Title:
TARGET DETECTION METHOD AND RELATED DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/178895
Kind Code:
A1
Abstract:
The present application discloses an autonomous driving technique in the field of artificial intelligence, and specifically discloses a target detection method and a related device. The method comprises: respectively performing voxelization on a target object at a plurality of first angles of view according to a point cloud eigenvector, so as to obtain a plurality of first pseudo-images, wherein the point cloud eigenvector is an eigenvector used to describe a point cloud of the target object; obtaining a first feature according to the plurality of first pseudo-images; performing voxelization on the target object at a second angle of view according to the first feature, so as to obtain a second pseudo-image; and determining the target object according to the second pseudo-image. According to the embodiments of the present application, during three-dimensional target detection, high performance and hardware friendliness can both be achieved.
Inventors:
YE CHAOQIANG (CN)
CHENG CHANGHAO (CN)
YANG ZHEN (CN)
ZHANG WEI (CN)
ZHANG HONGBO (CN)
CHENG CHANGHAO (CN)
YANG ZHEN (CN)
ZHANG WEI (CN)
ZHANG HONGBO (CN)
Application Number:
PCT/CN2021/078340
Publication Date:
September 01, 2022
Filing Date:
February 27, 2021
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06T15/00
Foreign References:
| CN111951368A | 2020-11-17 | |||
| CN111476822A | 2020-07-31 | |||
| US20140306955A1 | 2014-10-16 | |||
| US6556199B1 | 2003-04-29 | |||
| CN112257637A | 2021-01-22 |
Other References:
YIN ZHOU; PEI SUN; YU ZHANG; DRAGOMIR ANGUELOV; JIYANG GAO; TOM OUYANG; JAMES GUO; JIQUAN NGIAM; VIJAY VASUDEVAN: "End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 15 October 2019 (2019-10-15), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081515626
SU HANG; MAJI SUBHRANSU; KALOGERAKIS EVANGELOS; LEARNED-MILLER ERIK: "Multi-view Convolutional Neural Networks for 3D Shape Recognition", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 7 December 2015 (2015-12-07), pages 945 - 953, XP032866419, DOI: 10.1109/ICCV.2015.114
SU HANG; MAJI SUBHRANSU; KALOGERAKIS EVANGELOS; LEARNED-MILLER ERIK: "Multi-view Convolutional Neural Networks for 3D Shape Recognition", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 7 December 2015 (2015-12-07), pages 945 - 953, XP032866419, DOI: 10.1109/ICCV.2015.114
Attorney, Agent or Firm:
SCIHEAD IP LAW FIRM (CN)
Download PDF:
Previous Patent: COIL WINDING STRUCTURE
Next Patent: WIRELESS FIDELITY (WIFI) COMMUNICATION METHOD AND APPARATUS
Next Patent: WIRELESS FIDELITY (WIFI) COMMUNICATION METHOD AND APPARATUS