Radar Camera Fusion via Representation Learning in Autonomous Driving

被引:28
|
作者
Dong, Xu [1 ]
Zhuang, Binnan [1 ]
Mao, Yunxiang [1 ]
Liu, Langechuan [1 ]
机构
[1] XSense Ai, 11010 Roselle St, San Diego, CA 92121 USA
关键词
D O I
10.1109/CVPRW53098.2021.00183
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Radars and cameras are mature, cost-effective, and robust sensors and have been widely used in the perception stack of mass-produced autonomous driving systems. Due to their complementary properties, outputs from radar detection (radar pins) and camera perception (2D bounding boxes) are usually fused to generate the best perception results. The key to successful radar-camera fusion is the accurate data association. The challenges in the radar-camera association can be attributed to the complexity of driving scenes, the noisy and sparse nature of radar measurements, and the depth ambiguity from 2D bounding boxes. Traditional rule-based association methods are susceptible to performance degradation in challenging scenarios and failure in corner cases. In this study, we propose to address radar-camera association via deep representation learning, to explore feature-level interaction and global reasoning. Additionally, we design a loss sampling mechanism and an innovative ordinal loss to overcome the difficulty of imperfect labeling and to enforce critical human-like reasoning. Despite being trained with noisy labels generated by a rule-based algorithm, our proposed method achieves a performance of 92.2% F1 score, which is 11.6% higher than the rule-based teacher. Moreover, this data-driven method also lends itself to continuous improvement via corner case mining.
引用
收藏
页码:1672 / 1681
页数:10
相关论文
共 50 条
  • [21] Road-objects tracking for autonomous driving using lidar and radar fusion
    Farag, Wael
    JOURNAL OF ELECTRICAL ENGINEERING-ELEKTROTECHNICKY CASOPIS, 2020, 71 (03): : 138 - 149
  • [22] Surrounding Objects Detection and Tracking for Autonomous Driving Using LiDAR and Radar Fusion
    Ze Liu
    Yingfeng Cai
    Hai Wang
    Long Chen
    Chinese Journal of Mechanical Engineering, 2021, 34 (05) : 85 - 96
  • [23] Surrounding Objects Detection and Tracking for Autonomous Driving Using LiDAR and Radar Fusion
    Ze Liu
    Yingfeng Cai
    Hai Wang
    Long Chen
    Chinese Journal of Mechanical Engineering, 2021, 34
  • [24] Surrounding Objects Detection and Tracking for Autonomous Driving Using LiDAR and Radar Fusion
    Liu, Ze
    Cai, Yingfeng
    Wang, Hai
    Chen, Long
    CHINESE JOURNAL OF MECHANICAL ENGINEERING, 2021, 34 (01)
  • [25] Video Representation Learning for Decoupled Deep Reinforcement Learning Applied to Autonomous Driving
    Mohammed, Shawan Taha
    Kastouri, Mohamed
    Niederfahrenhorst, Artur
    Ascheid, Gerd
    2023 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION, SII, 2023,
  • [26] WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces
    Yao, Shanliang
    Guan, Runwei
    Wu, Zhaodong
    Ni, Yi
    Huang, Zile
    Liu, Ryan Wen
    Yue, Yong
    Ding, Weiping
    Lim, Eng Gee
    Seo, Hyungjoon
    Man, Ka Lok
    Ma, Jieming
    Zhu, Xiaohui
    Yue, Yutao
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (11) : 16584 - 16598
  • [27] Multimodal Object Detection and Ranging Based on Camera and Lidar Sensor Fusion for Autonomous Driving
    Khan, Danish
    Baek, Minjin
    Kim, Min Young
    Han, Dong Seog
    2022 27TH ASIA PACIFIC CONFERENCE ON COMMUNICATIONS (APCC 2022): CREATING INNOVATIVE COMMUNICATION TECHNOLOGIES FOR POST-PANDEMIC ERA, 2022, : 342 - 343
  • [28] Introspective Failure Prediction for Autonomous Driving Using Late Fusion of State and Camera Information
    Kuhn, Christopher B.
    Hofbauer, Markus
    Petrovic, Goran
    Steinbach, Eckehard
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (05) : 4445 - 4459
  • [29] Object detection using depth completion and camera-LiDAR fusion for autonomous driving
    Carranza-Garcia, Manuel
    Javier Galan-Sales, F.
    Maria Luna-Romera, Jose
    Riquelme, Jose C.
    INTEGRATED COMPUTER-AIDED ENGINEERING, 2022, 29 (03) : 241 - 258
  • [30] Radar Fault Detection via Camera-Radar Branches Learning Network
    Ning, Dian
    Han, Dong Seog
    2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC, 2023, : 463 - 467