基于深度学习的行人和车辆检测与跟踪研究
Research on Pedestrian and Vehicle Detection and Tracking Based on Deep Learning
袁旻颉 1罗荣芳 1陈静 1苏成悦2
作者信息
- 1. 广东工业大学 物理与光电工程学院,广东 广州 510006
- 2. 广东工业大学 物理与光电工程学院,广东 广州 510006;广东工业大学 先进制造学院,广东 揭阳 515548
- 折叠
摘要
针对行人及车辆的多目标检测和跟踪中检测精度不足及跟踪目标丢失和身份切换问题,文章提出一种改进YOLOv5与改进Deep SORT相结合的多目标检测跟踪算法.检测阶段使用Varifocal Loss替换二元交叉熵损失函数结合CA注意力机制和DIoU_NMS算法.跟踪阶段将Deep SORT的REID模块特征提取网络替换为EfficientNetV2-S.在COCO数据集检测上,map@0.5 达到 78%,比原始模型提升 4.5%,在MOT16 数据集跟踪上,MOTA达到 58.1,比原始模型提升5.7,IDswitch减少了516次相当于减少了55.1%,测试结果表明该算法有较好的实际应用价值.
Abstract
This paper proposes a multi-objective detection and tracking algorithm combining improved YOLOv5 and improved Deep SORT to address the issues of insufficient detection accuracy,lost tracking targets,and identity switching in pedestrian and vehicle's multi-target detection and tracking.Replacing binary cross entropy loss function with Varifocal Loss in the detection phase,combined with CA attention mechanism and DIoU_NMS algorithm.During the tracking phase,replace the feature extraction network of the REID module of Deep SORT with EfficientNetV2-S.In COCO dataset detection,map@0.5 reaches 78%,an improvement of 4.5%compared to the original model.On the MOT16 dataset tracking,the MOTA reaches 58.1,an improvement of 5.7 compared to the original model.The IDswitch is reduced by 516 times,which is equivalent to a reduction of 55.1%.The test results show that the algorithm has good practical application value.
关键词
深度学习/目标检测/目标跟踪/计算机视觉Key words
Deep Learning/object detection/object tracking/computer vision引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据