-
11.发明申请公开(公告)号：US20190208177A1
公开(公告)日：2019-07-04
申请号：US16295582
申请日：2019-03-07
Inventor： Tatsuya KOYAMA , Toshiyasu SUGIO , Toru MATSUNOBU , Satoshi YOSHIKAWA , Pongsak LASANG , Chi WANG
IPC: H04N13/139 , H04N13/282 , G06T7/80
CPC classification number: H04N13/139 , G06T7/55 , G06T7/70 , G06T7/85 , G06T2207/10021 , H04N13/282
Abstract: A three-dimensional model generating device includes: a converted image generating unit that, for each of input images included in one or more items of video data and having mutually different viewpoints, generates a converted image from the input image that includes fewer pixels than the input image; a camera parameter estimating unit that detects features in the converted images and estimates, for each of the input images, a camera parameter at a capture time of the input image, based on a pair of similar features between two of the converted images; and a three-dimensional model generating unit that generates a three-dimensional model using the input images and the camera parameters.
-
公开(公告)号：US20190191146A1
公开(公告)日：2019-06-20
申请号：US16284339
申请日：2019-02-25
Inventor： Tatsuya KOYAMA , Toshiyasu SUGIO , Toru MATSUNOBU , Satoshi YOSHIKAWA
IPC: H04N13/246 , H04N13/243 , G06T7/80 , G06K9/00 , G06T7/20 , H04N13/296 , H04N13/111 , G06T7/70
CPC classification number: H04N13/246 , G06K9/00744 , G06K2009/00738 , G06T7/20 , G06T7/70 , G06T7/80 , G06T2207/10016 , G06T2207/30244 , H04N5/222 , H04N5/232 , H04N7/18 , H04N13/111 , H04N13/243 , H04N13/296
Abstract: A multiple viewpoint image capturing system includes: a plurality of cameras that capture videos in a predetermined space from different positions; a circumstance sensing unit that senses at least one of circumstances of the respective cameras and circumstances of the predetermined space, and outputs the sensed circumstances in a form of capturing circumstance information; and an event detector that detects a predetermined event based on the capturing circumstance information, determines whether to perform camera calibration in a case of detecting the predetermined event, and outputs camera calibration information that indicates the camera calibration to be performed in a case of determining that the camera calibration is to be performed.
-
公开(公告)号：US20190051036A1
公开(公告)日：2019-02-14
申请号：US16163010
申请日：2018-10-17
Inventor： Toru MATSUNOBU , Toshiyasu SUGIO , Satoshi YOSHIKAWA , Tatsuya KOYAMA , Pongsak LASANG , Jian GAO
Abstract: Provided is a three-dimensional reconstruction method of reconstructing a three-dimensional model from multi-view images. The method includes: selecting two frames from the multi-view images; calculating image information of each of the two frames; selecting a method of calculating corresponding keypoints in the two frames, according to the image information; and calculating the corresponding keypoints using the method of calculating corresponding keypoints selected in the selecting of the method of calculating corresponding keypoints.
-
公开(公告)号：US20250047888A1
公开(公告)日：2025-02-06
申请号：US18924514
申请日：2024-10-23
Inventor： Satoshi YOSHIKAWA , Hisao SASAI , Kengo TERADA
IPC: H04N19/50 , H04N19/176 , H04N19/182 , H04N19/46
Abstract: A decoder, encoder, and a recording medium causes a processor to generate a prediction image by an inter prediction process by i) obtaining first information from a bitstream associated with a variable number of feature points of a current block usable in performing an affine prediction, ii) obtaining a flag from the bitstream indicating a first or second value, iii) obtaining second information from the bitstream specifying first points in response to the flag indicating the first value, iv) determining third information provided the first points based on the second information and indicating a difference between coordinate values of a first point and a corresponding second point included in a reference picture, v) generating a prediction image of the current block according to the determined third information, and vi) refraining from obtaining the second information from the bitstream, in response to the flag indicating the second value.
-
15.发明公开公开(公告)号：US20230281927A1
公开(公告)日：2023-09-07
申请号：US18195606
申请日：2023-05-10
Inventor： Toru MATSUNOBU , Kensho TERANISHI , Masaki FUKUDA , Ukyou KATSURA , Makoto KOHRIN , Satoshi YOSHIKAWA
Abstract: A three-dimensional point cloud densification device includes: an obtainer that obtains a plurality of three-dimensional points, each of which indicates a three-dimensional position of at least one object, and auxiliary information for creating a polygon; and a densifier that: identifies the polygon having, as vertices, at least three three-dimensional points among the plurality of three-dimensional points, based on the auxiliary information; and generates a new three-dimensional point inside the polygon.
-
Patent Agency Ranking
16.发明公开公开(公告)号：US20230206558A1
公开(公告)日：2023-06-29
申请号：US18117056
申请日：2023-03-03
Inventor： Masaki FUKUDA , Toru MATSUNOBU , Satoshi YOSHIKAWA , Kensho TERANISHI , Ukyou KATSURA
IPC: G06T17/10
CPC classification number: G06T17/10
Abstract: A three-dimensional model generation method includes: detecting a first line from each of a plurality of images of a target area shot to detect a plurality of first lines, the plurality of images being shot from a plurality of viewpoints; excluding, from the plurality of first lines detected, a second line that reaches an edge of an image among the plurality of images; and generating a line segment model which is a three-dimensional model of the target area represented by lines, using a plurality of line segments which are the plurality of first lines from which the second line is excluded.
-
17.发明申请公开(公告)号：US20230005220A1
公开(公告)日：2023-01-05
申请号：US17943415
申请日：2022-09-13
Inventor： Satoshi YOSHIKAWA , Toru MATSUNOBU , Kensho TERANISHI , Masaki FUKUDA , Ukyou KATSURA
Abstract: A shooting method executed by a shooting device includes: shooting first images of a target space; generating a first three-dimensional point cloud of the target space, based on the first images and a first shooting position and a first shooting orientation of each of the first images; and determining a first region of the target space for which generating a second three-dimensional point cloud which is denser than the first three-dimensional point cloud is difficult, using the first three-dimensional point cloud and without generating the second three-dimensional point cloud. The determining includes generating a mesh using the first three-dimensional point cloud, and determining the region other than a second region of the target space for which the mesh is generated.
-
公开(公告)号：US20220116641A1
公开(公告)日：2022-04-14
申请号：US17558755
申请日：2021-12-22
Inventor： Satoshi YOSHIKAWA , Hisao SASAI , Kengo TERADA
IPC: H04N19/50
Abstract: A decoder includes a memory and a processor coupled to the memory. The processor is configured to obtain first information from a bitstream, the first information indicating a number of first points in a current picture. The processor is also configured to determine second information provided for each of the first points based on the first information, the second information indicating a difference between a coordinate value of a first point and a coordinate value of a corresponding second point, the corresponding second point being included in a reference picture. The processor is further configured to generate a prediction image of a current block by performing an affine prediction according to the determined second information.
-
公开(公告)号：US20210335010A1
公开(公告)日：2021-10-28
申请号：US17370402
申请日：2021-07-08
Inventor： Masaki FUKUDA , Toshiyasu SUGIO , Toru MATSUNOBU , Satoshi YOSHIKAWA , Tatsuya KOYAMA
Abstract: A calibration method of calibrating, using a processor, parameters of a plurality of imaging apparatuses that capture a common three-dimensional space, includes: obtaining images captured by the plurality of imaging apparatuses; obtaining the parameters of the plurality of imaging apparatuses; for each of the images, generating at least one search window to extract a plurality of feature points of the image using the parameters; for each of the images, extracting the plurality of feature points from an inside of the at least one search window; performing feature point matching between the images using the plurality of feature points; and calibrating the parameters based on a plurality of matching results obtained.
-
20.发明申请公开(公告)号：US20210027529A1
公开(公告)日：2021-01-28
申请号：US17066935
申请日：2020-10-09
Inventor： Toru MATSUNOBU , Toshiyasu SUGIO , Satoshi YOSHIKAWA , Tatsuya KOYAMA , Masaki FUKUDA
Abstract: A three-dimensional model processing method includes: generating, from first images shot by respective cameras at a first time, a first three-dimensional model including: first three-dimensional points indicating a subject at the first time; and first camera parameters indicating positions and orientations of the cameras; generating, from second images shot by the respective cameras at a second time, a second three-dimensional model including: second three-dimensional points indicating the subject at the second time; and second camera parameters indicating positions and orientations of the cameras; detecting a stationary camera among the cameras, whose position and orientation has not changed between the first and second times, or stationary three-dimensional points among the three-dimensional points, whose positions have not changed between the first and second times; and matching world coordinate systems of the first and second three-dimensional models, based on the first camera parameters of the stationary camera or the stationary three-dimensional points detected.
-
-
-
-
-
-
-
-
-
Search Results
32
records
(took 0.054 seconds)
