-
公开(公告)号：US20180365858A1
公开(公告)日：2018-12-20
申请号：US16008933
申请日：2018-06-14
申请人： HYUNDAI MOBIS CO., LTD. , KOREA NATIONAL UNIVERSITY OF TRANSPORTATION INDUSTRY-ACADEMIC COOPERATION FOUNDATION
发明人： Hoon Min KIM , Dong Wook JUNG , Sung Joo LEE , Kyoungtaek CHOI , Jae Kyu SUHR , Ho Gi JUNG
CPC分类号： G06T7/80 , B60R11/04 , G06K9/00798 , G06T7/13 , G06T7/536 , G06T7/74 , G06T7/77 , G06T2207/20032 , G06T2207/20036 , G06T2207/30252 , G06T2207/30256 , G08G1/167 , H04N7/181
摘要： A calibration method may include: detecting, by a lane detection unit, lanes from around images acquired through cameras of a vehicle, when a behavior of the vehicle satisfies a preset behavior condition; analyzing, by a valid lane extraction unit, statistical characteristics of the positions and directions of the detected lanes, and extracting a valid lane by removing a misdetected lane; and estimating, by a parameter estimation unit, installation angles of the cameras based on the direction of the valid lane and a vanishing point decided through the valid lane.
-
公开(公告)号：US20180322687A1
公开(公告)日：2018-11-08
申请号：US15895869
申请日：2018-02-13
发明人： Hang-Kee KIM , Ki-Suk LEE , Ki-Hong KIM
CPC分类号： G06T15/20 , G06F3/011 , G06T7/536 , G06T19/003
摘要： Disclosed herein are an apparatus and method for providing interactive content. The apparatus for providing interactive content includes an object classification unit for classifying content to be output into a view-independent background and view-dependent objects, a viewpoint association unit for determining viewpoints of users who are to be interactively associated with respective view-dependent objects and interactively associating the viewpoints of the users with the view-dependent objects, a rendering unit for generating a background-visualized image by rendering the view-independent background with respect to a hot spot, and generating object-visualized images by rendering the view-dependent objects based on the viewpoints interactively associated with respective view-dependent objects, and an output unit for outputting the background-visualized image and the object-visualized images.
-
公开(公告)号：US20180247423A1
公开(公告)日：2018-08-30
申请号：US15754162
申请日：2016-08-08
发明人： Daisuke SUZUKI , Takeo FUJITA , Toru AOKI , Narihiro MATOBA
CPC分类号： G06T7/536 , G06T5/003 , G06T5/50 , G06T7/579 , G06T2207/10016 , G06T2207/20201 , G06T2207/30252
摘要： An image processing device is provided with an optical flow calculation circuit (101) for calculating a plurality of optical flows between a first image and a second image captured before the first image, a vector decomposition circuit (102) for decomposing each of the optical flows into a vanishing point direction vector and an orthogonal vector, a vibration blur amount calculation circuit (103) for calculating the aggregate values of horizontal and vertical components of the orthogonal vector and calculating the amount of vibration blur of the first image based on the aggregate values, an optical flow starting point correction circuit (104) for correcting the calculated optical flows by the amount of vibration blur, and a vanishing point calculation circuit (105) for calculating a vanishing point of the first image based on the corrected optical flows.
-
公开(公告)号：US10043286B2
公开(公告)日：2018-08-07
申请号：US15260587
申请日：2016-09-09
发明人： Joo-Haeng Lee
CPC分类号： G06T7/536
摘要： An apparatus for restoring a cubical object includes: a vanishing point computing part configured to compute vanishing points corresponding to an image; an image depth computing part configured to compute an image depth of a cubical object in the image; a central rectangle computing part configured to compute a central rectangle based on a representative rectangle of the image and the vanishing points; a restored rectangle computing part configured to compute a restored rectangle corresponding to the central rectangle and a projection center point using a coupled line camera (CLC) method; a cube depth computing part configured to computed a restored cubical object depth based on the central rectangle, the restored rectangle and the projection center point; and a cube restoring part configured to restore a cubical object having the restored rectangle as one surface thereof and having a depth of the restored cubical object depth.
-
公开(公告)号：US20180211412A1
公开(公告)日：2018-07-26
申请号：US15859790
申请日：2018-01-02
申请人： MANTISVISION LTD.
发明人： Eyal Gordon , Michael Slutsky , Yonatan Samet
CPC分类号： G06T7/80 , G01B11/2513 , G06K9/2036 , G06K9/209 , G06K9/3216 , G06T7/521 , G06T7/536 , G06T7/85 , G06T15/205 , G06T2200/04 , G06T2207/10021 , G06T2207/20228 , G06T2207/30204 , H04N5/2224 , H04N13/246
摘要： A structured light projector includes an optical mask and a light emitter. The light emitter can be capable of illuminating the optical mask, and the optical mask can be capable of transforming the light from the emitter so as to provide structured light bi-dimensional coded light pattern that includes a plurality of feature types formed by a unique combination of feature elements. The projected light pattern includes one or more markers which include pairs of feature elements between which the epipolar distances are modified relative to distances between respective feature elements in non-marker areas of the pattern, and an appearance of feature elements within the marker and across the marker's edges is continuous.
-
公开(公告)号：US20180165822A1
公开(公告)日：2018-06-14
申请号：US15833482
申请日：2017-12-06
发明人： Mithun ULIYAR , Ravi SHENOY , Soumik UKIL , Krishna A G , Gururaj PUTRAYA , Pushkar PATWARDHAN
CPC分类号： G06T7/55 , G06K9/00798 , G06K9/00805 , G06K9/00818 , G06K9/36 , G06K2009/363 , G06T7/536 , G06T7/62 , G06T7/80 , G06T2207/10016 , G06T2207/10024 , G06T2207/10032 , G06T2207/30244 , G06T2207/30256 , G06T2207/30261 , H04N5/23296 , H04N7/181
摘要： A method for estimating distance of an object from a moving vehicle is provided. The method includes detecting, by a camera module in one or more image frames, an object on a road on which the vehicle is moving. The method includes electronically determining a pair of lane markings associated with the road. The method further includes electronically determining a lane width between the pair of the lane markings in an image coordinate of the one or more image frames. The lane width is determined at a location of the object on the road. The method includes electronically determininga real world distance of the object from the vehicle based at least on number of pixels corresponding to the lane width in the image coordinate, a pre-defined lane width associated with the road and at least one camera parameter of the camera module.
-
公开(公告)号：US09898835B2
公开(公告)日：2018-02-20
申请号：US15220661
申请日：2016-07-27
发明人： Chaur-Heh Hsieh , Hsiu-Chien Hsu
IPC分类号： G06K9/00 , G06T11/00 , G06T11/60 , G06T7/73 , G06T7/529 , G06T7/536 , G06T7/11 , G06T7/13 , G06T7/90 , G06T7/187
CPC分类号： G06T11/00 , G06K9/00248 , G06K9/00281 , G06T7/11 , G06T7/13 , G06T7/187 , G06T7/529 , G06T7/536 , G06T7/74 , G06T7/90 , G06T11/60 , G06T2200/04 , G06T2207/10016 , G06T2207/10024 , G06T2207/20068 , G06T2207/20221 , G06T2207/30201 , G06T2207/30204
摘要： A method for creating a face replacement database includes steps of creating a face database for storing a plurality of replaced images with a face image rotation angle by using a method for estimating a 3D vector angle from a 2D face image, and defining a region to be replaced in the replaced image. The method for estimating a 3D vector angle from a 2D face image includes the steps of creating a feature vector template; detecting a corner of eye and mouth in a face image; defining a sharp point in a vertical direction of the quadrilateral plane, and converting the vertices into 3D coordinates; computing the four vectors from the sharp point to the four vertices to obtain a vector set, and matching the vector set with the feature vector model to obtain an angle which is defined as a rotation angle of the input face image.
-
公开(公告)号：US09857581B2
公开(公告)日：2018-01-02
申请号：US14893240
申请日：2014-05-27
发明人： Jorg Engel , Thomas Kalkbrenner , Wolfgang Bathe
CPC分类号： G02B21/367 , G01N21/6428 , G01N21/6458 , G01N21/6486 , G02B21/16 , G02B21/26 , G02B27/58 , G06T7/536 , G06T7/77 , G06T2200/04 , G06T2207/10024 , G06T2207/10056 , G06T2207/10064 , G06T2207/10072
摘要： The invention relates to a method for high-resolution luminescence microscopy of a specimen marked with marker molecules, and to a luminescence microscope for performing the method, wherein the marker molecules can be excited to emit luminescence radiation. The method for luminescence microscopy comprises the excitation and imaging of marker molecules and the transmission of a trigger time and a position of the specimen. An optical recording device images the marker molecules in a capture area and transmits data from the imaging to an image capture circuit. The recording device transmits a time for the imaging to a signal former as a trigger time; the trigger time is then transmitted to a data recorder. The data recorder generates a position of the specimen at the trigger time and transmits said position to the image capture circuit, which links the position of the specimen in the depth direction to the data of the imaging of a frame such that a three-dimensional tomographic image of the specimen can be created.
-
59.发明申请公开(公告)号：US20170278289A1
公开(公告)日：2017-09-28
申请号：US15466135
申请日：2017-03-22
申请人： Uru, Inc.
IPC分类号： G06T11/60 , G06T7/246 , G06T7/11 , G06K9/46 , G06T7/262 , G06T7/44 , G06T7/90 , G06T7/536 , G06T7/194 , G06K9/00
CPC分类号： G06T11/60 , G06K9/00765 , G06K9/4642 , G06Q30/0276 , G06T7/11 , G06T7/194 , G06T7/246 , G06T7/262 , G06T7/44 , G06T7/536 , G06T7/90 , G06T2207/10004 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/20016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221 , G06T2207/30204 , G06T2207/30244
摘要： Some embodiments of the present disclosure provide a content integration system. The content integration system is configured to retrieve a source digital content, retrieve a target digital content, identify a region within the target digital content for placing or integrating the source digital content, and place or integrate the target digital content onto the identified region of the source digital content. The content integration system can be configured to place the source digital content into the target digital content in an aesthetically-pleasing, unobtrusive, engaging, and/or otherwise favorable manner. The content integration system can be particularly useful for advertisements, enhanced expression, entertainment, information, or communication.
-
公开(公告)号：US20170177082A1
公开(公告)日：2017-06-22
申请号：US15454715
申请日：2017-03-09
发明人： Ashraf Ayman Michail , Roger Sebastian Kevin Sylvan , Quentin Simon Charles Miller , Alex Aben-Athar Kipman
CPC分类号： G06T19/006 , G02B27/0093 , G02B27/0172 , G02B27/0179 , G02B2027/0134 , G02B2027/014 , G02B2027/0178 , G02B2027/0187 , G06F3/011 , G06F3/013 , G06F3/0346 , G06F3/147 , G06K9/00604 , G06K9/00671 , G06T7/536 , G06T19/20 , G06T2207/20228 , G06T2207/30201 , G09G3/3266 , G09G5/346 , G09G2310/0235 , G09G2320/0261 , G09G2320/106
摘要： Embodiments are described herein for determining a stabilization plane to reduce errors that occur when a homographic transformation is applied to a scene including 3D geometry and/or multiple non-coplanar planes. Such embodiments can be used, e.g., when displaying an image on a head mounted display (HMD) device, but are not limited thereto. In an embodiment, a rendered image is generated, a gaze location of a user is determined, and a stabilization plane, associated with a homographic transformation, is determined based on the determined gaze location. This can involve determining, based on the user's gaze location, variables of the homographic transformation that define the stabilization plane. The homographic transformation is applied to the rendered image to thereby generate an updated image, and at least a portion of the updated image is then displayed.
-
-
-
-
-
-
-
-
-
搜索结果
265 条记录 (耗时 0.026 秒)
