Title:
DEPTH IMAGE PROCESSING METHOD, SMALL OBSTACLE DETECTION METHOD AND SYSTEM, ROBOT, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/147545
Kind Code:
A1
Abstract:
Provided are a depth image processing method, and a small obstacle detection method and system. The method comprises calibration of sensors, distortion and epipolar rectification, data alignment, and sparse stereo matching. The depth image processing method and the small obstacle detection method and system of the present invention only require execution of sparse stereo matching on hole portions of a structured light depth image, and do not require stereo matching of the entire image, thereby significantly reducing the overall computation load for processing a depth image, and enhancing the robustness of a system.
Inventors:
LIU YONG (CN)
ZHU JUN AN (CN)
HUANG YIN (CN)
GUO CONG (CN)
ZHU JUN AN (CN)
HUANG YIN (CN)
GUO CONG (CN)
Application Number:
PCT/CN2020/135024
Publication Date:
July 29, 2021
Filing Date:
December 09, 2020
Export Citation:
Assignee:
SHENZHEN PUDU TECH CO LTD (CN)
International Classes:
G06T7/593
Foreign References:
| CN111260715A | 2020-06-09 | |||
| CN106796728A | 2017-05-31 | |||
| CN110264510A | 2019-09-20 | |||
| CN108230403A | 2018-06-29 | |||
| US20190130773A1 | 2019-05-02 |
Other References:
See also references of EP 4083917A4
Attorney, Agent or Firm:
SHENZHEN ZHONGDING INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF:
Previous Patent: MONITORING METHOD AND APPARATUS
Next Patent: MULTI-SENSOR FUSION SLAM SYSTEM, MULTI-SENSOR FUSION METHOD, ROBOT, AND MEDIUM
Next Patent: MULTI-SENSOR FUSION SLAM SYSTEM, MULTI-SENSOR FUSION METHOD, ROBOT, AND MEDIUM