Scene-aware Learning Network for Radar Object Detection

被引:6
|
作者
Zheng, Zangwei [1 ]
Yue, Xiangyu [2 ]
Keutzer, Kurt [2 ]
Vincentelli, Alberto Sangiovanni [2 ]
机构
[1] Nanjing Univ, Nanjing, Peoples R China
[2] Univ Calif Berkeley, Berkeley, CA USA
关键词
Auto-driving; Radar Frequency Data; Object Detection; Neural Network; Data Augmentation;
D O I
10.1145/3460426.3463655
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in self-driving. However, cameras tend to fail in bad driving conditions, e.g. bad weather or weak lighting, while LiDAR scanners are too expensive to get widely deployed in commercial applications. Radar has been drawing more and more attention due to its robustness and low cost. In this paper, we propose a scene-aware radar learning framework for accurate and robust object detection. First, the learning framework contains branches conditioning on the scene category of the radar sequence; with each branch optimized for a specific type of scene. Second, three different 3D autoencoder-based architectures are proposed for radar object detection and ensemble learning is performed over the different architectures to further boost the final performance. Third, we propose novel scene-aware sequence mix augmentation (SceneMix) and scene-specific post-processing to generate more robust detection results. In the ROD2021 Challenge, we achieved a final result of average precision of 75.0% and an average recall of 81.0%. Moreover, in the parking lot scene, our framework ranks first with an average precision of 97.8% and an average recall of 98.6%, which demonstrates the effectiveness of our framework.
引用
收藏
页码:573 / 579
页数:7
相关论文
共 50 条
  • [1] LEARNING SELECTIVE ASSIGNMENT NETWORK FOR SCENE-AWARE VEHICLE DETECTION
    Wang, Zhenting
    Li, Wei
    Wu, Xiao
    Sheng, Luhan
    2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 1366 - 1370
  • [2] Video Object Counting With Scene-Aware Multi-Object Tracking
    Li, Yongdong
    Qu, Liang
    Cai, Guiyan
    Cheng, Guoan
    Qian, Long
    Dou, Yuling
    Yao, Fengqin
    Wang, Shengke
    JOURNAL OF DATABASE MANAGEMENT, 2023, 34 (03)
  • [3] Scene-aware Generative Network for Human Motion Synthesis
    Wang, Jingbo
    Yan, Sijie
    Dai, Bo
    Lin, Dahua
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 12201 - 12210
  • [4] Gated Hypergraph Neural Network for Scene-Aware Recommendation
    Yang, Tianchi
    Zhang, Luhao
    Shi, Chuan
    Yang, Cheng
    Xu, Siyong
    Fang, Ruiyu
    Hu, Maodi
    Liu, Huaijun
    Li, Tao
    Wang, Dong
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT II, 2022, : 199 - 215
  • [5] Scene-Aware Ensemble Learning for Robust Crowd Counting
    Xu, Ling
    Huang, Kefeng
    Sun, Kaiyu
    Yang, Xiaokang
    Zhang, Chongyang
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2021, PT II, 2021, 13020 : 360 - 372
  • [6] A Novel Scene-aware Pedestrian Detection in Dense Scenes
    Chen, Ting
    Chen, Jinghua
    Gao, Tao
    Zhu, Shukang
    Guo, Zongyang
    Liu, Zixiang
    Li, Ziqi
    Zhao, Quanzhao
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 1316 - 1321
  • [7] Scene-aware Foveated Rendering
    Fan, Runze
    Shi, Xuehuai
    Wang, Kangyu
    Ma, Qixiang
    Wang, Lili
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2024, 30 (11) : 7097 - 7106
  • [8] People Localization in a Camera Network Combining Background Subtraction and Scene-Aware Human Detection
    Lee, Tung-Ying
    Lin, Tsung-Yu
    Huang, Szu-Hao
    Lai, Shang-Hong
    Hung, Shang-Chih
    ADVANCES IN MULTIMEDIA MODELING, PT I, 2011, 6523 : 151 - +
  • [9] SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test
    Kou, Jie
    Zhang, Xinman
    Huang, Yuxuan
    Zhang, Cong
    SENSORS, 2021, 21 (13)
  • [10] Scene-Aware Feature Matching
    Lu, Xiaoyong
    Yan, Yaping
    Wei, Tong
    Du, Songlin
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 3681 - 3690