Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (8): 103-111.DOI: 10.3778/j.issn.1002-8331.2008-0272

Previous Articles     Next Articles

Research on Vehicle Detection and Tracking Algorithms in Traffic Monitoring Scenes

LI Zhenxiao, SUN Wei, LIU Mingming, ZHENG Lili, CHEN Shaoying   

  1. 1.School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
    2.Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, Jiangsu 221116, China
    3.School of Intelligent Manufacturing, Jiangsu Institute of Architecture and Technology, Xuzhou, Jiangsu 221000, China
  • Online:2021-04-15 Published:2021-04-23

交通监控场景中的车辆检测与跟踪算法研究

李震霄,孙伟,刘明明,郑丽丽,陈劭颖   

  1. 1.中国矿业大学 信息与控制工程学院,江苏 徐州 221116
    2.地下空间智能控制教育部工程研究中心,江苏 徐州 221116
    3.江苏建筑职业技术学院 智能制造学院,江苏 徐州 221000

Abstract:

Considering the real-time and identity hopping problems in the process of multi-object tracking, a multi-vehicle tracking algorithm based on detection is proposed. Using Mobilenetv2 to replace the backbone network of YOLOv3 detection algorithm, the object detection module Yolov3-Mobilenetv2 is constructed to reduce the detection algorithm model parameters and improve the running speed of the detection module. Bottom-up connection is introduced in Mobilenetv2 to enhance information fusion among multi-scale feature maps. The LSTM motion model is adopted to solve the prediction error generated by Kalman filtering in the nonlinear system. The LSTM motion model is introduced based on the Deepsort tracking algorithm to form the L-Deepsort tracking algorithm. It improves appearance matching strategy of L-Deepsort tracking algorithm to enhance the correlation between targets. The lightweight object detection algorithm Yolov3-Mobilenetv2 is fused with the multi-object tracking algorithm L-Deepsort to form the MYL-Deepsort multi-vehicle tracking algorithm and realize the real-time and accurate tracking of multi-vehicles. Experimental results show that the speed of this method is 21 frame/s higher than YOLOv3-Deepsort and 13 frame/s higher than YOLOv3-Deepsort on TX2 platform when tracking performance is improved.

Key words: object detection, lightweight neural network, multi-object tracking, Long Short-Term Memory(LSTM), YOLOv3

摘要:

考虑多目标跟踪过程中存在的实时性和身份跳变问题,提出一种基于检测的多车辆跟踪算法。首先利用Mobilenetv2替换YOLOv3检测算法的主干网络,构建目标检测模块YOLOv3-Mobilenetv2,减少检测算法模型参数,提高检测模块的运行速度;在Mobilenetv2中引入Bottom-up连接,增强多尺度特征图间的信息融合;然后构建基于LSTM的运动模型,解决卡尔曼滤波在非线性系统中产生的预测误差,基于Deepsort跟踪算法,引入LSTM运动模型,形成L-Deepsort跟踪算法;改进L-Deepsort跟踪算法外观匹配策略,提升目标间的关联性;最后融合轻量级目标检测算法YOLOv3-Mobilenetv2与多目标跟踪算法L-Deepsort,形成MYL-Deepsort多车辆跟踪算法,实现多车辆的实时准确跟踪。实验结果表明,该方法在跟踪性能提升的情况下,速度较YOLOv3-Deepsort提高21 frame/s,在TX2平台达到13 frame/s。

关键词: 目标检测, 轻量级神经网络, 多目标跟踪, 长短时记忆(LSTM), YOLOv3