公开(公告)号：US20190208182A1

公开(公告)日：2019-07-04

申请号：US16296562

申请日：2019-03-08

申请人： Shin Aoki ,  Naoki Kikuchi ,  Kagehiro Nagao ,  Jun Kishiwada

发明人： Shin Aoki ,  Naoki Kikuchi ,  Kagehiro Nagao ,  Jun Kishiwada

IPC分类号： H04N13/246 ,  B60R11/04 ,  G06T7/80 ,  G06T7/70 ,  G06T7/521 ,  H04N13/239

CPC分类号： H04N13/246 ,  B60R11/04 ,  B60R2011/0026 ,  G06T7/521 ,  G06T7/70 ,  G06T7/85 ,  G06T2207/10012 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/30208 ,  G06T2207/30252 ,  H04N13/239

摘要： A calibration method calibrates a stereo camera. The calibration method includes: measuring a relative position between the stereo camera and an object that is placed so as to fall within an image capturing area of the stereo camera; acquiring a captured image that is captured by the stereo camera and includes the object; and determining a calibration parameter for calibrating the stereo camera based on the relative position and the captured image.

公开(公告)号：US20190180453A1

公开(公告)日：2019-06-13

申请号：US16198213

申请日：2018-11-21

申请人： SICK AG

发明人： Jens SILVA ,  Uwe HAHNE

IPC分类号： G06T7/246

CPC分类号： G06T7/248 ,  G01B11/25 ,  G01B11/2545 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20021 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30232

摘要： A method of recognizing changes in a detection zone is provided in which three-dimensional image data of the detection zone are detected and evaluated to recognize changes with reference to three-dimensional reference image data. The detection zone is divided into cells in this process. Reference limit values at which heights objects are recognized are determined in a teaching phase. In an operating phase, a maximum value and/or a minimal value of the heights of currently recognized objects is/are determined from the respective detected image data and a change is recognized on a deviation with respect to the reference limit values.

公开(公告)号：US20190154872A1

公开(公告)日：2019-05-23

申请号：US16248418

申请日：2019-01-15

申请人： Reliance Core Consulting LLC

发明人： Jean-Pierre Leduc

IPC分类号： G01V8/20 ,  H04N5/247 ,  G06T7/292 ,  G06T17/00 ,  G06N3/08

CPC分类号： G01V8/20 ,  G06N3/08 ,  G06T7/292 ,  G06T7/593 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30232 ,  G06T2207/30241 ,  H04N5/247

摘要： According to some embodiments, a system for performing motion analysis in a field of interest is disclosed. Further, the system may include a plurality of motion sensors configured to generate a plurality of motion data corresponding to at least one motion of at least one object in the field of interest. Further, the system may include a communication device configured for receiving configuration data associated with the field of interest from at least one data source. Further, the system may include a processing device configured for generating a digital model corresponding to the field of interest based on the configuration data using a simulation module and generating one or more of a plurality of motion signatures corresponding to a plurality of predetermined motions and a plurality of object signatures corresponding to a plurality of predetermined objects based on the digital model using the simulation module.

公开(公告)号：US20190050636A1

公开(公告)日：2019-02-14

申请号：US16165432

申请日：2018-10-19

申请人： SportsMEDIA Technology Corporation

发明人： James G. Painter

IPC分类号： G06K9/00 ,  G06T7/292 ,  G06T7/254 ,  G06K9/46 ,  H04N5/247 ,  G06T7/215 ,  H04N5/262

CPC分类号： G06K9/00348 ,  G06K9/00664 ,  G06K9/46 ,  G06K2009/4666 ,  G06T7/215 ,  G06T7/254 ,  G06T7/292 ,  G06T2207/10021 ,  G06T2207/30221 ,  G06T2207/30241 ,  H04N5/247 ,  H04N5/2625

摘要： A path and/or orientation of object approaching an athlete is tracked using two or more cameras. At least two sets of images of the object are obtained using at least two different cameras having different positions. Motion regions within images are identified, and candidate locations in 2D space of the object are identified within the motion region(s). Based thereon, a probable location in 3D space of the identifiable portion is identified, for each of a plurality of instants during which the object was approaching. A piecewise 3D trajectory of at least the identifiable portion of the object is approximated from the probable locations in 3D space of the object for multiple instants during which the object was approaching the athlete. A graphical representation of the 3D trajectory of the object is incorporated into at least one of the sets of images.

公开(公告)号：US20190007675A1

公开(公告)日：2019-01-03

申请号：US15823493

申请日：2017-11-27

申请人： ArcherMind Technology (Nanjing) Co., Ltd.

发明人： Guangrong Zeng ,  Bin Du

IPC分类号： H04N13/25 ,  G06K9/20 ,  H04N5/33 ,  H04N13/257

CPC分类号： H04N13/25 ,  G01B11/2513 ,  G01B11/2545 ,  G06K9/00201 ,  G06K9/2036 ,  G06K2209/40 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/10028 ,  H04N5/33 ,  H04N13/254 ,  H04N13/257 ,  H04N13/271

摘要： Disclosed are a method and apparatus for acquiring a three-dimensional image using two cameras. The method includes: acquiring image information of a target object using a first camera, and sending the acquired image information to an image signal processor; acquiring a phase grating image subjected to strip deformation in a picture space with an identical visual angle using a second camera, calculating depth data of the target object, and sending the depth data to the image signal processor; upon receipt of the image information and the depth data, if the image signal processor judges that the depth data is received, directly sending the depth data to a 3D image generating module, and if the image signal processor judges that the image information is received, performing routine image signal processing and sending the image information to the 3D image generating module; and synthesizing the depth data and the image information subjected to the image signal processing using the 3D image generating module to generate a 3D image.

公开(公告)号：US20180349939A1

公开(公告)日：2018-12-06

申请号：US15915050

申请日：2018-03-07

申请人： GOOGLE LLC

发明人： William Setchell ,  Mallinath Bareddy ,  Phillip Ellsworth Stahlfeld ,  Yichen Zhao ,  Xiaoyong Chai ,  Timothy Raymond Zwiebel ,  Michal Palczewski ,  Chunxiao Diao ,  Dennis Yung-Chi Hu ,  Anuj Batra ,  Min-Hao Wu

IPC分类号： G06Q30/02 ,  G06N99/00 ,  G06Q20/20 ,  G06K9/00

CPC分类号： G06Q20/40145 ,  G06F21/32 ,  G06K9/00288 ,  G06K9/00771 ,  G06Q20/20 ,  G06T2207/10021 ,  H04L63/0861 ,  H04W12/06 ,  H04W12/08

摘要： A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.

公开(公告)号：US20180333081A1

公开(公告)日：2018-11-22

申请号：US15982795

申请日：2018-05-17

申请人： VISION RT LIMITED

发明人： Gideon Matthew HALE ,  Peter John HANSON

IPC分类号： A61B5/11 ,  A61N5/10 ,  H04N13/254 ,  G06T7/73 ,  G06T17/20 ,  G06T7/521 ,  G03B21/16

CPC分类号： A61B5/1113 ,  A61B5/1128 ,  A61B6/5258 ,  A61B6/5264 ,  A61N5/1049 ,  A61N5/1069 ,  A61N2005/1056 ,  A61N2005/1059 ,  G01B11/2545 ,  G03B21/16 ,  G06T7/521 ,  G06T7/74 ,  G06T7/75 ,  G06T17/20 ,  G06T2207/10021 ,  H04N13/254 ,  H04N2213/001

摘要： Some embodiments are directed to a patient monitoring system for monitoring the location of a patient at a distance, including a projector operable to project a pattern of light onto the surface of a patient and a imaging system operable to obtain images of a patient on to whom a pattern of light is projected. A heat sink is associated with the projector. A heat source, such as an array of resistors, is configured to apply heat to the heat sink when the projector is not being operated, reducing variation in the temperature of the heat sink which in turn reduces variation in thermal expansion and contraction of the monitoring system which can be a potential source of error for determining the position of a patient being monitored.

公开(公告)号：US20180330509A1

公开(公告)日：2018-11-15

申请号：US16043857

申请日：2018-07-24

申请人： Genki Watanabe ,  Keito Sawada ,  Hiroyoshi Sekiguchi

发明人： Genki Watanabe ,  Keito Sawada ,  Hiroyoshi Sekiguchi

IPC分类号： G06T7/246 ,  G06T7/593 ,  G06T7/73 ,  G06K9/62 ,  G06T7/292 ,  G05D1/02 ,  G05D1/00 ,  B60W30/095 ,  B60W30/09

CPC分类号： G06T7/248 ,  B60W30/09 ,  B60W30/0956 ,  B60W2420/42 ,  G05D1/0088 ,  G05D1/0214 ,  G05D1/0253 ,  G05D2201/0213 ,  G06K9/6215 ,  G06T7/00 ,  G06T7/20 ,  G06T7/285 ,  G06T7/292 ,  G06T7/593 ,  G06T7/74 ,  G06T2207/10012 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/30252 ,  G08G1/16

摘要： Disclosed is an image processing apparatus that includes one or more processors; and a memory, the memory storing instructions. When executed by the one or more processors, cause the one or more processors to: generate distribution data indicating a frequency distribution of horizontal distance values of a range image based on the range image having pixel values according to distance of an object in a plurality of captured images; predict a predicted position of the object in the distribution data with respect to a range image of a current frame, based on the distribution data with respect to range images of a plurality of previous frames; and continue tracking of the object, based on a similarity between a region of the object in a previous frame and a region in the current frame with respect to the predicted position of the object.

公开(公告)号：US20180322648A1

公开(公告)日：2018-11-08

申请号：US15775800

申请日：2016-11-09

申请人： ZHEJIANG DAHUA TECHNOLOGY CO., LTD.

发明人： Wei LU ,  Qiankun LI ,  Shizhu PAN ,  Miao CHENG ,  Xiangming ZHOU

IPC分类号： G06T7/593 ,  G06T7/80 ,  G06K9/62

CPC分类号： G06T7/593 ,  G06K9/6269 ,  G06T7/85 ,  G06T2207/10021 ,  G06T2207/20081

摘要： A system and method for binocular stereo vision is disclosed. The method includes acquiring a pair of images including a first image and a second image, the pair of images being captured by one or more cameras; obtaining a training model; determining a plurality of feature images according to the first image; determining one or more features of an object in the first image according to the training model and the plurality of feature images; determining a first area in the first image, the first area including at least one of the determined one or more features; obtaining depth information of the determined first area based on the first and second images; and determining a second area in the first image based on the determined first area and depth information, the second area including at least one of the determined first area.

公开(公告)号：US20180276805A1

公开(公告)日：2018-09-27

申请号：US15993414

申请日：2018-05-30

申请人： Edge 3 Technologies, Inc.

发明人： Tarek El Dokor ,  Jordan Cluster

IPC分类号： G06T7/00 ,  G06T7/11 ,  G06T7/174 ,  G06K9/00 ,  G06T7/593 ,  G06K9/66 ,  G06T7/187 ,  G06K9/62

CPC分类号： G06T7/00 ,  G06K9/00 ,  G06K9/00201 ,  G06K9/6218 ,  G06K9/66 ,  G06T7/11 ,  G06T7/174 ,  G06T7/187 ,  G06T7/593 ,  G06T2200/04 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/20112 ,  H05K999/99

摘要： A method and apparatus for segmenting an image are provided. The method may include the steps of clustering pixels from one of a plurality of images into one or more segments, determining one or more unstable segments changing by more than a predetermined threshold from a prior of the plurality of images, determining one or more segments transitioning from an unstable to a stable segment, determining depth for one or more of the one or more segments that have changed by more than the predetermined threshold, determining depth for one or more of the one or more transitioning segments, and combining the determined depth for the one or more unstable segments and the one or more transitioning segments with a predetermined depth of all segments changing less than the predetermined threshold from the prior of the plurality of images.