Target Tracking Or Detecting Patents (Class 382/103)
  • Patent number: 10097757
    Abstract: A method for determining bias in an inertial measurement unit of an image acquisition device comprises mapping at least one reference point within an image frame into a 3D spherical space based on a lens projection model for the image acquisition device to provide a respective anchor point in 3D space for each reference point.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: October 9, 2018
    Assignee: FotoNation Limited
    Inventor: Piotr Stec
  • Patent number: 10095942
    Abstract: Using various embodiments, methods, systems, and apparatuses for controlling a camera pivoting device (e.g., mechanical gimbal) are described. In one embodiment, the system comprises a main computing device, a gimbal stabilizer controller, and a computer vision camera, and/or a user camera. The system is able to track a target object using the computer vision camera even while the target object is moving, the base of the pivoting device is moving (e.g., when a user controlling the camera moves), or a combination of thereof. The camera pivoting device of the embodiments disclosed herein can be mounted on to any number of devices/objects that can provide mobility and/or transportation.
    Type: Grant
    Filed: December 14, 2015
    Date of Patent: October 9, 2018
    Assignee: Reflex Robotics, Inc
    Inventors: Enes Mentese, Seongdo Kim, Abdo Babukr
  • Patent number: 10095850
    Abstract: On-line course offerings can be made available to users using computational techniques that reliably authenticate the identity of individual student users during the course of the very submissions and/or participation that will establish student user proficiency with course content. Authentication methods and systems include applications of behavioral biometrics.
    Type: Grant
    Filed: May 19, 2015
    Date of Patent: October 9, 2018
    Assignee: Kadenze, Inc.
    Inventors: Perry R. Cook, Ajay Kapur, Owen S. Vallis, Jordan Hochenbaum
  • Patent number: 10095937
    Abstract: An apparatus for tracking a gaze of a user is provided. The apparatus includes a memory including computer executable instructions; and a processor that reads and executes the computer executable instructions. The instructions cause the processor to receive gaze information associated with the gaze of the user; based on the gaze information, determine whether change information associated with the gaze of the user is greater than a threshold value; and in response to determining the change information is greater than the threshold value, predict at least one from among a gaze vector of the gaze of the user and a location of a gaze target of the gaze of the user based on a kinematic model. The gaze tracking apparatus may be used in a vehicle to perform vehicle functions based on the gaze of a user of a vehicle or to update gaze modeling database.
    Type: Grant
    Filed: June 21, 2016
    Date of Patent: October 9, 2018
    Inventors: David A. Canella, Jarvis Chau, Steve A. Warden
  • Patent number: 10095954
    Abstract: Embodiments disclosed herein provide systems and methods for matching trajectories across disjointed video views. In a particular embodiment, a method provides receiving a plurality of tagged trajectories that are tagged with an indicator of which trajectory pairs of the plurality of tagged trajectories are matching trajectory pairs and processing each of the trajectory pairs using each of a plurality of trajectory matching algorithms. The method further provides creating a model for matching trajectories based on the output of each of the plurality of trajectory matching algorithms for each of the pairs. The method further provides receiving a pair of trajectories and processing the pair of trajectories using each of the plurality of the trajectory matching algorithms. The method further provides processing the output of each of the plurality of the trajectory matching algorithms for the pair of trajectories using the model to determine whether the pair of trajectories is matching.
    Type: Grant
    Filed: January 17, 2013
    Date of Patent: October 9, 2018
    Assignee: VERINT SYSTEMS LTD.
    Inventors: Shahar Daliyot, Gadi Zimerman, Shmuel Kiro, Oren Golan
  • Patent number: 10096117
    Abstract: A method for classifying a visual element in a video frame as either foreground or background, the video frame being characterized using a scene model comprising a plurality of modes, the method comprising the steps of: determining a blob boundary characteristic for a blob comprising at least the visual element; identifying a mode matched to the visual element; classifying the visual element and the matched mode as foreground dependent upon a match mode boundary characteristic of the matched mode; and updating the scene model dependent upon the blob boundary characteristic and the matched mode boundary characteristic.
    Type: Grant
    Filed: December 18, 2015
    Date of Patent: October 9, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventors: Amit Kumar Gupta, Ashley John Partis, David Kenji See
  • Patent number: 10096090
    Abstract: An image processing apparatus includes an identification unit configured to identify a contour region including a contour component in an input image, a determination unit configured to determine a scatter degree of the contour region in the input image, an emphasis processing unit configured to increase, in a case where the scatter degree of the contour region is greater than a determination value, an emphasis degree of the contour region in comparison to a case where the scatter degree is equal to or less than the determination value, and an output unit configured to output, to a display unit, the input image including the contour region in which the emphasis processing unit increases the emphasis degree.
    Type: Grant
    Filed: May 31, 2016
    Date of Patent: October 9, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventor: Yoshiyuki Nagashima
  • Patent number: 10096091
    Abstract: An image generating method and an image generating apparatus are provided. The image generating method includes generating a first image based on first event signals that are output from an event-based vision sensor during a first time period and stored in a buffer, generating a second image based on second event signals that are output from the event-based vision sensor during a second time period and stored in the buffer, and aligning the first image and the second image to generate a third image having a quality that is higher than qualities of the first image and the second image.
    Type: Grant
    Filed: July 14, 2016
    Date of Patent: October 9, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Kyoobin Lee, Eric Hyunsurk Ryu, Keun Joo Park
  • Patent number: 10097741
    Abstract: Provided are a depth camera and methods of measuring a depth image by using the depth camera. The depth camera is a time-of-flight (TOF) depth camera including: an illumination device that illuminates a patterned light to an object; a filter unit that reduces noise light included in light reflected by the object; and an image sensor that provides a depth image of the object by receiving light that enters through the filter unit. The illumination device includes: a light source; and a patterned light generator that changes the light emitted from the light source into the patterned light. The filter unit includes a band pass filter and an optical modulator. The patterned light generator may be a diffractive optical element or a refractive optical element.
    Type: Grant
    Filed: August 30, 2017
    Date of Patent: October 9, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jang-woo You, Yong-hwa Park, Hee-sun Yoon
  • Patent number: 10096107
    Abstract: Intelligent image parsing for anatomical landmarks and/or organs detection and/or segmentation is provided. A state space of an artificial agent is specified for discrete portions of a test image. A set of actions is determined, each specifying a possible change in a parametric space with respect to the test image. A reward system is established based on applying each action of the set of actions and based on at least one target state. The artificial agent learns an optimal action-value function approximator specifying the behavior of the artificial agent to maximize a cumulative future reward value of the reward system. The behavior of the artificial agent is a sequence of actions moving the agent towards at least one target state. The learned artificial agent is applied on a test image to automatically parse image content.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: October 9, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Florin Cristian Ghesu, Bogdan Georgescu, Dominik Neumann, Tommaso Mansi, Dorin Comaniciu, Wen Liu, Shaohua Kevin Zhou
  • Patent number: 10096132
    Abstract: A feature point positioning apparatus includes a memory storing computer-executable instructions; and one or more processors configured to execute the computer-executable instructions such that the one or more processors are configured to, iteratively update a first form coefficient based on, a nonlinear feature extracted from an image, and a regression factor matrix obtained through training, and detect a position of the feature point of the image based on, the updated first form coefficient, and a statistical form model obtained through training.
    Type: Grant
    Filed: January 26, 2017
    Date of Patent: October 9, 2018
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Mingcai Zhou, Jingu Heo, Tao Hong, Weiming Li, Zairan Wang, Zhihua Liu, Dong Kyung Nam, Haitao Wang
  • Patent number: 10096123
    Abstract: In one implementation, a method includes generating a set of candidate objects based at least in part on a set of image data, where the set of image data includes image data from a plurality of image sources. The method also includes generating a set of visual signatures, wherein each of the visual signatures in the set of visual signatures characterizes a candidate object in the set of candidate objects. The method further includes transforming at least two candidate objects in the set of candidate objects into a single object according to a determination that correspondence between visual signatures for the at least two candidate objects satisfies one or more correspondence criteria.
    Type: Grant
    Filed: April 19, 2016
    Date of Patent: October 9, 2018
    Assignee: CISCO TECHNOLOGY, INC.
    Inventors: Xiaoqing Zhu, Robert Edward Liston, Wai-tian Tan
  • Patent number: 10096251
    Abstract: An example method of establishing a flight pattern adjacent to a target for an aerial vehicle to follow includes determining a stand-off distance to the target. The stand-off distance indicates a distance from the target at a point along the flight pattern. The example method also includes generating the flight pattern in a form of a conchoidal transformation of a lemniscate based on the stand-off distance.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: October 9, 2018
    Assignee: Insitu, Inc.
    Inventor: Rolf Rysdyk
  • Patent number: 10088895
    Abstract: Systems and processes for providing virtual sexual experiences are disclosed for allowing a user to experience a virtual sexual encounter based on the user's real world movements. The system includes a provider platform for generating content having one or more of a sexual avatar and a user avatar. The system also includes a user platform having a motion tracking unit for detecting and tracking the real world physical movements of the user, and manipulating the generated content based on the movement.
    Type: Grant
    Filed: March 7, 2016
    Date of Patent: October 2, 2018
    Assignee: Bent Reality Labs, LLC
    Inventors: John Baker, Scott Johnson, Jaime Cisneros
  • Patent number: 10091477
    Abstract: The projection image display apparatus includes a display element that emits image light generated by modulating light from a light source based, a pixel-shifter that shifts a pixel of a projected image by changing an optical path of the image light, a resampling circuit, a motion-interpolation image processing circuit, and a pixel-shift controller. The resampling circuit generates a plurality of sub-frame image signals having a resolution of the display element, by resampling an image signal having a resolution of the projected image. The motion-interpolation image processing circuit provides a motion-interpolation image process to the sub-frame image signals. The pixel-shift controller receives the sub-frame image signals having undergone the motion-interpolation image process.
    Type: Grant
    Filed: June 15, 2016
    Date of Patent: October 2, 2018
    Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
    Inventors: Akiyoshi Yamaguchi, Masutaka Inoue, Takaaki Gyoten, Takaaki Abe, Ryoji Okubo, Kazuma Tani
  • Patent number: 10089551
    Abstract: Embodiments are directed to an object detection system having at least one processor circuit configured to receive a series of image regions and apply to each image region in the series a detector, which is configured to determine a presence of a predetermined object in the image region. The object detection system performs a method of selecting and applying the detector from among a plurality of foreground detectors and a plurality of background detectors in a repeated pattern that includes sequentially selecting a selected one of the plurality of foreground detectors; sequentially applying the selected one of the plurality of foreground detectors to one of the series of image regions until all of the plurality of foreground detectors have been applied; selecting a selected one of the plurality of background detectors; and applying the selected one of the plurality of background detectors to one of the series of image regions.
    Type: Grant
    Filed: December 8, 2015
    Date of Patent: October 2, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Russell P. Bobbitt, Rogerio S. Feris, Chiao-Fe Shu, Yun Zhai
  • Patent number: 10089827
    Abstract: An electronic gaming machine is provided. The computer device comprises at least one data storage unit storing game data for a game, a display unit to display graphical game components to a player of the game, at least one data capture unit, such as a camera, to collect data about the player's gaze, and a processor to process the player gaze data, determine if a player gaze condition is satisfied, determine whether a game condition is satisfied. If both the player gaze condition and the game condition are satisfied, the processor modifies at least some of the graphical game components based on the player gaze condition and the game condition.
    Type: Grant
    Filed: December 11, 2015
    Date of Patent: October 2, 2018
    Assignee: IGT CANADA SOLUTIONS ULC
    Inventors: David Froy, Edward Bowron, Reuben Dupuis, Vicky Leblanc, Karen Van Niekerk, Christopher Spurrell
  • Patent number: 10089435
    Abstract: The field of this invention is classifying animal behaviors. In particular the fields of this invention include using animals in vivariums, such as rodents, particularly mice. When two mice socialize, a first mouse vocalizes a call and the second mouse vocalizes a response. Ultrasonic calls and responses are compared to video behaviors of the same mice, and then a table is constructed where each line comprises a particular call and response, a corresponding video behavior, and a correlation weight.
    Type: Grant
    Filed: August 2, 2017
    Date of Patent: October 2, 2018
    Assignee: Vium, Inc.
    Inventors: Jonathan Betts-Lacroix, Laura Schaevitz
  • Patent number: 10085692
    Abstract: An exercise support device includes: a display section which has a display area where a first object as a virtual mobile object and a second object corresponding to a user are displayed; and a control section which controls display positions of the first object and the second object in the display area. The control section, while the user is moving from a first point to a second point, controls such that the display position of the first object is set to a position corresponding to a first movement distance based on a set target pace and an elapsed time after the user starts movement; and that the display position of the second object is set to a position corresponding to a second movement distance that the user moves from the first point in the elapsed time.
    Type: Grant
    Filed: December 13, 2013
    Date of Patent: October 2, 2018
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Kazuo Ura
  • Patent number: 10089527
    Abstract: An image processing device includes: a reference area setting unit which sets a reference area including an indicated segment; an extraction unit which extracts an interest object feature quantity indicating a first feature from the reference area; an interest area setting unit which sets an area of interest in a third image, based on a relationship between a position of a feature point extracted from a feature area which is an area corresponding to an object of interest and included in a second image and a position of a feature point in the third image corresponding to the extracted feature point; and a tracking unit which determines for each of two or more of plural segments included in the area of interest with use of the interest object feature quantity whether the segment is a segment corresponding to the object of interest.
    Type: Grant
    Filed: March 8, 2013
    Date of Patent: October 2, 2018
    Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA
    Inventor: Yasunori Ishii
  • Patent number: 10088294
    Abstract: A method includes determining movement of a camera from a first time point when a first image has been captured to a second time point when a second image has been captured, performing first estimation processing for estimating a position and pose of the camera in the second time point based on image data at the time of capturing, a past image captured in the past, and a past position and pose of the camera at a time point when the past image has been captured, when the movement is not a translational movement and a rotation movement around an optical direction, and performing a second estimation processing for estimating the position and pose based on a feature descriptor of a feature point extracted from the second image and a feature descriptor of a map point accumulated when the movement is the translational movement or the rotational movement.
    Type: Grant
    Filed: April 13, 2016
    Date of Patent: October 2, 2018
    Assignee: FUJITSU LIMITED
    Inventors: Atsunori Moteki, Nobuyasu Yamaguchi, Toshiyuki Yoshitake
  • Patent number: 10089330
    Abstract: A method of image retrieval includes obtaining information identifying a plurality of selected objects and selecting one among a plurality of candidate geometrical arrangements. This method also includes, by at least one processor, and in response to the selecting, identifying at least one digital image, among a plurality of digital images, that depicts the plurality of selected objects arranged according to the selected candidate geometrical arrangement.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: October 2, 2018
    Assignee: QUALCOMM Incorporated
    Inventors: Dashan Gao, Xin Zhong, Ananthapadmanabhan Arasanipalai Kandhadai, Steven Douglas Laver
  • Patent number: 10083620
    Abstract: Methods, apparatuses, and non-transitory computer readable storage media for a smart tutorial that adapts are described. The smart tutorial may assist in the operation of a vehicle including generating a situational profile that includes driver identity data, vehicle state data, or extra-vehicular state data. The situational profile is compared to assistance profiles that include aggregate identity data, aggregate vehicular state data, or aggregate extra-vehicular state data. The assistance profiles correspond to assistance instructions. Based on the comparison, similarity values corresponding to the assistance profiles are generated based on the comparison between the situational profile and the assistance profiles. The greatest similarity value corresponds to the assistance profile that is most similar to the situational profile.
    Type: Grant
    Filed: July 29, 2016
    Date of Patent: September 25, 2018
    Assignees: Nissan North America, Inc., Renault S.A.S.
    Inventors: David M. Nishijima, Lionel Cordesses, Simon Hougard
  • Patent number: 10085000
    Abstract: An imaging device includes an imaging sensor that outputs an imaging signal representing a sequence of frame images of a photographic subject. A buffer memory temporarily stores data of the sequence of frame images from the imaging signal. A release switch is actuated by a user to output an image-taking signal. A controller, upon receipt of the image-taking signal from the release switch: (i) generates moving image data from at least some of the plurality of frame images stored in the buffer memory, (ii) generates at least one piece of still image data based on at least one frame image of the plurality of frame images stored in the buffer memory, and (iii) associates the moving image data with the still image data and records the moving image data and the still image data in a recording medium.
    Type: Grant
    Filed: July 20, 2016
    Date of Patent: September 25, 2018
    Assignee: NIKON CORPORATION
    Inventor: Takashi Kuriyama
  • Patent number: 10082800
    Abstract: A method of stabilizing mission equipment by a mission equipment stabilization system using an unmanned aerial system command and posture information, includes, receiving and transmitting a roll or pitch posture command signal to an autopilot control loop and a posture prediction unit; transmitting a command signal to a control surface so that the aerial system follows the command signal; receiving the posture command signal, filtering a posture prediction through angular velocity limitation and time-delayed filtering, simulating/predicting a response from the autopilot control loop, and outputting a posture prediction signal; converting the posture prediction signal predicted by the posture prediction unit into an azimuth command signal; differentiating the azimuth command signal into an angular velocity command signal; removing noise from the differentiated angular velocity command signal; and receiving the angular velocity command signal and stably doing a mission.
    Type: Grant
    Filed: January 11, 2016
    Date of Patent: September 25, 2018
    Assignee: KOREAN AIR LINES CO., LTD.
    Inventor: Jung Ho Moon
  • Patent number: 10083601
    Abstract: A remote control device includes: a detector that detects a time-dependent change of a position of a recognition target object; a motion recognition unit that recognizes a gesture corresponding to the time-dependent change of the position of the recognition target object detected by the detector; a controller that generates a control signal based on the gesture recognized by the motion recognition unit; and a transmitter that transmits the control signal to an apparatus having a drivable portion to command a movement of the drivable portion.
    Type: Grant
    Filed: August 2, 2016
    Date of Patent: September 25, 2018
    Assignee: Minebea Co., Ltd.
    Inventors: Yoshihiro Nakamura, Kohei Nishibori
  • Patent number: 10083356
    Abstract: An example system includes a stand configured to position a computing device proximate to a physical activity surface. The system further includes a video capture device, a detector, and an activity application. The video capture device is coupled for communication with the computing device and is adapted to capture a video stream that includes an activity scene of the physical activity surface and one or more interface objects physically interactable with by a user. The detector is executable to detect motion in the activity scene based on the processing and, responsive to detecting the motion, process the video stream to detect one or more interface objects included in the activity scene of the physical activity surface. The activity application is executable to present virtual information on a display of the computing device based on the one or more detected interface objects.
    Type: Grant
    Filed: May 21, 2015
    Date of Patent: September 25, 2018
    Assignee: Tangible Play, Inc.
    Inventors: Pramod Kumar Sharma, Jerome Scholler
  • Patent number: 10079999
    Abstract: A magnetic resonance imaging (MRI) location surveillance system (10) for determining access to a room (12) containing an MRI device (14) which includes a superconducting magnet and images subjects includes at least one video camera (26) positioned to view an entrance (26) to the room containing the MRI device (14), a recognize unit (36) in communication with the at least one video camera, a classify unit (37), and an authorize unit (38). The at least one video camera (26) images objects and persons approaching the entrance (16). The recognize unit (36) receives the imaged objects and persons, and recognizes each imaged object and each imaged person. The classify unit (37) classifies each recognized object (24) and each recognized person (22) according to MRI safety. The authorize unit (38) determines access to the room (14) containing the MRI device (14) based on each classified object and each classified person.
    Type: Grant
    Filed: October 23, 2014
    Date of Patent: September 18, 2018
    Assignee: Koninklijke Philips N.V.
    Inventor: Johan Samuel Van Den Brink
  • Patent number: 10078890
    Abstract: Disclosed herein are methods and systems for anomaly detection within a field using images or sensor data. An anomaly detection process determines whether a pixel or a cluster of pixels fit within calculated or modeled expectations to identify an anomaly. The process can further analyze the anomaly to determine a likely cause. Example anomaly detection techniques account for intra-field inhomogeneity and for non-crop regions. Example anomaly detection techniques also can identify anomalous regions.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: September 18, 2018
    Assignee: CHS North LLC
    Inventors: Jerry D. Tagestad, Chris Rushing, Josh Brungardt, Chris Joyce, Bjorn Roth
  • Patent number: 10078961
    Abstract: A traffic-infrastructure unit and a method for operating a traffic-infrastructure unit encompassing a signal source, the method having a step of detecting at least one vehicle, a step of detecting at least one further road user, a step of determining a danger potential for the at least one further road user due to the at least one vehicle, and a step of operating the traffic-infrastructure unit as a function of the determined danger potential.
    Type: Grant
    Filed: May 24, 2017
    Date of Patent: September 18, 2018
    Assignee: ROBERT BOSCH GMBH
    Inventors: Johannes Ruenz, Berthold Kaeferstein
  • Patent number: 10076242
    Abstract: Systems and methods for classifying abnormalities within optical coherence tomography images of the eye are presented. One embodiment of the present invention is the classification of pigment epithelial detachments (PEDs) based on characteristics of their internal reflectivity, size and shape. The classification can be based on selected subsets of the data located within or surrounding the abnormalities. Training data can be used to generate the classification scheme and the classification can be weighted to highlight specific classes of particular clinical interest.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: September 18, 2018
    Assignees: DOHENY EYE INSTITUTE, UNIVERSITY OF SOUTHERN CALIFORNIA, CARL ZEISS MEDITEC, INC.
    Inventors: SriniVas R. Sadda, Paul F. Stetson
  • Patent number: 10073541
    Abstract: Applications such as gesture detection and head tracking can utilize one or more imaging elements on a computing device. While it can be desirable to hide these elements as much as possible so as to have minimal impact on the design or appearance of the device, hiding the elements can cause users to inadvertently cover or block these elements when performing certain actions. When one or more of these elements are determined to be blocked or obscured by a user, the device can provide one or more indicators or cues that can indicate not only that the user is blocking an element, but also indicates the location of the element. The cues can take the form of circles, arcs, arrows, or other elements that can guide the user to the location of an element. Other indicators can be used as well, as may include audio and/or haptic feedback.
    Type: Grant
    Filed: June 22, 2012
    Date of Patent: September 11, 2018
    Assignee: Amazon Technologies, Inc.
    Inventor: Leo B. Baldwin
  • Patent number: 10074017
    Abstract: A fusion based passenger tracking system includes one or more 2D/3D sensors for capturing 2D/3D data; one or more security sensors for capturing security data; and a processing module in communication with the one or more 2D/3D sensors to receive the 2D/3D data, and the one or more security sensors to receive the security data, the processing module uses the 2D/3D data and the security data to calculate passenger data to generate a passenger tracking list that tracks each individual passenger in the passenger data.
    Type: Grant
    Filed: April 4, 2016
    Date of Patent: September 11, 2018
    Assignee: Otis Elevator Company
    Inventors: Zhen Jia, Hui Fang, Arthur Hsu, Alan Matthew Finn
  • Patent number: 10074098
    Abstract: One aspect of the disclosure relates to a digital signage display system. In one embodiment, the digital signage display system includes: a camera configured to capture an image frame; a service processor in communication to the camera; and a digital signage display. The service processor includes a processor and a non-volatile memory storing a firmware. The firmware is configured, when executed at the processor, to process the captured image frame, detect persons in the image frame, generate a demographic-map data structure, and send the demographic-map data structure to a server system. The demographic-map data structure contains demographic information of the persons detected in the image frame. The digital signage display is configured to receive a display content provided by the server system in response to the demographic-map data structure.
    Type: Grant
    Filed: May 8, 2013
    Date of Patent: September 11, 2018
    Assignee: AMERICAN MEGATRENDS, INC.
    Inventors: Sanjoy Maity, Satheesh Thomas, Baskar Parthiban, Varadachari Sudan Ayanam, Samvinesh Christopher, Joseprabu Inbaraj
  • Patent number: 10074188
    Abstract: A method and apparatus for processing an image, whereby a 3-dimensional (3D) hand model corresponding to a hand image obtained may be generated by capturing an image of a hand of a person are provided. The method includes preparing a 3D hand model database, receiving a 2-dimensional (2D) hand image obtained by capturing an image of a first hand, and detecting a first 3D hand model corresponding to the 2D hand image by using the 3D hand model database.
    Type: Grant
    Filed: September 3, 2014
    Date of Patent: September 11, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ivan Koryakovskiy, Seong-oh Lee, Moon-sik Jeong, Sung-do Choi
  • Patent number: 10074205
    Abstract: Methods, apparatus, and systems to create, output, and use animation programs comprising keyframes, objects, object states, and programming elements. Objects, object states, and programming elements may be created through image analysis of image input. Animation programs may be output as videos, as non-linear interactive experiences, and/or may be used to control electronic actuators in articulated armatures.
    Type: Grant
    Filed: August 30, 2016
    Date of Patent: September 11, 2018
    Assignee: Intel Corporation
    Inventors: Glen J. Anderson, David I. Poisner, Ravishankar Iyer, Mark Francis, Michael E. Kounavis, Omesh Tickoo
  • Patent number: 10075436
    Abstract: An information processing apparatus includes an authenticating section, a detecting section, and a processor. The authenticating section authenticates a user. When the authenticating section has authenticated a first user, the detecting section detects a second user in the vicinity of the information processing apparatus. The second user is different from the first user. When the detecting section detects the second user, the processor performs a predetermined process.
    Type: Grant
    Filed: April 29, 2015
    Date of Patent: September 11, 2018
    Assignee: FUJI XEROX CO., LTD.
    Inventor: Yuri Takeuchi
  • Patent number: 10075651
    Abstract: Methods and apparatus for capturing images using a camera device including multiple camera modules, e.g., multiple optical chains, in an efficient manner are described. Different camera devices in the camera device may capture images corresponding to different size fields of view of a scene area. User input is used to identify an object of interest. A first type camera module having a large field of view is used to track the identified object of interest. Sets of second type camera modules having a smaller field of view are used to capture images of the object of interest. Different sets of second type camera modules may be used at different times as a function of object of interest location. In some embodiments, at least some second type camera modules include the capability to adjust, e.g., move, image capture area, e.g., by changing a mirror angle inclination and/or a mirror rotation.
    Type: Grant
    Filed: April 22, 2015
    Date of Patent: September 11, 2018
    Assignee: Light Labs Inc.
    Inventors: Rajiv Laroia, Sapna A. Shroff
  • Patent number: 10074021
    Abstract: A vehicle detection apparatus detects an object based on an image captured from a vehicle. In the vehicle detection apparatus, a camera is mounted in the vehicle. A search region determining unit determines a region including a road surface in the image to be a search region. A cost minimizing unit divides the search region into two, an upper region and a lower region, by a boundary line, determines corresponding points in a plurality of images captured by the camera at different time points by applying an optical flow model having a fixed magnification factor to the upper region and an optical flow model having a planar constraint condition to the lower region, and determines a boundary line that minimizes cost related to a difference between pixel values of the corresponding points. A vehicle presence determining unit determines presence of a forward vehicle based on the boundary line.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: September 11, 2018
    Assignee: DENSO CORPORATION
    Inventors: Kensuke Yokoi, Kohta Ishikawa, Ikuro Sato
  • Patent number: 10068375
    Abstract: To notify a user of an area where marker-based position and orientation measurement becomes unstable, an information processing apparatus according to the present specification includes, a first acquisition unit configured to acquire arrangement information and size information of a marker arranged in a real space, a second acquisition unit configured to acquire information about an imaging apparatus for capturing the real space, an unstable area derivation unit configured to derive an unstable area where the imaging apparatus is unable to stably detect the marker arranged in the real space, based on the arrangement information and the size information of the marker and the information about the imaging apparatus, and an output unit configured to output the area derived by the derivation unit.
    Type: Grant
    Filed: September 11, 2015
    Date of Patent: September 4, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Yasumi Tanaka
  • Patent number: 10068343
    Abstract: The present invention is applicable to the technical field of video monitoring. Provided are a method and an apparatus for recognizing a moving target. The method comprises: A: acquiring a video image with a background and a moving target; B: modeling a first video image to obtain a first background model; C: calculating a first differential image according to a second image and the first background model; D: modeling a second video image to obtain a second background model; E: calculating a second differential image according to a third image and the second background model; F: separately calculating a first binary image and a second binary image according to the first differential image and the second differential image; G: obtaining a variation region of the moving target according to the first binary image and the second binary image; and H: repeatedly performing steps A to G sequentially, and detecting variation regions of all moving targets.
    Type: Grant
    Filed: July 29, 2014
    Date of Patent: September 4, 2018
    Assignee: SHENZHEN HUABAO ELECTRONIC TECHNOLOGY CO., LTD.
    Inventors: Shaohua Zhuang, Wenming Chen, Changbei Jiang
  • Patent number: 10068336
    Abstract: Described is a system for frontal and side doorway detection. Salient line segments are extracted from an image frame captured of an indoor environment. Existence of a vanishing point in the image frame is determined. If a vanishing point is detected with a confidence score that meets or exceeds a predetermined confidence score, then the system performs side doorway detection via a side doorway detection module. If a vanishing point is detected with a confidence score below the predetermined confidence score, then the system performs frontal doorway detection via a frontal doorway detection module. A description of detected doorways is output and used by a mobile robot (Unmanned Aerial Vehicle) to autonomously navigate the indoor environment.
    Type: Grant
    Filed: August 29, 2016
    Date of Patent: September 4, 2018
    Assignee: HRL Laboratories, LLC
    Inventors: Lei Zhang, Fredy Monterroza, Kyungnam Kim, Jiejun Xu, Yang Chen, Deepak Khosla
  • Patent number: 10068135
    Abstract: A face detection and tracking method of a robotic device. The method includes obtaining a video frame from a camera of the robotic device; performing a face detection process on the video frame to detect one or more faces in the video frame and, after the face detection process, identifying the detected one or more faces in the video frame. The method also includes performing a vision-based tracking process to track the identified one or more faces using a combination of a feature points tracker and a correlation tracker and, after the vision-based tracking process, performing a detection and tracking fusion process and providing desired target prediction of the identified one or more faces.
    Type: Grant
    Filed: December 22, 2016
    Date of Patent: September 4, 2018
    Assignee: TCL RESEARCH AMERICA INC.
    Inventors: Xinyao Sun, Xinpeng Liao, Xiaobo Ren, Haohong Wang
  • Patent number: 10060734
    Abstract: The dimension measurement device of one aspect of the present invention includes: an obtainer configured to obtain, from a measurement device for performing three dimensional measurement of a desired object, a set of coordinates in three dimensions of the desired object; a surface extractor configured to determine a focused surface constituting the desired object based on the set of coordinates, and extract a position of a boundary of the focused surface; a region extractor configured to extract, in relation to a candidate region corresponding to an object being a specific object attached to the focused surface, a position of an edge surrounding the candidate region; and a dimension generator configured to generate dimensional data necessary for creating a dimensional drawing of the desired object from the position of the boundary and the position of the edge.
    Type: Grant
    Filed: September 26, 2014
    Date of Patent: August 28, 2018
    Assignee: Panasonic Intellectual Property Management Co., Ltd.
    Inventors: Harumi Yamamoto, Hajime Jikihara
  • Patent number: 10063835
    Abstract: Imaging apparatus includes an illumination assembly, including a plurality of radiation sources and projection optics, which are configured to project radiation from the radiation sources onto different, respective regions of a scene. An imaging assembly includes an image sensor and objective optics configured to form an optical image of the scene on the image sensor, which includes an array of sensor elements arranged in multiple groups, which are triggered by a rolling shutter to capture the radiation from the scene in successive, respective exposure periods from different, respective areas of the scene so as to form an electronic image of the scene. A controller is coupled to actuate the radiation sources sequentially in a pulsed mode so that the illumination assembly illuminates the different, respective areas of the scene in synchronization with the rolling shutter.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: August 28, 2018
    Assignee: APPLE INC.
    Inventors: Zafrir Mor, Alexander Shpunt
  • Patent number: 10060739
    Abstract: Method for precisely determining the position offset and orientation offset of a second deployment relative to a first deployment in the same measurement environment of a geodetic surveying device, in particular a total station or a theodolite, on the basis of directions, determined on the basis of the image, and at least one distance, measured by laser-optical means, to measurement environment points, which are imaged both in a second and in a first environment image.
    Type: Grant
    Filed: December 8, 2015
    Date of Patent: August 28, 2018
    Assignee: LEICA GEOSYSTEMS AG
    Inventors: Bernhard Metzler, Stefan Martin Benjamin G├Ąchter Toya
  • Patent number: 10062211
    Abstract: An example information processing system includes: a computer; an imaging device; a display device; and a first and a second feature placed in a real space. The computer includes: an image acquiring unit that acquires an image of the real space; a feature detecting unit that detects the first feature and the second feature from the image; a changing unit that changes an association of the first feature with a virtual objects by adding a virtual object associated with the second feature, and an generating unit that generates an image of a virtual space in which the virtual object associated with the first feature is placed at a position based on the first feature; and a display controlling unit that displays an image on the display device.
    Type: Grant
    Filed: May 6, 2014
    Date of Patent: August 28, 2018
    Assignee: Nintendo Co., Ltd.
    Inventors: Takeshi Hayakawa, Naoki Koga
  • Patent number: 10061896
    Abstract: The present disclosure describes various aspects of remote presence interfaces (RPIs) for use on portable electronic devices (PEDs) to interface with remote telepresence devices. An RPI may allow a user to interact with a telepresence device, view a live video feed, provide navigational instructions, and/or otherwise interact with the telepresence device. The RPI may allow a user to manually, semi-autonomously, or autonomously control the movement of the telepresence device. One or more panels associated with a video feed, patient data, calendars, date, time, telemetry data, PED data, telepresence device data, healthcare facility information, healthcare practitioner information, menu tabs, settings controls, and/or other features may be utilized via the RPI.
    Type: Grant
    Filed: May 13, 2016
    Date of Patent: August 28, 2018
    Assignees: INTOUCH TECHNOLOGIES, INC., IROBOT CORPORATION
    Inventors: Charles S. Jordan, Andy Young, Mei Sheng Ng, Yair Lurie, Fuji Lai, Timothy C. Wright, Cody Herzog, Blair Whitney, Bill Rizzi, James Ballantyne, Yulun Wang, Cheuk Wah Wong, Justin H. Kearns, Orjeta Taka, Ramchandra Karandikar
  • Patent number: 10059263
    Abstract: The present disclosure relates to a method for selectively highlighting visual zones associated with a vehicle. A point of origin and a gaze direction of a vehicle occupant are determined and a virtual projection plotted corresponding to the gaze of the vehicle occupant. The virtual projection extends from the determined point of origin in a direction of the determined gaze direction. With reference to a three-dimensional model comprising a plurality of pre-defined areas of interest, an intersection of the virtual projection with one of the plurality of areas of interest is identified. The method comprises controlling an illumination source that is associated with the determined one of said plurality of areas of interest so as to highlight a visual zone associated with the vehicle.
    Type: Grant
    Filed: April 15, 2015
    Date of Patent: August 28, 2018
    Assignee: Jaguar Land Rover Limited
    Inventors: Sebastian Paszkowicz, George Alexander, Robert Hardy, Eduardo Dias, Anna Gaszczak, Thomas Popham
  • Patent number: 10060751
    Abstract: An approach is provided for point-based map matchers using machine learning. The approach involves retrieving points collected within proximity to a map feature represented by a link of a geographic database. The probe points are collected from sensors of devices traveling near the map feature. The approach also involves determining a probe feature set for each probe point comprising probe attribute values, and determining a link feature set for the link comprising link attribute values. The apparatus further involves classifying, using a machine learning classifier, each probe point to determine a matching probability based on the probe feature set and the link feature to indicate a probability that each probe point is classified as map-matched to the link. The machine learning classifier is trained using ground truth data comprising reference probe points with known map-matches to respective reference links, and comprising known probe attribute values and known link attribute values.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: August 28, 2018
    Assignee: HERE Global B.V.
    Inventors: Qin Chen, Jaime Ballesteros