一种基于YOLOv4的改进DeepSort目标跟踪算法  

An improved DeepSort target tracking algorithm based on YOLOv4

作　　者：陈紫强[1] 张雅琼 CHEN Ziqiang;ZHAGN Yaqiong(School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《桂林电子科技大学学报》2021年第2期140-145,共6页Journal of Guilin University of Electronic Technology

基　　金：国家自然科学基金(61861011,61871425);广西自然科学基金(2016GXNSFAA380036,2018GXNSFAA138091);广西重大科技项目(AA17204093)。

摘　　要：针对车辆检测在弱光照和有遮挡情况下出现的漏检问题,提出了一种基于YOLOv4的改进DeepSort目标跟踪算法。首先使用YOLOv4算法对输入图片进行特征提取,获得目标信息,然后采用卡尔曼滤波算法估计车辆的轨迹状态并进行状态更新,最后在级联匹配中运用匈牙利匹配算法对检测框和预测框进行匹配。对未成功匹配的轨迹和检测结果,用广义交并比(GIOU)关联匹配代替交并比(IOU)匹配,提高DeepSort跟踪算法的匹配性能。对比单一检测算法和加入跟踪算法后的车辆检测效果,结果表明,加入跟踪算法后的车辆模型漏检现象变少,检测效果得到提高,鲁棒性增强,且MOTA提高了7.55%,证明了改进方法的有效性。To address the problem of missed detection in the case of weak illumination and occlusion in vehicle detection,proposed an improved DeepSort tracking algorithm based on the YOLOv4 algorithm.Firstly,the YOLOv4 algorithm is used to extract features from the input image to obtain the target information,then estimate and update the vehicle’s track condition using the Kalman filtering algorithm,and finally the matching relationship between the detection frame and the prediction frame is processed using Hungarian matching algorithm.The GIOU value of the detection and prediction results is used as measurement parameters instead of IOU value.The matching performance of DeepSort tracking algorithm is improved by it.Comparing the effect of vehicle detection with the single detection algorithm and the one after adding the tracking algorithm,the results show that there are fewer missed detections after adding the tracking algorithm,the vehicle detection effect is improved,and the robust is enhanced,and the MOTA is increased by 7.55%,proving the effectiveness of the improved method.

关 键 词：车辆检测跟踪 YOLOv4 DeepSort 广义交并比 匈牙利算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]