公开(公告)号：US11100702B2

公开(公告)日：2021-08-24

申请号：US16728358

申请日：2019-12-27

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Chung-Hsien Yang ,  Bo-Chun Hsu ,  Chih-Hao Cheng ,  Po-Sheng Huang ,  Chih-Hsiang Chan

IPC: G06T17/00 ,  G06K9/62 ,  G06K9/00

Abstract: A 3D image labeling device and a 3D image labeling method are provided. The 3D image labeling device includes a point cloud cluster module, a projection module, an integration module and a point cloud recovery module. The point cloud cluster module clusters multiple points of a 3D unlabeled image as one or more first point clusters according to a 3D unlabeled image and a cluster algorithm to generate a 3D clustered image. The projection module generates a first 2D image with first objects according to the 3D clustered image, wherein each first point cluster corresponds to one of the first objects. The integration module labels the first objects of the first 2D image according to one or more object frames of a 2D labeled image to generate a second 2D image. The point cloud recovery module generates a 3D labeled image according to the second 2D image.

公开(公告)号：US11024055B2

公开(公告)日：2021-06-01

申请号：US16508471

申请日：2019-07-11

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Bo-Chun Hsu ,  Wei-Po Nien ,  Yi-Ling Wu ,  Hsiu-Yu Lin ,  Shi-Xin Chen ,  An-Kai Jeng ,  Chung-Hsien Yang

IPC: G01S17/931 ,  G06T7/73 ,  H04N13/156 ,  H04N13/293 ,  G01S17/89 ,  G01S17/42

Abstract: A vehicle, a vehicle positioning system and a vehicle positioning method are provided. The vehicle positioning system includes a 2D image sensor, a 3D sensor and a processor. The 2D image sensor is configured for obtaining 2D image data. The 3D sensor is configured for obtaining 3D point cloud data. The processor is coupled to the 2D image sensor and the 3D sensor, and configured for merging the 2D image data and the 3D point cloud data to generate 3D image data, identifying at least one static object from the 2D image data, obtaining 3D point cloud data of the static object from the 3D image data based on each one of the at least one static object, and calculating a vehicle relative coordinate of the vehicle based on the 3D point cloud data of the static object.

公开(公告)号：US20200175720A1

公开(公告)日：2020-06-04

申请号：US16508471

申请日：2019-07-11

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Bo-Chun Hsu ,  Wei-Po Nien ,  Yi-Ling Wu ,  Hsiu-Yu Lin ,  Shi-Xin Chen ,  An-Kai Jeng ,  Chung-Hsien Yang

IPC: G06T7/73 ,  H04N13/156 ,  H04N13/293 ,  G01S17/42 ,  G01S17/89 ,  G01S17/93

Abstract: A vehicle, a vehicle positioning system and a vehicle positioning method are provided. The vehicle positioning system includes a 2D image sensor, a 3D sensor and a processor. The 2D image sensor is configured for obtaining 2D image data. The 3D sensor is configured for obtaining 3D point cloud data. The processor is coupled to the 2D image sensor and the 3D sensor, and configured for merging the 2D image data and the 3D point cloud data to generate 3D image data, identifying at least one static object from the 2D image data, obtaining 3D point cloud data of the static object from the 3D image data based on each one of the at least one static object, and calculating a vehicle relative coordinate of the vehicle based on the 3D point cloud data of the static object.