SIA OpenIR  > 光电信息技术研究室
RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving
Li PX(李培玄)1,2,3,5,6; Su S(苏顺)1,2,3,4; Zhao HC(赵怀慈)1,2,5,6
Department光电信息技术研究室
Conference Name35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence
Conference DateFebuary 2-9, 2021
Conference PlaceELECTR NETWORK
Author of SourceAssociation for the Advancement of Artificial Intelligence
Source PublicationTHIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
PublisherAAAI
Publication PlacePalo Alto, California
2021
Pages1930-1939
Indexed ByCPCI(ISTP)
WOS IDWOS:000680423502003
Contribution Rank1
ISSN2159-5399
ISBN978-1-57735-866-4
AbstractAlthough the recent image-based 3D object detection methods using Pseudo-LiDAR representation have shown great capabilities, a notable gap in efficiency and accuracy still exist compared with LiDAR-based methods. Besides, over-reliance on the stand-alone depth estimator, requiring a large number of pixel-wise annotations in the training stage and more computation in the inferencing stage, limits the scaling application in the real world. In this paper, we propose an efficient and accurate 3D object detection method from stereo images, named RTS3D. Different from the 3D occupancy space in the Pseudo-LiDAR similar methods, we design a novel 4D feature-consistent embedding (FCE) space as the intermediate representation of the 3D scene without depth supervision. The FCE space encodes the object's structural and semantic information by exploring the multi-scale feature consistency warped from stereo pair. Furthermore, a semantic-guided RBF (Radial Basis Function) and a structure-aware attention module are devised to reduce the influence of FCE space noise without instance mask supervision. Experiments on the KITTI benchmark show that RTS3D is the first true real-time system (FPS >24) for stereo image 3D detection meanwhile achieves 10% improvement in average precision comparing with the previous state-of-the-art method.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/29554
Collection光电信息技术研究室
机器人学研究室
Corresponding AuthorZhao HC(赵怀慈)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
5.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences
6.Key Lab of Image Understanding and Computer Vision, Liaoning Province
Recommended Citation
GB/T 7714
Li PX,Su S,Zhao HC. RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving[C]//Association for the Advancement of Artificial Intelligence. Palo Alto, California:AAAI,2021:1930-1939.
Files in This Item:
File Name/Size DocType Version Access License
RTS3D_ Real-time Ste(2213KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li PX(李培玄)]'s Articles
[Su S(苏顺)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li PX(李培玄)]'s Articles
[Su S(苏顺)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li PX(李培玄)]'s Articles
[Su S(苏顺)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: RTS3D_ Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.