基于改进YOLOv5的行人检测方法研究
Research on pedestrian detection method based on improved YOLOv5
薛继伟 1薛鹏杰 1胡馨元1
作者信息
- 1. 东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
- 折叠
摘要
针对行人检测中出现的目标遮挡和小尺度目标漏检等现象,提出一种基于YOLOv5 改进的行人检测模型DROE-YOLO.在YOLOv5 的C3 模块中引入了 Res2Net 的残差结构以增强网络对行人目标的表征能力.采用Dynamic Head作为YOLOv5 的检测头,提高检测的准确性和鲁棒性.在标签分配策略方面采用了Simplified OTA方法,可以更准确地匹配真实框与预测框.最后,使用soft-NMS+EIOU的方法,进一步提高行人目标的检测准确率.在CrowdHuman数据集上的实验结果表明,DROE-YOLO在行人检测任务上取得了较好的效果.与基准模型相比,在增加少量参数的情况下,DROE-YOLO模型的检测精度提升了 3.3%,召回率提升了 6.5%,相比原模型更适用于实际的行人检测任务.
Abstract
To address target occlusion and missed detections of small-scale pedestrians in pedestrian detection,a modified pedestrian detection model called DROE-YOLO is proposed based on YOLOv5.Specifically,the residual structure of Res2Net is introduced into the C3 module of YOLOv5 to enhance the network's representation capability for pedestrian targets.Additionally,Dynamic Head is employed as the detection head for YOLOv5 to improve detection accuracy and robustness.The Simplified OTA method is adopted for label assignment strategy,which enables more accurate matching between ground truth boxes and predicted boxes.Finally,the soft-NMS+EIOU method is used to further improve the detection accuracy of pedestrian targets.Our experimental results on the CrowdHuman dataset demonstrate that DROE-YOLO achieves excellent performances in pedestrian detection tasks.Compared to the baseline model,with a slight increase in parameters,DROE-YOLO model improves the precision by 3.3%and the recall by 6.5%,making it more suitable for practical pedestrian detection tasks.
关键词
行人检测/Res2Net/Dynamic-Head/Simplified-OTA/Soft-NMSKey words
pedestrian-detection/Res2Net/Dynamic-Head/Simplified-OTA/Soft-NMS引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据