面向车辆盲区防撞系统的交通目标智能检测

瓢正泉; 唐林波; 赵保军; 曾涛

doi:10.16798/j.issn.1003-0530.2021.02.009

面向车辆盲区防撞系统的交通目标智能检测

北京理工大学信息与电子学院雷达技术研究所

基金项目: 国家自然科学基金（31727901）

详细信息

中图分类号: TP751.1
计量
- 文章访问数: 204
- HTML全文浏览量: 16
- PDF下载量: 264
出版历程
- 收稿日期: 2020-11-05
- 修回日期: 2021-02-02
- 发布日期: 2021-02-24

Intelligent detection of traffic targets for vehicle blind zone collision avoidance system

Radar Research Lab,School of Information and Electronics, Beijing Institute of Technology

摘要

摘要: 交通目标智能检测是车辆盲区智能防撞系统中的基础技术，该技术的研究和应用对降低交通事故损失具有重要意义。本文面向车辆盲区防撞系统设计的检测模型，其在基础模型中融合了两个性能提升策略。将该模型应用于国内和国外道路场景检测数据集，以验证模型在所有范围和近距离目标的检测性能。实验结果表明该模型可以对近距目标表现出较高的检测精度，且具有较高的检测速度，因此该模型可适用于车辆低速启动或者转弯时智能盲区防撞系统对交通目标的检测需求。
- 道路场景 /
- 目标检测 /
- 深度网络 /
- 智能防撞
Abstract: Intelligent detection of traffic targets is the basic technology in the intelligent collision avoidance system for vehicle blind spots. The research and application of this technology is of great significance to reduce the loss of traffic accidents. In this paper, a detection model for vehicle blind zone collision avoidance system design, which combines two performance improvement strategies in the basic model. The model is applied to domestic and foreign road scene detection data sets to verify the detection performance of the model in all ranges and short-range targets. Experimental results show that the model can show high detection accuracy for close targets and has a high detection speed. Therefore, the model can be applied to the detection requirements of the intelligent blind zone collision avoidance system for traffic targets when the vehicle starts at low speed or when turning.
- road scene /
- object detection /
- deep networks /
- intelligent collision avoidance

HTML全文

参考文献(25)

[1]	Board U. Vehicle-and Infrastructure-based Technology for the Prevention of Rear-end Collisions, ser[J]. Special investigation report. National Transportation Safety Board, 2001.
[2]	Pan W , Lucas C , Tasmia R , et al. LiDAR and Camera Detection Fusion in a Real Time Industrial Multi-Sensor Collision Avoidance System[J]. Electronics, 2018, 7(6):84-.
[3]	Sotelo M á, Barriga J. Blind spot detection using vision for automotive applications[J]. Journal of Zhejiang University-Science A, 2008, 9(10): 1369-1372.
[4]	Ra M , Jung H G , Suhr J K , et al. Part-based Vehicle Detection in Side-rectilinear Images for Blind-Spot Detection[J]. Expert Systems with Applications,2018:S0957417418300757.
[5]	Zhao, Yiming, Bai, et al. Camera-Based Blind Spot Detection with a General Purpose Lightweight Neural Network[J]. Electronics, 2019.
[6]	Ba Y, Zhang W, Wang Q, et al. Crash prediction with behavioral and physiological features for advanced vehicle collision avoidance system[J]. Transportation Research Part C: Emerging Technologies, 2017, 74: 22-33.
[7]	Zhuang J, Zhang L, Zhao S, et al. Radar-based collision avoidance for unmanned surface vehicles[J]. China Ocean Engineering, 2016, 30(6): 867-883.
[8]	Liu G , Zhou M , Wang L , et al. A blind spot detection and warning system based on millimeter wave radar for driver assistance[J]. Optik - International Journal for Light and Electron Optics, 2017, 135:353-365.
[9]	王敏, 周树道, 彭文星,等. 基于超声波传感器的汽车盲区检测系统研究[J]. 自动化技术与应用, 2017(3).
[10]	Wang Min, Zhou Shudao, Peng Wenxing, et al. Research on Vehicle Blind Spot Detection System Based on Ultrasonic Sensor[J]. Automation Technology and Application, 2017(3). (in Chinese)
[11]	杨思思. 基于单目视觉的车辆盲区预警系统的研究及实现[D]. 2015.
[12]	Yang Sisi. Vehicle Blind Spot Warning Algorithm Research and Svstem Design based on Monocular Vision[D]. 2015. (in Chinese)
[13]	DALAL,N. Histograms of oriented gradients for human detection[J]. Proc of Cvpr, 2005.
[14]	Dollár P, Tu Z, Perona P, et al. Integral channel features[J]. 2009.
[15]	Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C], Advances in neural information processing systems. 2012: 1097-1105.
[16]	Girshick R. Fast r-cnn[C], Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.
[17]	Redmon J , Divvala S , Girshick R , et al. You Only Look Once: Unified, Real-Time Object Detection[J]. 2015.
[18]	Law H, Deng J. Cornernet: Detecting objects as paired keypoints[C], Proceedings of the European Conference on Computer Vision (ECCV). 2018: 734-750.
[19]	Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.
[20]	Zhang H, Cisse M, Dauphin Y N, et al. mixup: Beyond empirical risk minimization[J]. arXiv preprint arXiv:1710.09412, 2017.
[21]	Yun S, Han D, Oh S J, et al. Cutmix: Regularization strategy to train strong classifiers with localizable features[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 6023-6032.
[22]	Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. arXiv preprint arXiv:2004.10934, 2020.
[23]	Rezatofighi H, Tsoi N, Gwak J Y, et al. Generalized intersection over union: A metric and a loss for bounding box regression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 658-666.
[24]	Huang X, Cheng X, Geng Q, et al. The apolloscape dataset for autonomous driving[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018: 954-960.
[25]	Yu F, Chen H, Wang X, et al. BDD100K: A diverse driving dataset for heterogeneous multitask learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 2636-2645.