Motion Or Velocity Measuring Patents (Class 382/107)
-
Patent number: 10698063Abstract: Systems and methods are provided for correcting motion artifacts in magnetic resonance images. An image-to-image neural network is used to generate motion corrected magnetic resonance data given motion corrupted magnetic resonance data. The image-to-image neural network is coupled within an adversarial network to help refine the generated magnetic resonance data. The adversarial network includes a generator network (the image-to-image neural network) and a discriminator network. The generator network is trained to minimize a loss function based on a Wasserstein distance when generating MR data. The discriminator network is trained to differentiate the motion corrected MR data from motion artifact free MR data.Type: GrantFiled: June 14, 2018Date of Patent: June 30, 2020Assignee: Siemens Healthcare GmbHInventors: Sandro Braun, Boris Mailhe, Xiao Chen, Benjamin L. Odry, Pascal Ceccaldi, Mariappan S. Nadar
-
Patent number: 10682562Abstract: Exemplary embodiments of the present disclosure are directed to systems, methods, and computer-readable media configured to autonomously generate personalized recommendations for a user before, during, or after a round of golf. The systems and methods can utilize course data, environmental data, user data, and/or equipment data in conjunctions with one or more machine learning algorithms to autonomously generate the personalized recommendations.Type: GrantFiled: January 16, 2018Date of Patent: June 16, 2020Assignee: Arccos Golf LLCInventors: Salman Hussain Syed, Colin David Phillips
-
Patent number: 10687016Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A selection of a time-lapse amount can be received. A subset of frames from the original set of frames can be identified based on the time-lapse amount. An orientation-based image stabilization process can be applied to the subset of frames to produce a stabilized subset of frames. A stabilized time-lapse media content item can be provided based on the stabilized subset of frames.Type: GrantFiled: May 27, 2016Date of Patent: June 16, 2020Assignee: Facebook, Inc.Inventors: Thomas Frederick Dimson, Alexandre Karpenko
-
Patent number: 10681336Abstract: Aspects of the disclosure relate generally to generating depth data from a video. As an example, one or more computing devices may receive an initialization request for a still image capture mode. After receiving the request to initialize the still image capture mode, the one or more computing devices may automatically begin to capture a video including a plurality of image frames. The one or more computing devices track features between a first image frame of the video and each of the other image frames of the video. Points corresponding to the tracked features may be generated by the one or more computing devices using a set of assumptions. The assumptions may include a first assumption that there is no rotation and a second assumption that there is no translation. The one or more computing devices then generate a depth map based at least in part on the points.Type: GrantFiled: May 15, 2014Date of Patent: June 9, 2020Assignee: Google LLCInventors: David Gallup, Fu Yu, Steven Maxwell Seitz
-
Patent number: 10674909Abstract: An ophthalmic analysis apparatus for analyzing OCT motion contrast (MC) image data of a subject's eye acquired using an OCT apparatus for ophthalmology includes analysis process means for analyzing the OCT MC image data, in which the analysis process means generates OCT blood vessel change data including temporal change information in relation to a blood vessel region of the subject's eye based on first OCT MC image data and second OCT MC image data acquired at mutually different times.Type: GrantFiled: September 6, 2017Date of Patent: June 9, 2020Assignee: NIDEK CO., LTD.Inventors: Tetsuya Kano, Norimasa Satake, Yukihiro Higuchi, Yasuhiro Furuuchi
-
Patent number: 10672028Abstract: A favorable merging or grouping of simply connected regions into which the array of information samples is sub-divided, is coded with a reduced amount of data. To this end, a predetermined relative locational relationship is defined enabling an identifying, for a predetermined simply connected region, of simply connected regions within the plurality of simply connected regions which have the predetermined relative locational relationship to the predetermined simply connected region. Namely, if the number is zero, a merge indicator for the predetermined simply connected region may be absent within the data stream. In other embodiments, spatial sub-division is performed depending on a first subset of syntax elements, followed by combining spatially neighboring simply connected regions depending on a second subset of syntax elements, to obtain an intermediate sub-division.Type: GrantFiled: February 5, 2019Date of Patent: June 2, 2020Assignee: GE VIDEO COMPRESSION, LLCInventors: Philipp Helle, Simon Oudin, Martin Winken, Detlev Marpe, Thomas Wiegand
-
Patent number: 10664983Abstract: A method for implementing a virtual reality (VR) interface based on a single camera. The method includes obtaining pointer coordinates based on an image obtained by a single camera attached to a VR device, converting the pointer coordinates into virtual pointer coordinates based on a distance factor between the single camera and the VR device and a user factor including an input range of a real space derived according to a body characteristic of a user, and displaying the converted virtual pointer coordinates on the VR device.Type: GrantFiled: April 17, 2017Date of Patent: May 26, 2020Assignee: DEEPIXEL INC.Inventors: Jehoon Lee, Wahseng Yap, Honam Ahn
-
Patent number: 10650529Abstract: A lane detection method and apparatus is disclosed. The lane detection apparatus may set a regions of interest (ROIs) in a forward-view image of a vehicle obtained by a camera, estimate lane pixels corresponding to a lane from each of the ROIs using a neural network-based detector, and determine a lane region in the forward-view image based on the lane pixels.Type: GrantFiled: February 9, 2018Date of Patent: May 12, 2020Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventor: Cheolhun Jang
-
Patent number: 10645423Abstract: A video image encoding device includes a memory and a processor. The processor is configured to determine a noise distribution within a target image to be encoded and included in a video image. The processor may limit sizes of blocks to be used for video image encoding of the target image to one or more sizes among multiple selectable sizes when it is determined that the noise distribution within the target image to be encoded is a predetermined noise distribution. The processor may also encode the target image by executing the video image encoding using the blocks of the one or more sizes.Type: GrantFiled: November 13, 2018Date of Patent: May 5, 2020Inventor: Akihiro Yamori
-
Patent number: 10636156Abstract: A method for analyzing a three-dimensional (3D) information of an image based on a single camera according to an embodiment of the present disclosure is provided to. The method includes storing an image obtained by the single camera on a frame-by-frame basis, determining a plurality of feature points configuring a hand shape included in the stored image and extracting a region of interest (ROI) based on the feature points, tracking a change in a two-dimensional (2D) length component configured with feature points of the ROI during a predetermined time interval, analyzing a change in 3D coordinates of the feature points based on the change in the 2D length component and deriving a motion vector of the feature points during the predetermined time interval based on the analysis, and determining an operation indicated by a hand shape based on the derived motion vector.Type: GrantFiled: September 12, 2016Date of Patent: April 28, 2020Assignee: DEEPIXEL INC.Inventor: Jehoon Lee
-
Patent number: 10636190Abstract: A method for motion estimation in an augmented reality (AR) system includes receiving inertial sensor data and image data during movement of the AR system generating a probability map based on the inertial sensor data and the image data, the probability map corresponding to one frame in the image data and including probability values indicating that each pixel in the one frame is in an inertial coordinate frame or a local coordinate frame with a convolutional neural network encoder/decoder, identifying visual observations of at least one landmark in the local coordinate frame based on the image data and the probability map, and generating an estimate of secondary motion in the local coordinate frame based on a first prior state in a hidden Markov model (HMM) corresponding to the local coordinate frame and the visual observations of the at least one landmark in the local coordinate frame.Type: GrantFiled: October 12, 2018Date of Patent: April 28, 2020Assignee: Robert Bosch GmbHInventors: Benzun Pious Wisely Babu, Zhixin Yan, Mao Ye, Liu Ren
-
Patent number: 10631818Abstract: A method for geometric calibration of a mobile radiography apparatus, executed at least in part by a computer, acquires a series of tomosynthesis projection images of a patient positioned between an x-ray source of the mobile radiography apparatus and a detector that is positionally uncoupled from the x-ray source. A vector field is generated having a first set of vectors indicative of feature movement between a first acquired projection image and a second acquired projection image. The generated vector field is associated with an epipolar geometry according to an optimization of an energy relationship between an epipolar model and the generated vector field values. The mobile radiography apparatus is calibrated according to the associated model epipolar geometry. At least a portion of the tomosynthesis image is reconstructed and displayed.Type: GrantFiled: July 6, 2018Date of Patent: April 28, 2020Assignee: Carestream Health, Inc.Inventors: Levon O. Vogelsang, Lawrence A. Ray, Richard A. Simon
-
Patent number: 10628850Abstract: A favorable merging or grouping of simply connected regions into which the array of information samples is sub-divided, is coded with a reduced amount of data. To this end, a predetermined relative locational relationship is defined enabling an identifying, for a predetermined simply connected region, of simply connected regions within the plurality of simply connected regions which have the predetermined relative locational relationship to the predetermined simply connected region. Namely, if the number is zero, a merge indicator for the predetermined simply connected region may be absent within the data stream. In other embodiments, spatial sub-division is performed depending on a first subset of syntax elements, followed by combining spatially neighboring simply connected regions depending on a second subset of syntax elements, to obtain an intermediate sub-division.Type: GrantFiled: February 5, 2019Date of Patent: April 21, 2020Assignee: GE VIDEO COMPRESSION, LLCInventors: Philipp Helle, Simon Oudin, Martin Winken, Detlev Marpe, Thomas Wiegand
-
Patent number: 10628968Abstract: A system and method for determining an IR image offset and calibrating a depth sensing camera to account for the offset is provided. An RGB-D camera may image a checkerboard pattern at a known distance and location. The checkerboard pattern may be provided on a planar device, such as a board. A three-dimensional primitive shape may be placed at in a known location in relation to the checkerboard. Depth data may be obtained from the checkerboard with the primitive shape. As the system knows the actual depth of the primitive shape, a depth offset may be calculated from the returned depth information from the RGB-D camera. The system may determine the offset between the depth information and the color image. The offset may be taken into account to produce more accurate RGB-D images.Type: GrantFiled: December 5, 2018Date of Patent: April 21, 2020Assignee: TOYOTA RESEARCH INSTITUTE, INC.Inventors: Duy-Nguyen Ta-Huynh, Alexander Alspach, Naveen Suresh Kuppuswamy
-
Patent number: 10628648Abstract: Computerized methods and systems for locating barcodes applied to objects are provided. A method can receive a first image of a first barcode fragment applied to a first object captured at a first time and identify a first position of the first barcode fragment. The method can also receive a second image of a second barcode fragment captured at a second time and identify a second position of the second barcode fragment. The method can also predict a range of possible positions of the first barcode fragment at the second time based on a tracking model that tracks the first barcode fragment based on the first position, and determine that the first barcode fragment and the second barcode fragment correspond to the same barcode, if the second position is within the range of possible positions of the first barcode fragment at the second time.Type: GrantFiled: November 3, 2017Date of Patent: April 21, 2020Assignee: COGNEX CORPORATIONInventors: James A. Negro, Ivan Bachelder
-
Patent number: 10628686Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: GrantFiled: March 12, 2018Date of Patent: April 21, 2020Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky
-
Patent number: 10621435Abstract: Methods, systems, and apparatus for efficient image analysis. In some aspects, a system includes a camera configured to capture images, one or more environment sensors configured to detect movement of the camera, a data processing apparatus, and a memory storage apparatus in data communication with the data processing apparatus. The data processing apparatus can access, for each of a multitude of images captured by a mobile device camera, data indicative of movement of the camera at a time at which the camera captured the image. The data processing apparatus can also select, from the images, a particular image for analysis based on the data indicative of the movement of the camera for each image, analyze the particular image to recognize one or more objects depicted in the particular image, and present content related to the one or more recognized objects.Type: GrantFiled: February 9, 2018Date of Patent: April 14, 2020Assignee: Google LLCInventors: Matthew J. Bridges, Alessandro Fin, Hartwig Adam, Jeffrey M. Gilbert
-
Patent number: 10621614Abstract: A favorable merging or grouping of simply connected regions into which the array of information samples is sub-divided, is coded with a reduced amount of data. To this end, a predetermined relative locational relationship is defined enabling an identifying, for a predetermined simply connected region, of simply connected regions within the plurality of simply connected regions which have the predetermined relative locational relationship to the predetermined simply connected region. Namely, if the number is zero, a merge indicator for the predetermined simply connected region may be absent within the data stream. In other embodiments, spatial sub-division is performed depending on a first subset of syntax elements, followed by combining spatially neighboring simply connected regions depending on a second subset of syntax elements, to obtain an intermediate sub-division.Type: GrantFiled: October 12, 2012Date of Patent: April 14, 2020Assignee: GE VIDEO COMPRESSION, LLCInventors: Philipp Helle, Simon Oudin, Martin Winken, Detlev Marpe, Thomas Wiegand
-
Patent number: 10612951Abstract: An optical flow sensing method includes: using an image sensor to capture images; using a directional-invariant filter device upon at least one first block of the first image to process values of pixels of the at least one first block of the first image, to generate a first filtered block image; using the first directional-invariant filter device upon at least one first block of the second image to process values of pixels of the at least one first block of the second image, to generate a second filtered block image; comparing the filtered block images to calculate a correlation result; and estimating a motion vector according to a plurality of correlation results.Type: GrantFiled: May 31, 2017Date of Patent: April 7, 2020Assignee: PixArt Imaging Inc.Inventors: Hsin-Chia Chen, Sen-Huang Huang, Wei-Chung Wang, Chao-Chien Huang, Ting-Yang Chang, Chun-Wei Chen
-
Patent number: 10614559Abstract: A decamouflaging method includes: obtaining image representing a scene including a multispectral image including components in the spectral domain ranging from the visible domain to the short-wavelength infrared and a thermal image including a component in the medium infrared and/or the long-wavelength infrared; extracting a sub-part (“window”) from each of the images obtained at a given position; applying a contrast accentuation procedure to the window extracted from the multispectral image allowing an improved window to be obtained where contrast between pixels corresponding to the object and pixels not corresponding to the object is accentuated; forming a multicomponent window, the improved window obtained and the window extracted from the thermal image each supplying a component of the multicomponent window; and applying the procedure to the multicomponent window; generating an image by inserting the improved window obtained by applying the procedure to the multicomponent window in a receiving image repreType: GrantFiled: November 10, 2016Date of Patent: April 7, 2020Assignee: SAFRAN ELECTRONICS & DEFENSEInventors: Nicolas Roux, Philippe Foubert, Thierry Touati, Marc Bousquet
-
Patent number: 10600189Abstract: Determining a movement of an object may include obtaining an event stream corresponding to a scene over time, wherein the event stream includes events associated with detected changes in brightness, wherein each event includes a pixel location, a timestamp, and a brightness indication; selecting a first subset of pixels from the plurality of pixels corresponding to an object for a first time period; determining a first movement of the object based on the brightness indications and timestamps for the first subset of pixels; determining that the first movement is insufficient to generate a velocity measure; selecting, based on the first movement, a second subset of pixels associated with the object for a second time period; determining an updated movement of the object based on the brightness indications and timestamps for the second subset of pixels and the first movement; and generating a velocity measure based on the updated movement.Type: GrantFiled: August 13, 2019Date of Patent: March 24, 2020Assignee: Apple Inc.Inventor: Raffi A. Bedikian
-
Patent number: 10599912Abstract: Spoofed faces are unlikely to reflect a likeness detection image in the same manner as live faces. To determine likeness of a subject face, a likeness detection image is displayed on a screen of a face recognition device in the direction of the subject face, and a reflection image of the subject face is captured while the likeness detection image is displayed. The reflection image is analyzed to determine whether the reflection image contains any reflections of the likeness detection image, and a likeness determination is made based on the location and/or character of any such reflections.Type: GrantFiled: July 18, 2017Date of Patent: March 24, 2020Assignee: AWARE, INC.Inventors: David Benini, Louis Scott Hills, Taras Riopka
-
Patent number: 10582850Abstract: An OCT motion contrast data acquisition method using an optical coherence tomography device includes: controlling an optical scanner for scanning measurement light on a test subject; performing a first scanning control for obtaining a first OCT signal group including at least four temporally different OCT signals at a same scanning position; performing a second scanning control for obtaining a second OCT signal group including at least four temporally different OCT signals at the same scanning position; obtaining first motion contrast data based on the first OCT signal group obtained in the first scanning control; obtaining second motion contrast data based on the second OCT signal group obtained in the second scanning control; and obtaining third motion contrast data based on the first motion contrast data and the second motion contrast data.Type: GrantFiled: June 15, 2017Date of Patent: March 10, 2020Assignee: NIDEK CO., LTD.Inventors: Norimasa Satake, Yukihiro Higuchi
-
Patent number: 10587795Abstract: A method of recoding a photograph for use in a personal photo identification document such as a passport includes using a digital image capture system, including a digital camera, a computer processor, and memory to store specifications and requirements for a photo print in order to be compliant for use in a user selected photo ID such as a passport for a selected country or jurisdiction, using the digital image capture system to capture a facial image, using facial image processing techniques to provide automatic detection of a face and facial feature points on the facial image, processing the facial image and generating a visual indication of compliance, and when compliant, generating the photograph based on the compliant facial image.Type: GrantFiled: November 13, 2018Date of Patent: March 10, 2020Assignee: KODAK ALARIS INC.Inventors: Peter Stubler, David Kloosterman, Joseph A. Manico
-
Patent number: 10581773Abstract: A user is prompted to select a social site for generating a voice enabled social artifact. A user selection of the social site is received. Responsive to receiving the user selection, information associated with an account of the user on the social site is obtained. The user is prompted to select a social artifact associated with the social site for voice enablement. A user selection of the social artifact is received. The selected social artifact is configured for voice enablement. The selected social artifact is displayed on the social site with an indication that the selected social artifact is voice enabled.Type: GrantFiled: February 14, 2018Date of Patent: March 3, 2020Inventors: Ahmed Tewfik Bouzid, David James Rennyson, Michael Jerry Saylor
-
Patent number: 10580158Abstract: Systems, devices, and methods are described for generating dense depth estimates, and confidence values associated with such depth estimates, from image data. A machine learning algorithm can be trained using image data and associated depth values captured by one or more LIDAR sensors providing a ground truth. When the algorithm is deployed in a machine vision system, image data and/or depth data can be used to determine dense depth estimates for all pixels of the image data, as well as confidence values for each depth estimate. Such confidence values may be indicative of how confident the machine learned algorithm is of the associated depth estimate.Type: GrantFiled: November 3, 2017Date of Patent: March 3, 2020Assignee: Zoox, Inc.Inventors: Arsalan Mousavian, James William Vaisey Philbin
-
Patent number: 10565724Abstract: A method for tracking a position of a device is provided, wherein the method includes capturing, at a first positional resolution, based on information from a first sensor, a first position of the device within an optical tracking zone of the first sensor. The method also includes determining, based on information from the first sensor, that the device exits the optical tracking zone of the first sensor. Further, the method includes responsive to determining that the device exits the optical tracking zone of the first sensor, capturing, at a second positional resolution, a second position of the device based on acceleration information from a second sensor, wherein the second positional resolution corresponds to a minimum threshold value for the acceleration information from the second sensor.Type: GrantFiled: December 26, 2017Date of Patent: February 18, 2020Assignee: Samsung Electronics Co., Ltd.Inventor: Christopher A. Peri
-
Patent number: 10552707Abstract: Pixel values may be obtained for a scene at two or more exposure levels, each exposure level corresponding to at least one of an exposure time interval different from that of another exposure level or an applied gain different from that of another exposure level. The pixel values may be aggregated into superpixel values, wherein each of the superpixel values includes a plurality of pixel values. A background model corresponding to each exposure level may be obtained. The superpixel values corresponding to each exposure level may be compared with the background model corresponding to each exposure level, to obtain an image change detection result for each exposure level. The image change detection results for each exposure level may be aggregated to obtain a combined image change detection result. A region of interest and/or a background region for the scene may be determined according to the combined image change detection result.Type: GrantFiled: December 7, 2017Date of Patent: February 4, 2020Assignee: QUALCOMM IncorporatedInventor: Edwin Chongwoo Park
-
Patent number: 10549426Abstract: Movement of a poly-articulated object, having a plurality of segments linked by at least one articulation, is estimated. Inertial measurements are obtained from capture modules that are fixed relative to respective segments, each module having an accelerometer and a gyrometer, with the measurements being expressed in a measurement reference frame that is fixed relative to the respective segment. The measurements are used to determine at least one stress vector external to the object so as to control a physical model of this object representing the object. Kinematic quantities associated with the segments of the object are then estimated using fundamental dynamics principles using the computed stress vector(s).Type: GrantFiled: December 10, 2013Date of Patent: February 4, 2020Assignees: Commissariat A L'Energie Atomique et aux Energies Alternatives, MOVEAInventors: Boris Moriniere, Claude Andriot
-
Patent number: 10547785Abstract: A photographing method includes: collecting, by a terminal device, data of M image frames of a photographed object, and processing the data of the M image frames to obtain M image frames; when collecting data of each of the M image frames of the photographed object, obtaining angular acceleration of the terminal device in an X-axis direction, a Y-axis direction, and a Z-axis direction; processing—the obtained angular acceleration in a period corresponding to the data of each image frame into shake information; selecting—one image frame from the M image frames as a reference image, performing registration on each of (M?1) image frames based on the reference image, the shake information, and a preset motion vector table, and performing fusion on the registered images; and displaying the compressed image.Type: GrantFiled: March 31, 2015Date of Patent: January 28, 2020Assignee: Huawei Technologies Co., Ltd.Inventor: Gang Chen
-
Patent number: 10546391Abstract: Provided is an apparatus for generating an around view. The apparatus includes a capture unit configured to capture images in front of, behind, to the left of, and to the right of a vehicle using cameras, a mask generation unit configured to set a region ranging a predetermined distance from the vehicle in the captured image as a mask region, a feature point extraction unit configured to extract ground feature points from the mask region of each of the captured images; a camera attitude angle estimation unit configured to generate a rotation matrix including a rotation angle of the camera using the extracted feature points; and an around view generation unit configured to rotationally convert the captured images to a top-view image using the rotation matrix.Type: GrantFiled: June 29, 2017Date of Patent: January 28, 2020Assignee: Hyundai Mobis Co., Ltd.Inventor: Seong Soo Lee
-
Patent number: 10529075Abstract: This disclosure relates generally to computer vision, and more particularly to method and system for tracking objects within a video. In one embodiment, a method for tracking objects within a video is disclosed. The method includes receiving one or more regions of interest (ROIs) corresponding to one or more objects in an initial frame of the video, extracting a set of scale and rotation invariant interest data points in each of the ROIs, clustering the set of scale and rotation invariant interest data points in a ROI into a set of clusters based on corresponding locations in the ROI, determining an optimal set of interest data points from each of the set of clusters based on corresponding feature response values and spread values, and initiating tracking of the optimal set of interest data points in subsequent frames of the video to track the one or more objects in the video.Type: GrantFiled: March 15, 2018Date of Patent: January 7, 2020Assignee: Wipro LimitedInventor: Ghulam Mohiuddin Khan
-
Patent number: 10524663Abstract: Methods and apparatus for assessing and correcting phase variations and motion artifacts in a coherent tomogram of a sample. Coherent techniques are used scan a broadband optical beam across a sample in a specified scan pattern and to acquire a cube of complex data constituting a full tomogram. Generalized motion of the sample is then quantified based at least on a phase variation measured during the course of scanning the broadband optical beam in the specified scan pattern. Generalized motion includes both actual motion and apparent motion due to organized variation of some physical parameter such as temperature. Intensity structure of speckle imaged during the course of coherently acquiring the full tomograpm may be used to correct for motion of the sample in a plane transverse to a depth axis along the incident beam.Type: GrantFiled: June 17, 2016Date of Patent: January 7, 2020Assignee: The Board of Trustees of the University of IllinoisInventors: Stephen A. Boppart, Paul Scott Carney, Nathan Shemonski
-
Patent number: 10521247Abstract: Techniques are disclosed for advantageously relocating graphical digital content on a screen of a client device. The technique can include displaying a dynamic content at a particular location on the screen of a client device (e.g., inline with an article displayed on a webpage). Upon determination that a relocation condition exists (e.g., a viewability of the inline dynamic content drops below a particular threshold), the dynamic content can be relocated to another location on the screen. In some instances, rather than being relocated to a static, previously determined position, the dynamic content can be dynamically relocated, based on the location of the other content.Type: GrantFiled: November 22, 2016Date of Patent: December 31, 2019Assignee: XANDR INC.Inventors: Jeffrey Weiss, Vikki Pitts, Alexander Krassel, Radhika Shivapurkar, Kyungsuk Song
-
Patent number: 10509954Abstract: A system, article, and method of image segmentation refinement for image processing.Type: GrantFiled: February 10, 2016Date of Patent: December 17, 2019Assignee: Intel CorporationInventor: Gilad Baruch
-
Patent number: 10499867Abstract: The present disclosure relates to a method, storage medium, and system for analyzing an image sequence of a periodic physiological activity. In one implementation, the method includes receiving the image sequence acquired by an imaging device, the image sequence having a plurality of frames and determining local motions for pixels in each frame of the image sequence. The local motion for a pixel may be determined using corresponding pixels in frames adjacent to the frame to which the pixel belongs. The method further includes determining principal motions for the plurality of frames based on the local motions; determining a motion magnitude profile based on the principal motions; and determining the phase of each frame in the image sequence based on the motion magnitude profile.Type: GrantFiled: January 8, 2018Date of Patent: December 10, 2019Assignee: SHENZHEN KEYA MEDICAL TECHNOLOGY CORPORATIONInventors: Xiaoxiao Liu, Shubao Liu, Bin Ma, Kunlin Cao, Youbing Yin, Yuwei Li, Qian Zhao, Qi Song
-
Patent number: 10503245Abstract: Methods and systems for relative inertial measurement may include a user device configured to couple with a user's body and measure motion of the user's body or a part of the user's body while the user rides in a vehicle. A second inertial measurement device may be configured to move with the vehicle but to not move with movements of the user's body within the vehicle. One or more processors may receive inertial measurements from the first and second inertial measurement devices and determine movement of the user's body or the part of the user's body relative to the vehicle by comparing the received inertial measurements.Type: GrantFiled: September 21, 2016Date of Patent: December 10, 2019Assignee: Apple Inc.Inventor: Fletcher R. Rothkopf
-
Patent number: 10497120Abstract: The present disclosure illustrates a method and an apparatus of fiber tracking, and non-transitory computer-readable medium thereof. In an embodiment, a fiber tracking process is performed on a diffusion magnetic resonance image of a subject's brain based on validated and better tracking parameters, so as to obtain first tracking images, nerve fibers between two first regions of interest in each of the first tracking images are extracted, a nerve fasciculus skeleton is established based on an overlapping process performed on the plurality of nerve fibers extracted from the first tracking images, and the nerve fibers more similar to the structure of the nerve fasciculus skeleton are selected to obtain a specific fasciculus of the subject. Thus, the technical solution of the present disclosure can be used to improve the sensitivity of fiber tracking and be useful for improvement of preoperative assessment and surgical navigation.Type: GrantFiled: April 15, 2018Date of Patent: December 3, 2019Assignee: NATIONAL YING-MING UNIVERSITYInventors: Ching-Po Lin, Shin-Tai Chong, Chun-Yi Lo, Chu-Chung Huang
-
Patent number: 10489820Abstract: A favorable merging or grouping of simply connected regions into which the array of information samples is sub-divided, is coded with a reduced amount of data. To this end, a predetermined relative locational relationship is defined enabling an identifying, for a predetermined simply connected region, of simply connected regions within the plurality of simply connected regions which have the predetermined relative locational relationship to the predetermined simply connected region. Namely, if the number is zero, a merge indicator for the predetermined simply connected region may be absent within the data stream. In other embodiments, spatial sub-division is performed depending on a first subset of syntax elements, followed by combining spatially neighboring simply connected regions depending on a second subset of syntax elements, to obtain an intermediate sub-division.Type: GrantFiled: October 12, 2012Date of Patent: November 26, 2019Assignee: GE VIDEO COMPRESSION, LLCInventors: Philipp Helle, Simon Oudin, Martin Winken, Detlev Marpe, Thomas Wiegand
-
Patent number: 10482126Abstract: A content system identifies shots in a first video and shots in a second video. Shot durations are determined for the identified shots of each video. A histogram is generated for each video, each histogram dividing the identified shots of the corresponding video into a set of buckets divided according to a range of shot durations. The system determines confidence weights for the buckets of each histogram, with the confidence weight for a bucket based on a likelihood of a particular number of identified shots occurring within the range of shot duration for that bucket. A correlation value is computed for the two videos based on a number of identified shots in each bucket of each respective histogram and based on the confidence weights. The content system determines whether the two videos are similar based on the correlation value and a self-correlation value of each video.Type: GrantFiled: November 30, 2016Date of Patent: November 19, 2019Assignee: Google LLCInventors: Yongzhe Wang, Anthony Mai
-
Patent number: 10475216Abstract: An imaging system determines a heart rate of a patient, a cardiac disease state, and/or a target cardiac anatomy of the patient. The system calculates an image acquisition time range from a patient population model using the heart rate, the cardiac disease state, and/or the target anatomy. The model represents relationships between cardiac motion of other patients and time or cardiac phases of the other patients. The system also determines imaging settings to acquire image data of the target anatomy during the image acquisition time range that is calculated. Imaging the target anatomy of the patient according to the imaging settings generates image data of the target anatomy having less cardiac motion and/or a reduced image acquisition time range relative to determining the imaging settings without using the patient population model.Type: GrantFiled: February 26, 2018Date of Patent: November 12, 2019Assignee: General Electric CompanyInventors: John Irvin Jackson, John Londt, Eric Gros, Dave Chevalier
-
Patent number: 10477200Abstract: A camera system captures images from a set of cameras to generate binocular panoramic views of an environment. The cameras are oriented in the camera system to maximize the minimum number of cameras viewing a set of randomized test points. To calibrate the system, matching features between images are identified and used to estimate three-dimensional points external to the camera system. Calibration parameters are modified to improve the three-dimensional point estimates. When images are captured, a pipeline generates a depth map for each camera using reprojected views from adjacent cameras and an image pyramid that includes individual pixel depth refinement and filtering between levels of the pyramid. The images may be used generate views of the environment from different perspectives (relative to the image capture location) by generating depth surfaces corresponding to the depth maps and blending the depth surfaces.Type: GrantFiled: April 18, 2017Date of Patent: November 12, 2019Assignee: Facebook, Inc.Inventors: Michael John Toksvig, Forrest Samuel Briggs, Brian Keith Cabral
-
Patent number: 10467729Abstract: A method and system for a deep learning-based approach to image processing to increase a level of optical zooming and increasing the resolution associated with a captured image. The system includes an image capture device to generate a display of a field of view (e.g., of a scene within a viewable range of a lens of the image capture device). An indication of a desired zoom level (e.g., 1.1× to 5×) is received, and, based on this selection, a portion of the field of view is cropped. In one embodiment, the cropped portion displayed by the image capture device for a user's inspection, prior to the capturing of a low resolution image. The low resolution image is provided to an artificial neural network trained to apply a resolution up-scaling model to transform the low resolution image to a high resolution image of the cropped portion.Type: GrantFiled: October 12, 2017Date of Patent: November 5, 2019Assignee: Amazon Technologies, Inc.Inventors: Pramuditha Hemanga Perera, Gurumurthy Swaminathan, Vineet Khare
-
Patent number: 10467737Abstract: A method for adjusting grayscale values of an image includes: for each pixel in the image, calculating a first mapping value for a grayscale value of the pixel in the image through a histogram equalization mapping function; calculating a second mapping value by subtracting a first preset value from the grayscale value of the pixel through the histogram equalization mapping function, and when the result exceeds a preset grayscale range, selecting a minimum value of the preset grayscale range for calculating the second mapping value; calculating a third mapping value by adding a second preset value to the grayscale value of the pixel through the histogram equalization mapping function and when the result exceeds the preset grayscale range, selecting a maximum value of the preset grayscale range; and calculating an output grayscale value of the pixel based on the first, second, and third mapping value and respective weights.Type: GrantFiled: June 20, 2017Date of Patent: November 5, 2019Assignee: BOE TECHNOLOGY GROUP CO., LTD.Inventors: Pablo Navarrete Michelini, Han Yan, Ran Duan
-
Patent number: 10462354Abstract: A control system for a vehicle includes a camera module having a plurality of cameras. A control is operable to adjust a field of view of the cameras responsive to an input. When the vehicle is traveling in and along a traffic lane, the control sets the field of view of at least some of the cameras forward through the vehicle windshield. Responsive to an input indicative of an intended lane change, the control adjusts at least one camera to set the field of view of the camera toward an exterior rearview mirror at the side of the vehicle at which the target lane is located. Responsive to determination, via processing of captured image data when the camera views the exterior rearview mirror of the vehicle, that the target lane is clear, the control controls the at least one vehicle control system to maneuver the vehicle into the target lane.Type: GrantFiled: December 6, 2017Date of Patent: October 29, 2019Assignee: MAGNA ELECTRONICS INC.Inventor: Krishna Koravadi
-
Patent number: 10460344Abstract: A favorable merging or grouping of simply connected regions into which the array of information samples is sub-divided, is coded with a reduced amount of data. To this end, a predetermined relative locational relationship is defined enabling an identifying, for a predetermined simply connected region, of simply connected regions within the plurality of simply connected regions which have the predetermined relative locational relationship to the predetermined simply connected region. Namely, if the number is zero, a merge indicator for the predetermined simply connected region may be absent within the data stream. In other embodiments, spatial sub-division is performed depending on a first subset of syntax elements, followed by combining spatially neighboring simply connected regions depending on a second subset of syntax elements, to obtain an intermediate sub-division.Type: GrantFiled: November 20, 2018Date of Patent: October 29, 2019Assignee: GE VIDEO COMPRESSION, LLCInventors: Philipp Helle, Simon Oudin, Martin Winken, Detlev Marpe, Thomas Wiegand
-
Patent number: 10452999Abstract: A method of generating a confidence measure for an estimation derived from images captured by a camera mounted on a vehicle includes: capturing consecutive training images by the camera while the vehicle is moving; determining ground-truth data for the training images; computing optical flow vectors from the training images and estimating a first output signal based on the optical flow vectors for each of the training images, the first output signal indicating an orientation of the camera; classifying the first output signal for each of the training images as a correct signal or a false signal depending on how good the first output signal fits to the ground-truth data; determining optical flow field properties for each of the training images derived from the training images; and generating a separation function that separates the optical flow field properties into two classes based on the classification of the first output signal.Type: GrantFiled: March 23, 2017Date of Patent: October 22, 2019Assignee: APTIV TECHNOLOGIES LIMITEDInventors: Stephanie Lessmann, Mirko Meuter, Jens Westerhoff
-
Patent number: 10430964Abstract: An image processing device includes a predicted position calculator configured to predict a current position of a target object, an obtained image analyzer configured to search for a position of the target object from a predetermined region that is a partial region of a captured image and that includes a position predicted by the predicted position calculator, and an analysis result outputting unit configured to output the position of the target object retrieved by the obtained image analyzer.Type: GrantFiled: October 18, 2017Date of Patent: October 1, 2019Assignee: OMRON CorporationInventors: Yuki Taniyasu, Gaku Shiramizu
-
Patent number: 10430671Abstract: A system and method for remapping surface areas of vehicle environment that include receiving a plurality of images of the surface areas of the vehicle environment from a computing device. The system and method also include evaluating the plurality of images to determine an optical flow value associated with at least one pixel of at least two images of the plurality of images. The system and method additionally include determining at least one surface area that includes an external environment of the vehicle. The system and method further include remapping the surface areas by filtering the at least one surface area from which the external environment is captured.Type: GrantFiled: April 22, 2017Date of Patent: October 1, 2019Assignee: Honda Motor Co., Ltd.Inventors: John P. Moon, Robert Wesley Murrish
-
Patent number: 10431095Abstract: The present invention extends to methods, systems, and computer program products for formulating lane level routing plans. In general, aspects of the invention are used in motorized vehicles to guide a driver to a terminal vehicle configuration according to a lane level routing plan that balances travel time with routing plan robustness. A lane level routing plan can be based on terminal guidance conditions (e.g., exiting a highway in the correct off ramp lane), statistical patterns of lanes themselves, current vehicle state, and state of the local environment near the vehicle. Lane level routing plans can be communicated to the driver with audio, visual, and/or haptic cues. Lane level routing plans can be revised online and in (essentially) real-time in response to changing conditions in the local environment (e.g., a trailing vehicle in a neighboring lane has decided to increase speed).Type: GrantFiled: June 7, 2017Date of Patent: October 1, 2019Assignee: FORD GLOBAL TECHNOLOGIES, LLCInventors: Jinesh J Jain, Daniel Levine