融合YOLO-V4与改进SiameseRPN的多目标跟踪算法  

Multiobject Tracking Algorithm Combining YOLO-V4 and Improved SiameseRPN

作　　者：朱志玲 周志峰 赵勇 王永泉 王立端 Zhu Zhiling;Zhou Zhifeng;Zhao Yong;Wang Yongquan;Wang Liduan(School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;Shanxi New Energy Technology Co.,Ltd.,Taiyuan 030024,Shanxi,China;Shanghai Compass Satellite Navigation Technology Co.,Ltd.,Shanghai 201801,China)

机构地区：[1]上海工程技术大学机械与汽车工程学院,上海201620 [2]山西中电科新能源技术有限公司,山西太原030024 [3]上海司南卫星导航技术股份有限公司,上海201801

出　　处：《激光与光电子学进展》2022年第22期278-287,共10页Laser & Optoelectronics Progress

基　　金：上海市科学技术委员会科研基金(17511106700)。

摘　　要：针对现有多目标跟踪算法精度不高的问题,提出了一种融合YOLO-V4与改进SiameseRPN的多目标跟踪算法。首先通过YOLO-V4网络自动获取跟踪目标,制作模板后输入SiameseRPN跟踪网络;然后在模板分支中采用背景自适应策略初始化模板,并且融合残差连接构建Siamese网络;最后通过匈牙利算法对YOLO-V4的检测结果和改进SiameseRPN的跟踪结果进行数据关联,实现多目标跟踪。实验结果表明,与其他算法相比,所提算法具有较好的跟踪性能,在目标尺度变化、外观变化、部分遮挡等情况下能够实现稳定跟踪。This study proposes a multiobject tracking algorithm combining YOLO-V4 and improved SiameseRPN to overcome the low accuracy of existing multiobject tracking algorithms.First,the tracking objects are automatically obtained using the YOLO-V4 network.After creating the template,enter it into the SiameseRPN tracking network.Then,the adaptive background strategy is adopted in the template branch to initialize the template,and the Siamese network is constructed by integrating residual connections.Finally,the results of YOLO-V4 and improved SiameseRPN are used to perform data association through the Hungarian algorithm to achieve multiobject tracking.The experimental results show that the proposed algorithm has better tracking performance than other algorithms.Furthermore,the proposed algorithm can achieve stable tracking under object scale,appearance change,and partial occlusion conditions.

关 键 词：机器视觉 多目标跟踪 SiameseRPN算法 背景自适应 数据关联 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]