基于多特征融合的高速路车辆多目标跟踪算法研究Multi-Target Tracking Algorithm for Highway Vehicles Based on Multi-Feature Fusion
胡随芯;常艳昌;杨俊;章振原;
摘要(Abstract)：
针对高速路车辆移动速度快、检测器易出现漏检和误检、目标相互遮挡等问题,提出一种基于多种特征融合的高速路车辆多目标跟踪算法。检测器获取每帧目标检测框后,采用HSV颜色直方图和HOG直方图建立目标外观模型,通过卡尔曼滤波建立目标位置模型和尺寸模型,融合多种特征模型构建相似性度量矩阵,并利用二分图匹配解决在线数据关联问题。在KITTI车辆数据集和自采的高速车辆数据集上将该算法与若干经典算法进行比较,结果表明,该算法在跟踪正确率和跟踪速度上明显提升。
关键词(KeyWords)： 车辆跟踪;特征融合;卡尔曼滤波;数据关联
基金项目(Foundation):
作者(Authors): 胡随芯;常艳昌;杨俊;章振原;
DOI: 10.19620/j.cnki.1000-3703.20190903
参考文献(References)：
- [1]张琦,胡广地,朱晓媛,等. Lie群下利用改进JPDA滤波器的智能车立体视觉多目标跟踪方法[J].计算机应用研究,2019(11):1-3.
- [2] BOCHINSKI E, EISELEIN V, SIKORA T. High-Speed Tracking-by-Detection without Using Image Information[C]//14th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2017:1-6.
- [3] BEWLEY A, GE Z, OTT L, et al. Simple Online and Realtime Tracking[C]//IEEE International Conference on Image Processing, 2016:3464-3468.
- [4] WOJKE N, BEWLEY A, PAULUS D. Simple online and Realtime Tracking with a Deep Association Metric[C]//IEEE International Conference on Image Processing, 2017:3645-3649.
- [5] SHARMA S, ANSARI J, Murthy J K, et al. Beyond Pixels:Leveraging Geometry and Shape Cues for Online MultiObject Tracking[EB/OL].(2018-02-26). https://arxiv.org/pdf/1802.09298.pdf.
- [6] O?EP A, MEHNER W, MATHIAS M, et al. Combined Image-and World-Space Tracking in Traffic Scenes[C]//IEEE International Conference on Robotics and Automation(ICRA), 2017:1988-1995.
- [7] GUNDUZ G, ACARMAN G. A Lightweight Online Multiple Object Vehicle Tracking Method[C]//IEEE Intelligent Vehicles Symposium, 2018:427-432.
- [8] KIERITZ H, HUBNER W, ARENS M. Joint Detection and Online Multi-Object Tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), 2018:1572-1580.
- [9] GEIGER A, LENZ P, URTASUN R. Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE, 2012:3354-3361.
- [10] REN J, CHEN X, LIU J, et al. Accurate Single Stage Detector Using Recurrent Rolling Convolution[C]//2017IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2017:752-760.
- [11] REDMON J, FARHADI A. YOLOv3:An Incremental Improvement[EB/OL].(2018-04-06). https://arxiv.org/pdf/1804.02767.pdf.
- [12] BERNARDIN K, STIEFELHAGEN R. Evaluating Multiple Object Tracking Performance:The CLEAR MOT Metrics[J]. EURASIP Journal on Image and Video Processing, 2008(1):1-10.