公开(公告)号：US20230140170A1

公开(公告)日：2023-05-04

申请号：US17811028

申请日：2022-07-06

申请人： Samsung Electronics Co., Ltd.

发明人： Yingen Xiong ,  Christopher A. Peri

IPC分类号： G06T19/00 ,  G06T7/593 ,  G06T7/73 ,  G06F3/01 ,  H04N13/239

摘要： A method includes obtaining first and second image data of a real-world scene, performing feature extraction to obtain first and second feature maps, and performing pose tracking based on at least one of the first image data, second image data, and pose data to obtain a 6DOF pose of an apparatus. The method also includes generating, based on the 6DOF pose, first feature map, and second feature map, a disparity map between the image data and generating an initial depth map based on the disparity map. The method further includes generating a dense depth map based on the initial depth map and a camera model and generating, based on the dense depth map, a three-dimensional reconstruction of at least pail of the scene. In addition, the method includes rendering an AR or XR display that includes one or more virtual objects positioned to contact one or more surfaces of the reconstruction.

公开(公告)号：US20230130478A1

公开(公告)日：2023-04-27

申请号：US17798232

申请日：2020-06-22

申请人： Nvidia Corporation

发明人： Dong Zhang ,  Eric Viscito ,  Frans Sijstermans ,  Jagadeesh Sankaran ,  Ching Hung ,  Yen-Te Shih ,  Ravi Singh

IPC分类号： G06T7/593

摘要： A hybrid matching approach can be used for computer vision that balances accuracy with speed and resource consumption. Stereoscopic image data can be rectified and downsampled, then analyzed using a semi-global matching (SGM) process. The use of downsampled images greatly reduces time and bandwidth requirements, while providing high accuracy disparity results. These disparity results can be provided as external hints to a fast module that can perform a robust matching process in the time needed for applications such as real time navigation. The external hints can be used, along with potentially other hints, to define a search space for use by the fast module, which can result in higher quality disparity results obtained within specified timing constraints and with limited resources. The disparity results can be used to determine distances to various objects, as may be important for vehicle navigation or robotic task performance.

公开(公告)号：US11636614B2

公开(公告)日：2023-04-25

申请号：US17740763

申请日：2022-05-10

申请人： Mitutoyo Corporation

发明人： Kaoru Miyata

IPC分类号： G06T7/521 ,  G06T7/60 ,  G06T7/593

摘要： A three-dimensional geometry measurement apparatus including: a relationship identification part that identifies a combination of a first imaging pixel and a projection pixel of a projection image; a determination part that determines, for the combination of the first imaging pixel and the projection pixel, whether or not the combination includes a defective pixel on the basis of a distance between (i) a second imaging pixel corresponding to the same projection coordinate as a projection coordinate corresponding to the first imaging pixel and (ii) a second imaging pixel corresponding to the projection coordinate of the projection pixel and located on an epipolar line of a second captured image corresponding to the projection coordinate; and a geometry measurement part that measures a geometry of an object to be measured using at least one of the first imaging pixel excluding the defective pixel or the second imaging pixel excluding the defective pixel.

公开(公告)号：US20230116388A1

公开(公告)日：2023-04-13

申请号：US17940347

申请日：2022-09-08

申请人： OLYMPUS CORPORATION

发明人： Per SUPPA ,  Lorena KRAMES

IPC分类号： G06T7/33 ,  G06T7/593 ,  A61B1/00 ,  A61B1/313

摘要： A method of finding a set of corresponding points in images to be registered. According to the method, an input unit of the system receives a first user input, indicative of a reference point in an intraoperative image. A processing unit sets a reference area surrounding the reference point and converts the image data points in the reference area to a intraoperative point cloud. The input unit receives a second user input, indicative of a candidate point in a preoperative image. The processing unit sets a search area surrounding the reference point and converts the image data points in the reference area to a preoperative point cloud. By comparing geometric feature descriptors of the image data points, the processing unit finds a target point in the preoperative image corresponding to the reference point and defines the points as set of corresponding points.

公开(公告)号：US11620761B2

公开(公告)日：2023-04-04

申请号：US17341218

申请日：2021-06-07

申请人： Microsoft Technology Licensing, LLC

发明人： Navid Poulad ,  Rayna Demaster-Smith

IPC分类号： G06T7/593 ,  G06T7/40 ,  G06T7/11 ,  G06T7/80 ,  H04N13/239 ,  G06T17/00 ,  H04N9/04 ,  G06T15/04 ,  H04N13/344 ,  G02B27/01 ,  G06T7/521 ,  H04N13/00 ,  H04S7/00

摘要： Examples are disclosed that relate to displaying a hologram via an HMD. One disclosed example provides a method comprising obtaining depth data from a direct-measurement depth sensor included in the case for the HMD, the depth data comprising a depth map of a real-world environment. The method further comprises determining a distance from the HMD to an object in the real-world environment using the depth map, obtaining holographic imagery for display based at least upon the distance, and outputting the holographic imagery for display on the HMD.

公开(公告)号：US20230094182A1

公开(公告)日：2023-03-30

申请号：US17958089

申请日：2022-09-30

申请人： Ultrahaptics IP Two Limited

发明人： Kevin A. HOROWITZ ,  David S. HOLZ

IPC分类号： G06T17/10 ,  G06T17/20 ,  G06T7/593 ,  G06T7/11 ,  G06T7/246 ,  G06T7/194 ,  G06T7/136 ,  G06F3/01 ,  G06T19/00 ,  G06T19/20 ,  G06V40/20

摘要： Free space machine interface and control can be facilitated by predictive entities useful in interpreting a control object's position and/or motion (including objects having one or more articulating members, i.e., humans and/or animals and/or machines). Predictive entities can be driven using motion information captured using image information or the equivalents. Predictive information can be improved applying techniques for correlating with information from observations.

公开(公告)号：US11615583B2

公开(公告)日：2023-03-28

申请号：US17467002

申请日：2021-09-03

申请人： Autodesk, Inc.

发明人： Koh Naimin ,  Li Jiang

IPC分类号： G06T15/30 ,  G06T7/593 ,  H04N13/271

摘要： A method, apparatus, and system provide the ability to crop a three-dimensional (3D) scene. The 3D scene is acquired and includes multiple 3D images (with each image from a view angle of an image capture device) and a depth map for each image. The depth values in each depth map are sorted. Multiple initial cutoff depths are determined for the scene based on the view angles of the images (in the scene). A cutoff relaxation depth is determined based on a jump between depth values. A confidence map is generated for each depth map and indicates whether each depth value is above or below the cutoff relaxation depth. The confidence maps are aggregated into an aggregated model. A bounding volume is generated out of the aggregated model. Points are cropped from the scene based on the bounding volume.

公开(公告)号：US11615548B2

公开(公告)日：2023-03-28

申请号：US17124028

申请日：2020-12-16

申请人： Beijing Smarter Eye Technology Co. Ltd.

发明人： Feng Cui ,  Zhao Sun ,  Yongcai Liu ,  Shanshan Pei ,  Jian Li

IPC分类号： G06T7/593 ,  G06T7/80 ,  H04N13/204 ,  H04N13/00

摘要： The present disclosure provides a method for distance measurement based on a binocular camera, a system for distance measurement based on a binocular camera, a device and a computer-readable storage medium. The method includes: taking N images of a distance measurement marker placed at each of Z positions in a depth direction of the binocular camera; calculating an average disparity of the distance measurement marker at the middle position, the left side position and the right side position at each of the Z positions; calculating a distance measurement value at each of the Z positions in the depth direction; calculating a distance measurement error value at the middle position, the left side position and the right side position at each of the Z positions, and acquiring a total error cost function; and calculating extrinsic parameters, so as to acquire a distance measurement result in the depth direction.

公开(公告)号：US20230086983A1

公开(公告)日：2023-03-23

申请号：US17865855

申请日：2022-07-15

申请人： MULTIPLEYE CO., LTD.

发明人： Chang Hee WON

IPC分类号： G06T7/593 ,  H04N5/247 ,  H04N13/271 ,  H04N13/156 ,  G06T7/70 ,  G06T7/10 ,  G06T7/13 ,  G06T7/60

摘要： A method for acquiring a distance from a moving body to an object located in any direction of the moving body includes steps of: an image processing device (a) instructing a sweep network to project pixels of images, generated by cameras covering all directions of the moving body, onto main virtual geometries and apply 3D concatenation operation thereon to generate an initial 4D cost volume, (b) generating a final main 3D cost volume therefrom through a cost volume computation network, and (c) generating sub inverse distance indices corresponding to inverse values of sub separation distances between a sub reference point and sub virtual geometries, and main inverse distance indices corresponding to inverse values of main separation distances between a main reference point and the main virtual geometries, by using a sub cost volume and the final main 3D cost volume, to thereby acquire the distance to the object.

公开(公告)号：US20230084316A1

公开(公告)日：2023-03-16

申请号：US17821346

申请日：2022-08-22

申请人： KACHE.AI

发明人： Anthony Levandowski ,  Eli Riggs ,  Catherine Culkin

IPC分类号： G05D1/00 ,  G06N20/00 ,  G05D1/02 ,  G06T7/80 ,  H04N13/246 ,  G06T7/292 ,  G06T7/593

摘要： Systems and methods for implementing one or more autonomous features for autonomous and semi-autonomous control of one or more vehicles are provided. More specifically, image data may be obtained from an image acquisition device and processed utilizing one or more machine learning models to identify, track, and extract one or more features of the image utilized in decision making processes for providing steering angle and/or acceleration/deceleration input to one or more vehicle controllers. In some instances, techniques may be employed such that the autonomous and semi-autonomous control of a vehicle may change between vehicle follow and lane follow modes. In some instances, at least a portion of the machine learning model may be updated based on one or more conditions.