Combining Image Portions (e.g., Portions Of Oversized Documents) Patents (Class 382/284)
  • Patent number: 10297082
    Abstract: Various technologies pertaining to shared spatial augmented reality (SSAR) are described. Sensor units in a room output sensor signals that are indicative of positions of two or more users in the room and gaze directions of the two or more users. Views of at least one virtual object are computed separately for each of the two or more users, and projectors project such views in the room. The projected views cause the two or more users to simultaneously perceive the virtual object in space.
    Type: Grant
    Filed: April 9, 2015
    Date of Patent: May 21, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Andrew D. Wilson, Hrvoje Benko
  • Patent number: 10282439
    Abstract: The present disclosure relates to methods and systems for storing and querying data. According to the embodiments of the present invention, two-layer indexes are created for multi-dimension data, wherein the primary index is created based on two or more dimensions to retrieve respective data units of the data, while the secondary index is created based on specific dimensions to retrieve respective data blocks in the data unit. Correspondingly, when receiving a multi-dimension query request for data, the primary retrieval first determines a data unit including the target data based on a primary index, and then the secondary retrieval quickly locates a data block including the target data based on the secondary index. In this way, the multi-dimension retrieval can be efficiently performed. Moreover, by appropriately setting the size of a smallest data block, the I/O efficiency of data access will be significantly enhanced.
    Type: Grant
    Filed: May 15, 2015
    Date of Patent: May 7, 2019
    Inventors: Xiao Yan Chen, Yao Liang Chen, Sheng Huang, Kai Liu, Wei Lu, Xiao Min Xu
  • Patent number: 10275934
    Abstract: A video rendering system includes a field-of-view detector, a display, and a computing platform including a hardware processor and a memory storing a multi-viewpoint video rendering software code. The hardware processor executes the multi-viewpoint video rendering software code to parameterize visible surfaces in a scene to define multiple texels for each visible surface, precompute one or more illumination value(s) for each texel of each visible surface, and for each texel of each visible surface, store the illumination value(s) in a cache assigned to the texel. In addition, the multi-viewpoint video rendering software code receives a perspective data from the field-of-view detector identifying one of multiple permissible perspectives for viewing the scene, and renders the scene on the display in real-time with respect to receiving the perspective data, based on the identified perspective and using one or more of the illumination value(s) precomputed for each texel of each visible surface.
    Type: Grant
    Filed: December 20, 2017
    Date of Patent: April 30, 2019
    Assignee: Disney Enterprises, Inc.
    Inventors: Jan Novak, Christopher Schroers, Fabrice Pierre Armand Rousselle, Matthias Fauconneau, Alexander Sorkine Hornung
  • Patent number: 10275899
    Abstract: An optical navigation system comprising a camera oriented to face towards a plurality of markers located at spaced apart locations from the camera, calculating means adapted to calculate an angle subtended between pairs of markers, the subtended angles being calculated by monitoring the pixel locations of the markers in a series of images captured by the camera, the optical navigation system additionally comprising means for creating a three-dimensional model whereby the location of the camera relative to the markers is determined by triangulating the subtended angles in the three-dimensional model.
    Type: Grant
    Filed: March 3, 2014
    Date of Patent: April 30, 2019
    Assignee: Mo-Sys Engineering Limited
    Inventors: Michael Paul Alexander Geissler, Martin Peter Parsley
  • Patent number: 10269128
    Abstract: An image processing device includes: one or more detectors that respectively receive reference images, and each detect, for each pixel in the reference image, a displacement relative to a base image; one or more generators that respectively receive the reference images, and each generate an aligned image by, for each pixel in the reference image, moving the pixel according to the displacement for the pixel and assigning a grayscale value of the pixel to a pixel position closest to the moved pixel; and a combiner that takes each pixel in the base image as a pixel of interest and calculates a grayscale value of a pixel at the same position as the pixel of interest in a combined image by weighting and summing grayscale values of the pixel of interest and pixels at the same position as the pixel of interest in the aligned images.
    Type: Grant
    Filed: February 16, 2016
    Date of Patent: April 23, 2019
    Inventors: Yoshitaka Toyoda, Toshiki Fujino, Kohei Kurihara, Narihiro Matoba
  • Patent number: 10250773
    Abstract: An image reading device includes: light receiving sensors configured to read an image of a document conveyed in a sub-scanning direction and be arranged with an interval in a main scanning direction; one pair of document conveying rollers configured to be provided in front and back of the light receiving sensors in a document conveying direction; a detection unit configured to detect an image overlap amount in an image overlap area and/or an image missing amount in an image missing area; an adjustment amount determination unit configured to determine an adjustment amount for adjusting a distance between the document and the light receiving sensors based on the image overlap amount and/or image missing amount detected; and a drive unit configured to adjust a distance between the document and the light receiving sensors by displacing one of the document conveying rollers and light receiving sensors according to the adjustment amount.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: April 2, 2019
    Assignee: KONICA MINOLTA, INC.
    Inventor: Hiroyuki Suzuki
  • Patent number: 10244259
    Abstract: A method and apparatus of three-dimensional/multi-view coding using aligned reference information are disclosed. The method operates by receiving input data associated with a current block of a current frame in a dependent view, determining a first DV (Disparity Vector) from one or more neighboring blocks of the current block, wherein the first DV refers to a first reference view to derive first reference information, selecting a second reference view for the current block to derive second reference information, aligning the first reference information associated with the first reference view with the second reference information associated with the second reference view, and applying inter-view encoding or decoding to the input data utilizing the first DV or the second reference information after applying said aligning the first reference information with the second reference information.
    Type: Grant
    Filed: January 12, 2018
    Date of Patent: March 26, 2019
    Inventors: Jicheng An, Kai Zhang, Jian-Liang Lin
  • Patent number: 10242035
    Abstract: A real-time reverse image searching for images analogous to a frame having patterns, performed using a processor connected to a network and having access to digital libraries warehousing a plurality of vectors and respective images/videos associated with each of the plurality of vectors, including: calculating representations for each of the patterns in the frame to form a vector, the representations corresponding to dimensions of the vector; reducing a size of the vector by reducing a number of the dimensions to one of about 8% and a maximum trade-off between the quality of the image and the size of vector; detecting, in the digital libraries, of the plurality of vectors that are most similar to the vector of the frame; and offering, in real-time via the network, images/videos associated with the selected of the plurality of vectors, wherein a number of the offered images and videos is pre-determined.
    Type: Grant
    Filed: September 18, 2018
    Date of Patent: March 26, 2019
    Assignee: POND5, INC.
    Inventors: Carl Asman, Jonas Persson, Marcus Engene
  • Patent number: 10217232
    Abstract: System, methods, and other embodiments described herein relate to locally aligning features within a map. In one embodiment, a method includes segmenting map data that forms the map using a first grid to divide the map into a first set of tiles and a second grid to divide the map into a second set of tiles that are offset and overlap the first set of tiles. The method includes analyzing neighbor tiles in relation to a patch tile based, at least in part, on shared features between the patch tile and the neighbor tiles to identify external misalignments between one or more of the neighbor tiles and the patch tile. The neighbor tiles are from a different one of the first grid and the second grid. The method includes adjusting alignment of the neighbor tiles within the map according to the external misalignments for the neighbor tiles.
    Type: Grant
    Filed: February 8, 2017
    Date of Patent: February 26, 2019
    Assignee: Toyota Motor Engineering & Manufacturing North America, Inc.
    Inventor: Masahiro Harada
  • Patent number: 10210603
    Abstract: A store profile generation system includes a mobile base and an image capture assembly mounted on the base. The assembly includes at least one image capture device for acquiring images of product display units in a retail environment. A control unit acquires the images captured by the at least one image capture device at a sequence of locations of the mobile base in the retail environment. The control unit extracts product-related data from the acquired images and generates a store profile indicating locations of products and their associated tags throughout the retail environment, based on the extracted product-related data. The store profile can be used for generating new product labels for a sale in an appropriate order for a person to match to the appropriate locations in a single pass through the store.
    Type: Grant
    Filed: October 17, 2016
    Date of Patent: February 19, 2019
    Assignee: Conduent Business Services LLC
    Inventors: Dennis L. Venable, Wencheng Wu, Thomas F. Wade, Ethan Shen, Charles D. Rizzolo
  • Patent number: 10205878
    Abstract: An image processing apparatus configured to generate a panoramic image by combining a plurality of images includes a first acquirer configured to acquire information of a first moving amount of the image based on a common area of the plurality of images, and an aligner configured to align the plurality of images based on difference information between the first moving amount and a second moving amount of the image acquired based on position information of an image-capturing apparatus configured to capture the plurality of images, and information of the second moving amount.
    Type: Grant
    Filed: December 2, 2016
    Date of Patent: February 12, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Tohru Ishibashi
  • Patent number: 10204398
    Abstract: An image distortion transformation method for transforming an original image by an imager having an original distortion profile to a transformed image optimized for a distortion processing unit includes inputting the original image from the imager into the transformation unit, inputting an original image distortion profile into the original distortion profile memory of the transformation unit, and inputting a target distortion profile into the target distortion profile memory of the transformation unit. The target distortion profile is different from the original distortion profile. The method further includes transforming the original image into a transformed image by transforming the distortion profile of the original image from the original image distortion profile to the target image distortion profile, and outputting the transformed image from the transformation unit.
    Type: Grant
    Filed: February 16, 2017
    Date of Patent: February 12, 2019
    Assignee: 6115187 Canada, Inc.
    Inventors: Patrice Roulet, Xiaojun Du, Jocelyn Parent, Pierre Konen, Simon Thibault, Pascale Nini, Valentin Bataille, Jhinseok Lee, Hu Zhang
  • Patent number: 10187582
    Abstract: Disclosed are an infrared camera and an infrared lamp brightness adjustment method therefore. The method comprises: when an infrared lamp of an infrared camera is turned on, conducting following processing at a pre-set time period: determining whether there is at least one sub-region with abnormal brightness in N sub-regions of the same size, which constitute a monitoring picture, where N is a positive integer which is greater than 1; and if so, according to a pre-determined parameter of the acquired at least one sub-region with abnormal brightness and a pre-determined parameter of the monitoring picture, determining an infrared lamp adjustment manner, and according to the determined infrared lamp adjustment manner, conducting infrared lamp brightness adjustment so that the at least one sub-region with the abnormal brightness is recovered to be normal. By means of the solution of the present invention, the picture of the monitoring picture can be improved.
    Type: Grant
    Filed: January 6, 2015
    Date of Patent: January 22, 2019
    Assignee: Hangzhou Hikvision Digital Technology Co., Ltd.
    Inventor: Yuming Wang
  • Patent number: 10179543
    Abstract: A dynamic image stitching system for stitching images captured by multiple cameras of a vision system of a vehicle includes a first camera disposed at a vehicle and having a first field of view exterior the vehicle and a second camera disposed at the vehicle and having a second field of view exterior the vehicle. The first and second fields of view at least partially overlap. A processor is operable to process image data captured by the first and second cameras. The processor processes captured image data to determine characteristics of features or objects present in the overlapping region of the first and second fields of view. The processor is operable to adjust a stitching algorithm responsive to a determination of a difference between a characteristic of a feature as captured by the first camera and the characteristic of the feature as captured by the second camera.
    Type: Grant
    Filed: February 27, 2014
    Date of Patent: January 15, 2019
    Inventors: Ghanshyam Rathi, Hilda Faraji, Nikhil Gupta, Christian Traub, Michael Schaffner, Goerg Pflug
  • Patent number: 10175492
    Abstract: A display device system providing augmented reality (AR) and virtual reality (VR) displays in the same device and a method for switching between augmented reality and virtual reality modes in the embodiments of the device are disclosed. The system enables users to view an augmented reality setting, interact with objects, and switch to a virtual reality setting or vice versa without having to switch devices. When switching from virtual reality to augmented reality, a shuttering mechanism may open allowing the user to see the real environment within an augmented setting. Position on the user in the physical reality may be tracked relative to position of the user in the AR or VR. Some actions may be triggered based on the tracked location and orientation of the user.
    Type: Grant
    Filed: November 1, 2017
    Date of Patent: January 8, 2019
    Assignee: EON REALITY, INC.
    Inventors: Erbo Li, Dan Lejerskar, Yazhou Huang, Jan Kjallstrom, Mats Johansson
  • Patent number: 10171690
    Abstract: A print-image generation device comprising: a display; and a processor that controls the display to display a print-image generation screen and a plurality of part images in the print-image generation screen, and performs alignment of at least one of the plurality of part images to generate a print image composed of the plurality of part images, wherein the processor, when the alignment is performed in a state in which two or more part images are selected from among the plurality of part images in the print-image generation screen, performs first alignment of the two or more part images on the basis of a mutual positional relationship between the two or more part images, determines whether or not there exists an area in which the two or more part images overlap each other as the result of the alignment, and when it is determined that there exists an area in which the two or more part images at least partially overlap each other, notifies a user that the overlapped area exists, and when the user is notified
    Type: Grant
    Filed: August 15, 2017
    Date of Patent: January 1, 2019
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Tatsuya Ueda
  • Patent number: 10154820
    Abstract: A method for a CT scan of a body part, wherein a marker is positioned on the body part. The method comprises: positioning a marker on the body part; performing a scout scan of the area which contains the body part, to acquire a scout image; detecting the marker in the scout image to acquire position information of the marker; and using the position information to navigate the CT scan.
    Type: Grant
    Filed: November 26, 2013
    Date of Patent: December 18, 2018
    Assignee: General Electric Company
    Inventors: Ping Liu, Jiaqin Dong, Hai Feng Wu, Meng Zhang
  • Patent number: 10148884
    Abstract: According to one aspect, there is provided an apparatus comprising at least one processing unit and at least one memory. The at least one memory stores program instructions that, when executed by the at least one processing unit, cause the apparatus to obtain a set of captured still images captured with a camera, detect at least one face in the captured still images, and cause display of the detected at least one face on a display providing a live viewfinder feed of a scene to be captured as an additional display element while providing the live viewfinder feed on the display.
    Type: Grant
    Filed: July 29, 2016
    Date of Patent: December 4, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Mikko Kankainen, Jukka Miettinen
  • Patent number: 10148924
    Abstract: Each projection apparatus in a multi-projection system has a liquid crystal panel, a driving circuit configured to perform PWM control of the liquid crystal panel, and a projection image processing unit configured to perform edge blending processing to perform compositing display by each projection apparatus and processing to change gain properties of the edge blending processing by each projection apparatus. Synchronization of each projection apparatus is maintained by a synchronization circuit. Therefore, a sum of image gain in a region of image compositing by each projection apparatus is 1, and the position and image gain properties of the compositing region are changed for each frame, so the position of image deterioration changes for each frame.
    Type: Grant
    Filed: April 19, 2017
    Date of Patent: December 4, 2018
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hidetoshi Wada, Azusa Koike, Michihisa Yanagi
  • Patent number: 10148887
    Abstract: An imaging system 1 includes an imaging control device 10, an imaging device 20, and a light emitting device 30. The imaging control device 10 is provided for controlling the imaging device 20 and the light emitting device 30, and includes an evaluation unit 13, a light reception adjustment unit 14, and a light emission adjustment unit 15. The evaluation unit 13 evaluates respective brightnesses of the first image data and the second image data that are output from the imaging device 20. The light reception adjustment unit 14 adjusts any of an exposure time, a diaphragm value, and a gain that are to be used when the imaging device 20 captures an image, based on a brightness evaluation result. The light emission adjustment unit 15 causes the light emitting device 30 to emit light of either wavelength band of the first wavelength band and the second wavelength band, and adjusts a light emission intensity of the light, based on an evaluation result.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: December 4, 2018
    Inventors: Toshihiko Terada, Yoichi Tosaka, Tetsuji Uezono, Kazunori Suzuki
  • Patent number: 10133950
    Abstract: Various arrangements for tracking a target within a series of images is presented. The target may be detected within a first image at least partially based on a correspondence between the target and a stored reference template. A tracking template may be created for tracking the target using the first image. The target may be located within a second image using the tracking template.
    Type: Grant
    Filed: December 2, 2011
    Date of Patent: November 20, 2018
    Assignee: QUALCOMM Incorporated
    Inventor: Charles Wheeler Sweet, III
  • Patent number: 10127632
    Abstract: Implementations relate to display and update of panoramic image montages. In some implementations, a computer-implemented method includes causing one or more view portions of a panoramic image montage to be displayed in a display view of a display device. First user input is received at a first time while at least one of the one or more view portions of the panoramic image montage is displayed. In response to the first user input, an image feed is caused to be displayed, the image feed including a plurality of image frames captured by a camera. Second user input is received at a second time later than the first time while a particular view portion of the panoramic image montage is displayed in the display view. In response to the second user input, the particular view portion is updated based on the image feed.
    Type: Grant
    Filed: September 5, 2016
    Date of Patent: November 13, 2018
    Assignee: Google LLC
    Inventors: Ryan Burke, Troy Lumpkin, Daniel Motzenbecker, Brian K. Kehrer, Glenn Cochon
  • Patent number: 10108755
    Abstract: Various implementations include systems and methods for generating a radio frequency floor plan. The systems and methods include receiving map data for a map image. A user is provided with functionalities for generating a trace outline in the map image. Floor dimensions are determined from the trace outline in the map image. A blank floor plan is generated using the floor dimensions and the map image. Access point position data can be received that signifies the position of placed access points. Access point type data can be received that signifies the type of access points that are positioned. The access point position data, the access point type data, and the floor plan or blank floor plan can be used to generate a RF floor plan.
    Type: Grant
    Filed: November 19, 2013
    Date of Patent: October 23, 2018
    Assignee: Aerohive Networks, Inc.
    Inventors: David Flynn, Chris Scheers
  • Patent number: 10096154
    Abstract: Computer-implemented methods for detecting and characterizing surface depressions in a topographical landscape based on processing of high resolution digital elevation model data according to a local tree contour algorithm applied to an elevation contour representation of the landscape, and characterizing the detected surface depressions according to morphometric threshold values derived from data relevant to surface depressions of the topographical area. Non-transitory computer readable media comprising computer-executable instructions for carrying out the methods are also provided.
    Type: Grant
    Filed: April 4, 2017
    Date of Patent: October 9, 2018
    Assignee: University of Cincinnati
    Inventors: Hongxing Liu, Qiusheng Wu
  • Patent number: 10067327
    Abstract: To acquire a pasted image having an enlarged dynamic range and having a high quality and a high angle of view, an image acquisition apparatus includes an imaging unit that captures an object, to acquire an image, an imaging control unit that controls the imaging unit, an HDR processing unit that combines a plurality of partial images acquired by capturing the same region of the object under different exposures, to generate an HDR image having an enlarged dynamic range, a pasting processing unit that pastes the plurality of HDR images generated for different regions of the object, to acquire a pasted image having a higher angle of view, and an exposure setting unit that sets an exposure condition in capturing all the partial images based on image information acquired by capturing a wider range than the single partial image included in the pasted image.
    Type: Grant
    Filed: May 14, 2015
    Date of Patent: September 4, 2018
    Inventor: Masashi Okabe
  • Patent number: 10043315
    Abstract: The invention relates to a method for representing a virtual object in a real environment, having the following steps: generating a two-dimensional representation of a real environment by means of a recording device, ascertaining a position of the recording device relative to at least one component of the real environment, segmenting at least one area of the real environment in the two-dimensional image on the basis of non-manually generated 3D information for identifying at least one segment of the real environment in distinction to a remaining part of the real environment while supplying corresponding segmentation data, and merging the two-dimensional image of the real environment with the virtual object or, by means of an optical, semitransparent element directly with reality with consideration of the segmentation data. The invention permits any collisions of virtual objects with real objects that occur upon merging with a real environment to be represented in a way largely close to reality.
    Type: Grant
    Filed: July 8, 2016
    Date of Patent: August 7, 2018
    Assignee: Apple Inc.
    Inventors: Peter Meier, Stefan Holzer
  • Patent number: 10033925
    Abstract: A mobile terminal including a main body; a camera mounted in the main body and configured to capture an external environment; a display unit configured to display an image obtained by the camera in real time; a sensing unit configured to sense a motion of the main body while the camera is activated; a memory configured to store therein the image displayed on the display unit in response to a capture control command being applied; and a controller configured to generate a processed image formed by continuous images displayed on the display unit when the motion of the main body forms a continuous virtual track while displaying the image.
    Type: Grant
    Filed: November 9, 2015
    Date of Patent: July 24, 2018
    Inventors: Sungjin Kim, Taehoon Cho
  • Patent number: 10028711
    Abstract: A marker-coordinate detecting unit detects coordinates of a stent marker on a new image when the new image is stored in an image-data storage unit; and then a correction-image creating unit creates a correction image from the new image through, for example, image transformation processing, so as to match up the detected coordinates with reference coordinates that are coordinates of the stent marker already detected by the marker-coordinate detecting unit in a first frame. An image post-processing unit then creates an image for display by performing post-processing on the correction image created by the correction-image creating unit, the post-processing including high-frequency noise reduction filtering-processing, low-frequency component removal filtering-processing, and logarithmic-image creating processing; and then a system control unit performs control of displaying a moving image of an enlarged image of a set region that is set in the image for display, together with an original image.
    Type: Grant
    Filed: November 21, 2016
    Date of Patent: July 24, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Takuya Sakaguchi, Kyojiro Nambu, Hisato Takemoto
  • Patent number: 10031526
    Abstract: Described is a system (and method) for generating a driving scenario for an autonomous driving simulator. The system may use a camera mounted to a vehicle as a cost effective approach to obtain real-life driving scenario data. The system may then analyze the two-dimensional image data to create a three-dimensional driving simulation. The analysis may include detecting objects (e.g. vehicles, pedestrians, etc.) within the two-dimensional image data and determining movements of the object based on a position, trajectory, and velocity of the object. The determined information of the object may then be projected onto a map that may be used for generating the three-dimensional driving simulation. The use of cost-effective cameras provides the ability to obtain vast amounts of driving image data that may be used to provide an extensive coverage of the potential types of driving scenarios an autonomous vehicle may encounter.
    Type: Grant
    Filed: July 3, 2017
    Date of Patent: July 24, 2018
    Assignee: BAIDU USA LLC
    Inventors: Zhang Li, Jun Zhan, Yiqing Yang, Xuan Liu, Yu Cao, Siyang Yu, Guang Yang
  • Patent number: 10027887
    Abstract: The technology relates to transitioning between panoramic imagery and the imagery from which the panoramic imagery was generated. Individual images of a portion of a scene may be combined to create a panoramic image of the entire scene. The individual images may be associated with the portion of the panoramic image which they form. The full panoramic image may then be displayed. Based on user input, a portion of the panoramic image may be zoomed-in on, and the individual image associated with that portion of the panoramic image may be displayed.
    Type: Grant
    Filed: January 30, 2015
    Date of Patent: July 17, 2018
    Assignee: Google LLC
    Inventors: Robert Anderson, Carlos Hernandez Esteban
  • Patent number: 10015407
    Abstract: Methods and apparatus for supporting zoom operations using a plurality of optical chain modules, e.g., camera modules, are described. Switching between use of groups of optical chains with different focal lengths is used to support zoom operations. Digital zoom is used in some cases to support zoom levels corresponding to levels between the zoom levels of different optical chain groups or discrete focal lengths to which optical chains may be switched. In some embodiments optical chains have adjustable focal lengths and are switched between different focal lengths. In other embodiments optical chains have fixed focal lengths with different optical chain groups corresponding to different fixed focal lengths. Composite images are generate from images captured by multiple optical chains of the same group and/or different groups. Composite image is in accordance with a user zoom control setting. Individual composite images may be generated and/or a video sequence.
    Type: Grant
    Filed: August 24, 2016
    Date of Patent: July 3, 2018
    Assignee: Light Labs Inc.
    Inventor: Rajiv Laroia
  • Patent number: 10008009
    Abstract: A method of dynamically generating a graphic includes receiving, at a vector graphics engine loaded on a server system, graphic template input; receiving, at the vector graphics engine loaded on the server system, data template input; and generating, at the server system, code in a standard format representative of a vector graphic. The generating includes identifying a special tag associated with the vector graphics engine, converting code associated with this tag from a first format associated with the vector graphics engine to a second standardized format, and binding data content based on the received data template input to graphic content based on the received graphic template input.
    Type: Grant
    Filed: August 16, 2016
    Date of Patent: June 26, 2018
    Inventors: Alexis Salvatore Pecoraro, Sheppard David Narkier, David Antila, Paul Renaud
  • Patent number: 10008184
    Abstract: The invention includes a method including the steps of obtaining a plurality of images, each of the images in the plurality having at least one corresponding region, generating a merged image, the merged image also having the corresponding region. The step of generating includes selecting an image source from the plurality of images to source image data for the corresponding region in the merged image by comparing attributes of the corresponding regions of the plurality of images to identify the image source having preferred attributes.
    Type: Grant
    Filed: November 26, 2012
    Date of Patent: June 26, 2018
    Assignee: Hologic, Inc.
    Inventors: Kevin Kreeger, Andrew P. Smith, Ashwini Kshirsagar, Jun Ge, Yiheng Zhang, Haili Chui, Christopher Ruth, Xiangwei Zhang, Liyang Wei, Jay Stein
  • Patent number: 9996913
    Abstract: A system for two color image fusion blending co-registered low light level images in the visible region of the electromagnetic spectrum with thermal infrared images maximizes the information content of the scene by detecting in which of the two image types, IR and visible, there is more structural information and increasing the weight of the pixels in the image type having the most structural information. Additionally, situational awareness is increased by categorizing image information as “scene” or “target” and colorizing the target images to highlight target features when raw IR values are above a predetermined threshold. The system utilizes Red, Green and Blue (RGB) planes to convey different information such that for targets the Red plane is used to colorize regions when raw IR exceeds the predetermined threshold. For scene images, the Green plane provides improved situational awareness due to the above weighted blend of the two image types.
    Type: Grant
    Filed: April 1, 2015
    Date of Patent: June 12, 2018
    Assignee: BAE Systems Information and Electronic Systems Integration Inc.
    Inventors: Steven D. Beck, Derek T. Robison, Michael S. Chan, John H. Koltookian, Mark R. Mallalieu, Christopher M. Houle, Kari M. Karwedsky
  • Patent number: 9972212
    Abstract: This disclosure describes systems, methods, and apparatus for automating the verification of aerial vehicle sensors as part of a pre-flight, flight departure, in-transit flight, and/or delivery destination calibration verification process. At different stages, aerial vehicle sensors may obtain sensor measurements about objects within an environment, the obtained measurements may be processed to determine information about the object, as presented in the measurements, and the processed information may be compared with the actual information about the object to determine a variation or difference between the information. If the variation is within a tolerance range, the sensor may be auto adjusted and operation of the aerial vehicle may continue. If the variation exceeds a correction range, flight of the aerial vehicle may be aborted and the aerial vehicle routed for a full sensor calibration.
    Type: Grant
    Filed: June 21, 2016
    Date of Patent: May 15, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Samuel Sperindeo, Benji Barash, Yves Albers Schoenberg, Daniel Buchmueller
  • Patent number: 9965881
    Abstract: A method, executed by a processor of an image generation system, includes obtaining an image of a first area included in a first image and an image of a second area included in a second image, calculating a first conversion parameter for converting the image of the first area such that color information regarding the image of the first area becomes similar to color information regarding the image of the second area, converting the first image using the first conversion parameter, and generating a third image as a training image used for machine learning for image recognition by combining the converted first image and the second image with each other.
    Type: Grant
    Filed: August 3, 2016
    Date of Patent: May 8, 2018
    Inventors: Yasunori Ishii, Sotaro Tsukizawa, Masaki Takahashi, Reiko Hagawa
  • Patent number: 9959479
    Abstract: Image classification techniques are described for adjustment of an image. In one or more implementations, an image is classified by one or more computing device based on suitability of the image for adjustment to correct perspective distortion of the image. Responsive to a classification of the image as not suitable for the adjustment, suitability of the image is detected for processing by a different image adjustment technique by the one or more computing devices.
    Type: Grant
    Filed: July 3, 2017
    Date of Patent: May 1, 2018
    Inventors: Hyunjoon Lee, Elya Shechtman, Jue Wang
  • Patent number: 9961264
    Abstract: A camera including a camera lens, acquisition circuitry receiving images via the camera lens, for acquiring a first field of view when the camera lens is in a first orientation and for acquiring a second field of view when the camera lens is in a second orientation, and a viewfinder displaying the second field of view when the camera lens is in the second orientation and displaying at least a portion of the first field of view at least partially composited with the second field of view.
    Type: Grant
    Filed: August 29, 2011
    Date of Patent: May 1, 2018
    Assignee: Intellectual Ventures I LLC
    Inventor: Patrick Teo
  • Patent number: 9922266
    Abstract: Embodiments of the invention provide a method of visual saliency estimation comprising receiving an input sequence of image frames. Each image frame has one or more channels, and each channel has one or more pixels. The method further comprises, for each channel of each image frame, generating corresponding neural spiking data based on a pixel intensity of each pixel of the channel, generating a corresponding multi-scale data structure based on the corresponding neural spiking data, and extracting a corresponding map of features from the corresponding multi-scale data structure. The multi-scale data structure comprises one or more data layers, wherein each data layer represents a spike representation of pixel intensities of a channel at a corresponding scale. The method further comprises encoding each map of features extracted as neural spikes.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: March 20, 2018
    Assignee: International Business Machines Corporation
    Inventors: Alexander Andreopoulos, Steven K. Esser, Dharmendra S. Modha
  • Patent number: 9907468
    Abstract: An eye imaging apparatus can include a housing, an optical imaging system in the housing, and a light source in the housing to illuminate an eye. The optical imaging system can include an optical window at a front end of the housing with a concave front surface for receiving the eye as well as an imaging lens disposed rearward the optical window. The apparatus can comprise a light conditioning element configured to receive light from the light source and direct said light to the eye. The apparatus can further include an image sensor in the housing disposed to receive an image of the eye from the optical imaging system. In various embodiments, light conditioning element includes at least one multi-segment surface. In some embodiments, the housing is provided with at least one hermitic seal, for example, with the optical window. In some embodiments, time sequential illumination is employed.
    Type: Grant
    Filed: October 12, 2015
    Date of Patent: March 6, 2018
    Inventor: Wei Su
  • Patent number: 9884254
    Abstract: An augmented reality (AR) game system is disclosed wherein real-world objects are transformed into AR terrain elements and AR events generate real-world impact. The game environment is set up using real-world objects that include everyday objects and game pieces on a field of play. When viewed on the screen of a computing device executing the modules of the game system, the everyday objects are transformed into elements of an AR terrain while the game pieces can be augmented with various controls. Multiple viewing modes, for example, a third person view, a first person view or “POV” view from a selected game piece or a split screen view are contemplated for viewing the field of play. A subset of the augmented controls can be activated by the user to execute AR events some of which can have real-world impact. The AR events are executed based on game rules. Detection mechanisms such as colored detection can be used for detecting positions of game pieces within the field of play.
    Type: Grant
    Filed: September 2, 2015
    Date of Patent: February 6, 2018
    Inventors: Jason Yim, Mikayel Saryan
  • Patent number: 9881384
    Abstract: An approach is provided for providing one or more road conditions based on aerial imagery. The road condition platform processes and/or facilitates a processing of one or more road segments on an aligned image including an aerial image frame of an area and a reference map of the area to determine one or more non-road elements. The road condition platform also determines one or more characteristics of the one or more non-road elements disposed within the one or more road segments. The road condition platform further determines one or more road conditions based on the one or more characteristics.
    Type: Grant
    Filed: December 10, 2014
    Date of Patent: January 30, 2018
    Assignee: HERE Global B.V.
    Inventors: Joel Ponder, Leon Oliver Stenneth
  • Patent number: 9881371
    Abstract: Certain aspects of an apparatus and method for automatic ER/PR scoring of tissue samples may include for determining a cancer diagnosis score comprising identifying a positive stained nucleus in a slide image of the tissue sample, identifying a negative stained nucleus in the slide image, computing a proportion score based on number of the positive stained nucleus identified and number of the negative stained nucleus identified and determining the cancer diagnosis score based on the proportion.
    Type: Grant
    Filed: April 3, 2017
    Date of Patent: January 30, 2018
    Inventors: Ming-Chang Liu, Ximin Zhang
  • Patent number: 9883102
    Abstract: Provided are an image processing apparatus, an image processing method, a program, and a camera which are capable of generating a joined image in which misalignment is less likely to occur. An image processing apparatus according to an exemplary embodiment includes a motion vector derivation unit that derives a motion vector between images of a plurality of images; a correction unit that corrects a motion vector between images included in a target section from a first image to a second image based on cumulative errors in the section from the first image to the second image; and a texture writing unit that writes, into a frame memory, the plurality of textures that form the joined image, based on the motion vector corrected by the correction unit.
    Type: Grant
    Filed: March 24, 2015
    Date of Patent: January 30, 2018
    Inventor: Kunio Yamada
  • Patent number: 9871956
    Abstract: Generally, this disclosure describes multiple lenses in a mobile device. A mobile device may include a housing including a first surface, an opposing second surface and third, fourth, fifth and sixth surfaces connecting the first surface and the second surface forming the housing; a plurality of lenses, each lens configured to capture a respective image, each lens positioned relative to the housing so that a respective lens axis associated with each lens is perpendicular within a tolerance to at least a portion of at least one surface and a first lens axis associated with a first lens is perpendicular within the tolerance to a second lens axis associated with a second lens; at least one image sensor coupled to the plurality of lenses, configured to convert each captured image into respective image data; and circuitry configured to receive and process the image data.
    Type: Grant
    Filed: April 26, 2012
    Date of Patent: January 16, 2018
    Inventors: Todd S. Harple, Gyan Prakash, Rajesh Poornachandran
  • Patent number: 9864915
    Abstract: An around-view monitoring (AVM) apparatus including a camera module for obtaining a plurality of video images from around a vehicle; a display unit for displaying an around-view video image; and a control unit for composing the plurality of video images to generate an around-view video image, detecting a first parking line and a second parking line from the around-view video image, tracking the detected first and second parking lines, and generating an imaginary parking line when any one of the first and second parking lines is not tracked to control the display unit to output the around-view video image.
    Type: Grant
    Filed: November 11, 2014
    Date of Patent: January 9, 2018
    Assignee: Hyundai Mobis Co., Ltd.
    Inventor: Seong soo Lee
  • Patent number: 9834143
    Abstract: A system and method for creating an enhanced perspective view of an area in front of a vehicle, using images from left-front and right-front cameras. The enhanced perspective view removes the distortion and exaggerated perspective effects which are inherent in wide-angle lens images. The enhanced perspective view uses a camera model including a virtual image surface and other processing techniques which provide corrections for two types of problems which are typically present in de-warped perspective images—including a stretching effect at the peripheral area of a wide-angle image de-warped by rectilinear projection, and double image of objects in an area where left-front and right-front camera images overlap.
    Type: Grant
    Filed: May 16, 2014
    Date of Patent: December 5, 2017
    Assignee: GM Global Technology Operations LLC
    Inventors: Wende Zhang, Jinsong Wang, Kent S. Lybecker, Jeffrey S. Piasecki, Bakhtiar Brian Litkouhi, Ryan M. Frakes
  • Patent number: 9813622
    Abstract: A high resolution imaging system includes an imaging camera array creating a sets or frames of array images of a scene and a reference camera creating reference images of the same scene. A synchronization controller coordinates imaging of the scene by the imaging camera array and the reference camera. An image processor merges the sets of array images into high resolution images and apply a color correction to the high resolution images based on reference images. Color correction can be performed on the merged high resolution image or on individual array images prior to merger into the high resolution image.
    Type: Grant
    Filed: July 27, 2015
    Date of Patent: November 7, 2017
    Assignee: Futurewei Technologies, Inc.
    Inventors: Dong-Qing Zhang, Radhakrishna Dasari, Jie Hu, John Wus
  • Patent number: 9805509
    Abstract: A system and method of generating a virtual image and displaying the virtual image so that the image appears to be anchored to a real world object. A data frame of spatial data obtained by one or more sensors is analyzed to determine whether one or more real-world objects to be detected is located in the data frame. If one of the real-world objects is in the data frame, the coordinates of a real-world reference point associated with the real-world object are determined. A virtual 3D space is generated and a base plane is constructed passing through a virtual object reference point in the virtual space. One or more planar content elements are placed on or parallel to the base plane. An image is formed in which the content elements appear to lie in a plane passing through the real-world reference point of the detected object.
    Type: Grant
    Filed: November 26, 2014
    Date of Patent: October 31, 2017
    Inventor: Yoav Shefi
  • Patent number: 9785842
    Abstract: A safety alarm system for a vehicle including: a sensor module configured to output an open signal when a vehicle door is opened; an image photographing module configured to output first and second vehicle surrounding image obtained by sequentially photographing a vehicle surrounding area; and a control module configured to detect whether a moving object is located within a predetermined vehicle safety area in the first and second images input by operating the image photographing module at the time of inputting the open signal and generating a safety alarm when the moving object is detected.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: October 10, 2017
    Assignee: Hyundai Mobis Co., Ltd.
    Inventor: Seong soo Lee