Invention Grant
- Patent Title: Output of a neural network method for deep odometry assisted by static scene optical flow
-
Application No.: US15703885Application Date: 2017-09-13
-
Publication No.: US10552979B2Publication Date: 2020-02-04
- Inventor: Wentao Zhu , Yi Wang , Yi Luo
- Applicant: TUSIMPLE
- Applicant Address: US CA San Diego
- Assignee: TUSIMPLE
- Current Assignee: TUSIMPLE
- Current Assignee Address: US CA San Diego
- Agency: Perkins Coie LLP
- Main IPC: G05D1/02
- IPC: G05D1/02 ; G06K9/32 ; G06T7/55 ; G06T7/73

Abstract:
A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs includes instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: performing data alignment among sensors including a LiDAR, cameras and an IMU-GPS module; collecting image data and generating point clouds; processing, in the IMU-GPS module, a pair of consecutive images in the image data to recognize pixels corresponding to a same point in the point clouds; and establishing an optical flow for visual odometry.
Public/Granted literature
- US20190080470A1 OUTPUT OF A NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW Public/Granted day:2019-03-14
Information query