2024年 05期

Multi-target Detection and Tracking Based on Improved YOLOv5 Algorithm and DeepSort Algorithm


摘要(Abstract):

针对因受水面波纹、反光及目标外观特征相似而导致的游泳池中目标检测跟踪困难的问题,提出一种基于改进YOLOv5算法和DeepSort算法的多目标检测和跟踪方法;通过引入注意力机制改进YOLOv5算法,增强算法对目标特征的提取能力;将检测结果输入到DeepSort算法中,在级联匹配中引入K邻域限制筛选目标检测框,减少因目标外观特征不明显引起的身份切换问题;利用匈牙利算法对检测框和预测框进行匹配,对未匹配成功的检测框采用距离交并比代替交并比进行二次匹配,提高DeepSort算法的跟踪性能;通过对比实验和消融实验验证所提出的多目标检测跟踪算法的性能。结果表明:改进的YOLOv5算法平均精准度提高2%,结合DeepSort算法跟踪检测,身份切换平均减少58次,多目标跟踪精确率为80.26%,比原始YOLOv5算法和Deepsort算法跟踪准确率提升了3.85%。

关键词(KeyWords): 目标检测;目标跟踪;YOLOv5算法;DeepSort算法;注意力机制;K邻域限制

基金项目(Foundation): 山东省重点研发计划项目(2017CXGC0810);; 山东省教育科学“十三五”规划教育招生考试专项课题项目(BYZK201917)

作者(Author): 李志安,林道程,姜晓凤,夏英杰,李金屏

DOI: 10.13349/j.cnki.jdxbn.20240307.001

参考文献(References):

[1] 井明涛.基于正负锚框自动选择与注意力机制的溺水检测模型研究[D].青岛:青岛大学,2021.

[2] 洪嘉卉.基于骨骼点轨迹的溺水行为检测[D].汕头:汕头大学,2022.

[3] 张相胜,沈庆.基于改进YOLOv3的多目标跟踪算法研究[J].激光与光电子学进展,2021,58(16):190.

[4] 董美琳,任安虎.基于深度学习的高速公路交通事件检测研究[J].国外电子测量技术,2021,40(10):108.

[5] SONG H J,ZHANG X H,SONG J,et al.Detection and tracking of safety helmet based on DeepSort and YOLOv5[J].Multimedia Tools and Applications,2023,82(7):10781.

[6] CHENG Y Z.Mean shift,mode seeking,and clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790.

[7] OKUMA K,TALEGHNI A,DE F N,et al.A boosted particle filter:multitarget detection and tracking[C]//European Conference on Computer Vision,May 11-14,2004,Prague,The Czech Republic.Berlin:Springer,2004:28.

[8] 金立生,华强,郭柏苍,等.基于改进DeepSort的前方车辆多目标跟踪[J].浙江大学学报(工学版),2021,55(6):1056.

[9] 黄凯文,凌六一,王成军,等.基于改进YOLO和DeepSORT的实时多目标跟踪算法[J].电子测量技术,2022,45(6):7.

[10] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137.

[11] HE K M,GKIOXARI G,DOLLáR P,et al.Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision,October 22-29,2017,Venice,Italy.New York:IEEE,2017:2980.

[12] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multiBox detector[M]//LEIBE B,MATASJ,SEBE N,et al.Computer Vision-ECCV 2016:Vol 9905.Cham:Springer International Publishing,2016:21.

[13] REDMON J,FARHADI A.Yolov3:an incremental improvement[EB/OL].(2018-04-08)[2023-05-02].http://arxiv.org/pdf/1804.02767.pdf.

[14] BOCHKOVSKIY A,WANG C Y W,LIAO H Y M.Yolov4:optimal speed and accuracy of object detection[EB/OL].(2020-04-23)[2023-05-02].http://arxiv.org/pdf/2004.10934.pdf.

[15] 杨慧剑,孟亮.基于改进的YOLOv5的航拍图像中小目标检测算法[J].计算机工程与科学,2023,45(6):1063.

[16] WOO S Y,PARK J C,LEE J Y,et al.CBAM:convolutional block attention module[M]//FERRARI V,HEBERT M,SMINCHISESCU C,et al.Computer Vision-ECCV 2018:Vol 11211.Cham:Springer,2018:3.

[17] 韩晓冰,王雨田,黄综浏,等.改进YOLOv5+DeepSort的行人跟踪算法[J].现代电子技术,2023,46(7):33.

[18] 张俊宁,毕泽洋,闫英,等.基于注意力机制与改进YOLO的温室番茄快速识别[J].农业机械学报,2023,54(5):236.

[19] BEWLEY A,GE Z Y,OTT L,et al.Simple online and realtime tracking[C]//2016 IEEE International Conference on Image Processing,September 25-28,2016,Phoenix,USA.New York:IEEE,2016:3464.

[20] WOJKE N,BEWLEY A,PAULUS D.Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing,September 17-20,2017,Beijing,China.New York:IEEE,2017:3645.

[21] 葛雯,姜添元.改进YOLO与Deepsort检测跟踪算法的研究[J].计算机仿真,2022,39(5):186.

[22] ZHENG Z H,WANG P,LIU W,et al.Distance-IoU loss:faster and better learning for bounding box regression[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12993.