for detecting a stop line on a roadway. The system and method a front view camera that generates images of the roadway. The system and method also include a controller that receives the images generated from the front view camera, including a bird's eye view image, said controller further programmed to provide a composite image that includes an original bird's eye view image and a rotated bird's eye view image. The controller is also programmed to use the composite image to determine if a stop line is present on the roadway.
    Type: Grant
    Filed: July 20, 2015
    Date of Patent: November 7, 2017
    Assignee: GM Global Technology Operations LLC
    Inventors: Wende Zhang, Zhencheng Hu
  • Patent number: 9813731
    Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.
    Type: Grant
    Filed: August 6, 2014
    Date of Patent: November 7, 2017
    Assignee: STMICROELECTONICS INTERNATIONAL N.V.
    Inventors: Santanu Chaudhury, Mona Mathur, Aditya Khandelia, Subarna Tripathi, Brejesh Lall, Sumantra Dutta Roy, Saurabh Gorecha
  • Patent number: 9801569
    Abstract: This method for detecting activity (A) of a physical system carrying a motion sensor comprises the following steps: extracting (100) a sequence (M) of measurements provided by the motion sensor; deducing (102) therefrom an observation sequence (O) calculated on the basis of the measurement sequence (M); determining (104) the activity (A) of the physical system in the form of a sequence of states corresponding to the observation sequence, using a statistical model of components of the observation sequence in view of a plurality of possible predetermined states of the physical system. At least one component of the observation sequence (O) is calculated on the basis of a reference value ({circumflex over (?)}) of a vector representing a reference axis.
    Type: Grant
    Filed: October 19, 2012
    Date of Patent: October 31, 2017
    Assignees: Commissariat à l'énergie atomique et aux énergies alternatives, MOVEA
    Inventor: Pierre Jallon
  • Patent number: 9807310
    Abstract: A field display system is provided which can intelligibly present to a user a range in which a camera can capture an image of an entire target to be monitored or a certain part or more of the target to be monitored. A projecting unit 5 projects a position in an image captured by a camera, on a plurality of monitoring domains obtained by moving, in parallel, a region to be monitored which defines a range to be checked for an image capturing situation of the camera, the monitoring domain being determined based on a height of a target to be monitored, an image of which is captured by the camera, and specifies fields of the plurality of monitoring domains as a range an image of which the camera can capture without being blocked by an obstacle. An integrating unit 6 integrates the fields in the monitoring domains. The display control unit 7 causes the display apparatus to display an integration result of the fields.
    Type: Grant
    Filed: November 29, 2013
    Date of Patent: October 31, 2017
    Assignee: NEC Corporation
    Inventor: Hiroo Ikeda
  • Patent number: 9805567
    Abstract: In one embodiment of the present invention, a video camera selectively streams to a remote server. Still images or short video events are intermittently transmitted when there is no significant motion detected. When significant motion is detected, video is streamed to the remote server. The images and video can be higher resolution than the bandwidth used, by locally buffering the images and video, and transmitting it at a lower frame rate that extends to when there is no live streaming. This provides a time-delayed stream, but with more resolution at lower bandwidth.
    Type: Grant
    Filed: September 14, 2015
    Date of Patent: October 31, 2017
    Assignee: Logitech Europe S.A.
    Inventors: Vincent Borel, Aaron Standridge, Fabian Nater, Helmut Grabner
  • Patent number: 9805267
    Abstract: A system for processing a video signal into a processed video signal includes a video codec configured to generate a processed video signal based on the image sequence. A photo generation module is configured to recognize an object of interest in the image sequence and generate photo data from a selected image in the image sequence that includes the object of interest.
    Type: Grant
    Filed: April 2, 2015
    Date of Patent: October 31, 2017
    Assignee: ViXS Systems, Inc.
    Inventors: Indra Laksono, Sally Jean Daub, John Pomeroy, Xu Gang Zhao
  • Patent number: 9805260
    Abstract: There is provided a vehicle safety system including a sensing unit, a processing unit, a control unit and a display unit. The sensing unit is configured to capture an image frame containing an eyeball image from a predetermined distance. The processing unit is configured to calculate a pupil position of the eyeball image in the image frame and generate a drive signal corresponding to the pupil position. The control unit is configured to trigger a vehicle device associated with the pupil position according to the drive signal. The display unit is configured to show information of the vehicle device.
    Type: Grant
    Filed: April 13, 2015
    Date of Patent: October 31, 2017
    Assignee: PixArt Imaging Inc.
    Inventors: Chun-Wei Chen, Shih-Wei Kuo
  • Patent number: 9804771
    Abstract: An electronic device with a touch-sensitive surface and a device motion sensor detects a predefined gesture on the touch-sensitive surface. The predefined gesture has one or more gesture components. The device detects a predefined movement of the electronic device with the device motion sensor. The predefined movement has one or more movement components. In response to detecting the predefined gesture and the predefined movement, the device, in accordance with a determination that the one or more gesture components and the one or more movement components satisfy predefined concurrency criteria, performs a predefined operation that is associated with concurrent detection of the predefined gesture and the predefined movement, and in accordance with a determination that the one or more gesture components and the one or more movement components do not satisfy the predefined concurrency criteria, foregoes performing the predefined operation.
    Type: Grant
    Filed: March 31, 2011
    Date of Patent: October 31, 2017
    Assignee: Apple Inc.
    Inventors: Charles J. Migos, Jay Christopher Capela, Markus Hagele, Diego Bauducco
  • Patent number: 9805276
    Abstract: In an example embodiment, a computer-implemented method is disclosed that generates a spectral signature describing one or more dynamic objects and a scene layout of a current road scene; identifies, from among one or more scene clusters included in a familiarity graph associated with a user, a road scene cluster corresponding to the current road scene; determine a position of the spectral signature relative to other spectral signatures comprising the identified road scene cluster; and generates a familiarity index estimating familiarity of the user with the current road scene based on the position of the spectral signature. The method can further include determining an assistance level based on the familiarity index of the user; and providing one or more of an auditory instruction, a visual instruction, and a tactile instruction to the user via one or more output devices of a vehicle at the determined assistance level.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: October 31, 2017
    Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
    Inventors: Preeti J. Pillai, Veeraganesh Yalla, Rahul Ravi Parundekar, Kentaro Oguchi
  • Patent number: 9805293
    Abstract: A method is provided for recognition of a sky portion, a vertical object portion and a ground portion in an image. The image into a plurality of pixel sets by the electronic system. Expected values of each pixel sets with a sky distribution function, a vertical object distribution function and a ground distribution function by the electronic system are calculated and compared for each pixel set for determine each pixel set belonging to one of the sky portion, the vertical object portion or the ground portion.
    Type: Grant
    Filed: April 13, 2015
    Date of Patent: October 31, 2017
    Assignee: NANJING YUANJUE INFORMATION AND TECHNOLOGY
    Inventors: Liming Zheng, Bingbing Cui
  • Patent number: 9804000
    Abstract: Disclosure is related to an optical sensor array apparatus. According to one embodiment of the invention, multiple sensor pixels are arranged as an array and forming a sensor array. Every comparator circuit is connected to one sensor pixel so as to calculate its energy state. A light source such as laser is installed in the apparatus. A control circuit is provided to recognize the sensor pixels' energy states for determining the spatial interference difference made by the reflected ray. The sensor array apparatus may be adapted to various surfaces since the light intensity and exposure time is able to be modulated as a compensation mechanism.
    Type: Grant
    Filed: September 25, 2013
    Date of Patent: October 31, 2017
    Inventors: Yun-Shan Chang, Da Wei Lin
  • Patent number: 9805301
    Abstract: Described is a system for dynamic background estimation which utilizes Particle Swarm Optimization (PSO). The present invention comprises a system, method, and computer program product for accurate estimation of a background mask corresponding to a dynamically changing scene. The system is configured to construct a background template model of a scene, and then capture an image of a current view of the scene with a camera. Thereafter, the system generates an image-based template matching cost function as an optimization problem, where the objective is to identify and fit a corresponding subregion of the background template model to the current camera view. The cost function is optimized using a PSO search algorithm. Finally, the system is configured to generate the corresponding subregion of the background template model for display. The inherent efficiency of PSO makes this system conducive for use in applications requiring real-time background estimation.
    Type: Grant
    Filed: August 20, 2009
    Date of Patent: October 31, 2017
    Assignee: HRL Laboratories, LLC
    Inventors: Yuri Owechko, Swarup Medasani, Payam Saisan
  • Patent number: 9798322
    Abstract: Methods and systems are described for new paradigms for user interaction with an unmanned aerial vehicle (referred to as a flying digital assistant or FDA) using a portable multifunction device (PMD) such as smart phone. In some embodiments, a user may control image capture from an FDA by adjusting the position and orientation of a PMD. In other embodiments, a user may input a touch gesture via a touch display of a PMD that corresponds with a flight path to be autonomously flown by the FDA.
    Type: Grant
    Filed: April 16, 2015
    Date of Patent: October 24, 2017
    Assignee: Skydio, Inc.
    Inventors: Abraham Bachrach, Adam Bry, Matthew Donahoe
  • Patent number: 9797728
    Abstract: A vertical-view camera (16) delivers an image signal (ScamV) of the ground overflown by the drone. Gyrometric sensors (102) measure the Euler angles (?, ?, ?) characterizing the attitude of the drone and delivering a gyrometric signal (Sgyro) representative of the instantaneous rotations. Rotation compensation means (136) receive the image signal and the gyrometric signal and deliver retimed image data, compensated for the rotations, then used to estimate the horizontal speeds of the drone. The camera and the inertial unit are piloted by a common clock (160), and it is provided a circuit (170) for determining the value of the phase-shift between the gyrometric signal and the image signal, and to apply this phase-shift value at the input of the rotation compensation means (136) to resynchronize the image signal onto the gyrometric signal before computation of the retimed image data.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: October 24, 2017
    Assignee: PARROT DRONES
    Inventors: Pierre Eline, Francois Callou
  • Patent number: 9798914
    Abstract: A source image having a bit depth greater than eight is captured from a moving target. The source image is processed to obtain a plurality of target images each having a bit depth of eight. A memory stores the 8-bit target images. A processor obtains statistical data about the source image, and selects one of the stored 8-bit target images based on the statistical data. A controller efficiently decodes only the selected 8-bit target image.
    Type: Grant
    Filed: June 2, 2016
    Date of Patent: October 24, 2017
    Assignee: Symbol Technologies, LLC
    Inventor: Duanfeng He