公开(公告)号：US20240362985A1

公开(公告)日：2024-10-31

申请号：US18307773

申请日：2023-04-26

申请人： T-Mobile USA, Inc.

发明人： Wilfred I. Tucker

IPC分类号： G08B13/196 ,  G06F3/0488 ,  G06T7/73 ,  G06T17/00 ,  G06T19/00 ,  G06V10/74 ,  G06V20/52 ,  G06V20/64 ,  G06V40/10

CPC分类号： G08B13/19684 ,  G06F3/0488 ,  G06T7/73 ,  G06T17/00 ,  G06T19/00 ,  G06V10/761 ,  G06V20/52 ,  G06V20/653 ,  G06V40/10 ,  G06T2200/04 ,  G06T2200/24 ,  G06T2207/30196 ,  G06T2210/56

摘要： The document discloses technology that improves the ability of a user to detect and deter the presence of an entity (e.g., person, animal) in a selected area. The system generates a three-dimensional (3D) point map of an environment. The system can then use 3D imaging technology such as LiDAR (light detection and ranging) to generate a baseline 3D point map that includes the selected area within the environment. In operation, the system can use the 3D technology to monitor for the entity and provide alerts in real time or near real time when the entity is present in the selected area, and/or the system can perform a deterrent action that is perceivable by the entity.

公开(公告)号：US20240362875A1

公开(公告)日：2024-10-31

申请号：US18335204

申请日：2023-06-15

申请人： Hong Kong Centre for Logistics Robotics Limited

发明人： Yunhui Liu ,  Xueyan Tang

IPC分类号： G06T19/20 ,  G06T7/13 ,  G06T7/60

CPC分类号： G06T19/20 ,  G06T7/13 ,  G06T7/60 ,  G06T2207/10028 ,  G06T2210/56 ,  G06T2219/2004

摘要： A computer-implemented method of aligning a source model with a target model includes receiving the source model and the target model, identifying geometric features in each of the source model and target model, assigning a feature vector to each feature, defining an associated geometry type, position, direction and magnitude for the feature, pairing each feature vector in the source model with each other feature vector in the source model and pairing each feature vector in the target model with each other feature vector in the target model, calculating a pair vector for each pairing, defining the geometry type of each feature vector in the pairing, the dimension of each feature vector in the pairing, a relative orientation and separation distance, identifying matching pair vectors between the source model and target model; and calculating a transformation matrix between the source model and target model based on the matching pair vectors.

公开(公告)号：US20240359095A1

公开(公告)日：2024-10-31

申请号：US18763530

申请日：2024-07-03

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Chao SHEN

IPC分类号： A63F13/52 ,  G06T7/55 ,  G06T7/73 ,  G06T7/90 ,  G06T19/20

CPC分类号： A63F13/52 ,  G06T7/55 ,  G06T7/74 ,  G06T7/90 ,  G06T19/20 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30244 ,  G06T2210/12 ,  G06T2210/56 ,  G06T2219/2008 ,  G06T2219/2012 ,  G06T2219/2024

摘要： A virtual-environment-based object construction method and apparatus, and a computer-readable storage medium are disclosed in this disclosure, relating to the field of virtual environment. Performed by a terminal comprising a camera, the method including: displaying an environment interface; receiving a capture operation being used for acquiring three-dimensional (3D) information of a to-be-acquired object; receiving a position input operation for determining a display position of the target object in the virtual environment; and displaying the target object at the display position in the virtual environment according to the capture operation and the position input operation.

公开(公告)号：US20240354971A1

公开(公告)日：2024-10-24

申请号：US18760359

申请日：2024-07-01

申请人： InterDigital Madison Patent Holdings, SAS

发明人： Tatu V J HARVIAINEN

IPC分类号： G06T7/33 ,  G06T7/38 ,  G06T19/20

CPC分类号： G06T7/33 ,  G06T7/38 ,  G06T19/20 ,  G06T2210/56

摘要： Apparatuses and methods are disclosed including techniques for optimizing the transmission of dynamic point clouds to a client. The disclosed techniques include obtaining a reference point cloud representing a first point cloud in a time sequence of point clouds; receiving a series of representations of changes to the reference point cloud, where each representation specifies an area of the reference point cloud and a change to be applied to the specified area, each such change comprises at least one of a 3D transformation, a set of points to be added to the reference point cloud, and a set of points to be removed from the reference point cloud; and successively applying the representations to the reference point cloud to generate a point cloud representing a second point cloud in the time sequence of point clouds.

公开(公告)号：US20240331292A1

公开(公告)日：2024-10-03

申请号：US18128979

申请日：2023-03-30

申请人： STREEM, LLC.

发明人： Ghislain Tasse ,  Nikilesh Urella ,  Pavan K. Kamaraju

IPC分类号： G06T17/20 ,  G06T7/11 ,  G06T19/20

CPC分类号： G06T17/20 ,  G06T7/11 ,  G06T19/20 ,  G06T2207/20084 ,  G06T2210/56 ,  G06T2219/2021

摘要： Embodiments include systems, processes, and/or techniques for creating a semantically segmented 3D mesh of a physical environment, where the semantically segmented 3D mesh may be at least partially created by a first user, and where a second user, for example a service professional, may view and modify one of the segments of the semantically segmented 3D mesh for subsequent viewing by the first user. Other embodiments may be described and/or claimed.

公开(公告)号：US12100107B2

公开(公告)日：2024-09-24

申请号：US18353592

申请日：2023-07-17

申请人： QUALCOMM Incorporated

发明人： Ke-Li Cheng ,  Kuang-Man Huang ,  Michel Adib Sarkis ,  Gerhard Reitmayr ,  Ning Bi

IPC分类号： G06T17/20 ,  G06T7/12 ,  G06T19/00

CPC分类号： G06T17/205 ,  G06T7/12 ,  G06T19/006 ,  G06T2210/56

摘要： Techniques are provided for generating three-dimensional models of objects from one or more images or frames. For example, at least one frame of an object in a scene can be obtained. A portion of the object is positioned on a plane in the at least one frame. The plane can be detected in the at least one frame and, based on the detected plane, the object can be segmented from the plane in the at least one frame. A three-dimensional (3D) model of the object can be generated based on segmenting the object from the plane. A refined mesh can be generated for a portion of the 3D model corresponding to the portion of the object positioned on the plane.

公开(公告)号：US12094056B2

公开(公告)日：2024-09-17

申请号：US18315634

申请日：2023-05-11

申请人： Willow Garage, LLC

发明人： Wim Meeussen ,  Eitan Marder-Eppstein ,  Stuart Glaser

IPC分类号： G06T17/00 ,  G01S17/89 ,  G06T15/10 ,  G06T15/20 ,  G06T17/05

CPC分类号： G06T17/005 ,  G06T15/10 ,  G06T15/20 ,  G06T17/05 ,  G01S17/89 ,  G06T2200/24 ,  G06T2207/10028 ,  G06T2210/36 ,  G06T2210/56

摘要： One embodiment is directed to a method for presenting views of a very large point data set, comprising: storing data on a storage system that is representative of a point cloud comprising a very large number of associated points; automatically and deterministically organizing the data into an octree hierarchy of data sectors, each of which is representative of one or more of the points at a given octree mesh resolution; receiving a command from a user of a user interface to present an image based at least in part upon a selected viewing perspective origin and vector; and assembling the image based at least in part upon the selected origin and vector, the image comprising a plurality of data sectors pulled from the octree hierarchy.

公开(公告)号：US20240290108A1

公开(公告)日：2024-08-29

申请号：US18693125

申请日：2022-08-04

申请人： SONY SEMICONDUCTOR SOLUTIONS CORPORATION

发明人： Yusuke KOMATSU

IPC分类号： G06V20/58 ,  G01S13/86 ,  G01S13/89 ,  G01S13/931 ,  G06T15/04 ,  G06T17/00 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82

CPC分类号： G06V20/58 ,  G01S13/867 ,  G01S13/89 ,  G01S13/931 ,  G06T15/04 ,  G06T17/00 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G01S2013/932 ,  G06T2210/56

摘要： Provided is an information processing apparatus that processes sensor data including speed information of an object. The information processing apparatus includes a generation unit that generates a sensing image on the basis of the sensor data including the speed information of the object, and a detection unit that detects the object from the sensing image using a learned model. The generation unit projects the sensor data including a three-dimensional point cloud on a two-dimensional plane to generate the sensing image having a pixel value corresponding to the speed information. The detection unit performs object detection using the learned model learned to recognize the object included in the sensing image.

公开(公告)号：US20240289992A1

公开(公告)日：2024-08-29

申请号：US18652147

申请日：2024-05-01

申请人： HYUNDAI MOTOR COMPANY ,  KIA CORPORATION ,  DIGITALINSIGHTS INC.

发明人： Yong Jo Ahn ,  Jong Seok Lee ,  Jin Heo ,  Seung Wook Park

IPC分类号： G06T9/00 ,  G06T17/00

CPC分类号： G06T9/00 ,  G06T17/00 ,  G06T2210/56

摘要： A LiDAR point cloud coding method includes determining, from LiDAR information, a coding block that is a point cloud encoding/decoding unit, to improve the LiDAR point cloud coding efficiency. The LiDAR point cloud coding method also includes encoding/decoding points on a per coding block basis.

公开(公告)号：US20240282013A1

公开(公告)日：2024-08-22

申请号：US18571361

申请日：2022-06-20

申请人： InterDigital Patent Holdings, Inc.

发明人： Jiahao PANG ,  Dong TIAN ,  Maurice QUACH ,  Giuseppe VALENZISE ,  Frederic DUFAUX

IPC分类号： G06T9/00 ,  G06T17/00

CPC分类号： G06T9/002 ,  G06T17/00 ,  G06T2210/56

摘要： In one implementation, we propose the UnfoldingOperator, which unfolds/flattens an unorganized input 3D point cloud onto a regular 2D grid. Given an input point cloud, an input 2D grid and the reconstructed point cloud produced by the FoldingNet, our proposal maps the input point cloud onto the 2D grid based on the reconstructed point cloud, leading to a 3-channel image. Alternatively, instead of using an image alone to represent a point cloud, the point cloud is decomposed into a codeword and a 3-channel residual image. This residual image is obtained by subtracting the reconstructed point cloud from the original input. The proposed UnfoldingOperator can be applied to point cloud compression, leading to a corresponding compression system that we call UnfoldingCompression. The UnfoldingCompression can work with the TearingCompression, where we can adaptively choose whether to use the UnfoldingCompression or TearingCompression.