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
  • [1] Radar and Camera Sensor Fusion with ROS for Autonomous Driving
    Kumar, Rahul
    Jayashankar, Sujay
    2019 FIFTH INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP 2019), 2019, : 568 - 573
  • [2] An Asymmetric Radar-Camera Fusion Framework for Autonomous Driving
    Su, Zhiyi
    Ming, Binbin
    Hua, Wei
    2023 IEEE SENSORS, 2023,
  • [3] Exploring Data Variance challenges in Fusion of Radar and Camera for Robotics and Autonomous Driving
    Hussain, Muhammad Ishfaq
    Rafique, Muhammad Aasim
    Khurbaev, Sayfullokh
    Jeon, Moongu
    2022 10TH INTERNATIONAL CONFERENCE ON CONTROL, MECHATRONICS AND AUTOMATION (ICCMA 2022), 2022, : 7 - 12
  • [4] Robust tracking and detection based on radar camera fusion filtering in urban autonomous driving
    Baek, Seoha
    Kim, Jongho
    Yi, Kyongsu
    INTELLIGENT SERVICE ROBOTICS, 2024, 17 (06) : 1125 - 1141
  • [5] A Multi-scale Fusion Obstacle Detection Algorithm for Autonomous Driving Based on Camera and Radar
    He, Sihuang
    Lin, Chen
    Hu, Zhaohui
    SAE INTERNATIONAL JOURNAL OF CONNECTED AND AUTOMATED VEHICLES, 2023, 6 (03):
  • [6] Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
    Yao, Shanliang
    Guan, Runwei
    Huang, Xiaoyu
    Li, Zhuoxiao
    Sha, Xiangyu
    Yue, Yong
    Lim, Eng Gee
    Seo, Hyungjoon
    Man, Ka Lok
    Zhu, Xiaohui
    Yue, Yutao
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2024, 9 (01): : 2094 - 2128
  • [7] A New Approach to Lidar and Camera Fusion for Autonomous Driving
    Bae, Seunghwan
    Han, Dongun
    Park, Seongkeun
    2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC, 2023, : 751 - 753
  • [8] Representation Learning for Vision-Based Autonomous Driving via Probabilistic World Modeling
    Chen, Haoqiang
    Liu, Yadong
    Hu, Dewen
    MACHINES, 2025, 13 (03)
  • [9] Autonomous Obstacle Avoidance for UAV based on Fusion of Radar and Monocular Camera
    Hang Yu
    Fan Zhang
    Huang, Panfeng
    Chen Wang
    Li Yuanhao
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 5954 - 5961
  • [10] Fusing mmWave Radar With Camera for 3-D Detection in Autonomous Driving
    Liu, Yangyang
    Chang, Shuo
    Wei, Zhiqing
    Zhang, Kezhong
    Feng, Zhiyong
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (20) : 20408 - 20421