计算机与现代化 ›› 2024, Vol. 0 ›› Issue (05): 85-91.doi: 10.3969/j.issn.1006-2475.2024.05.015

• 图像处理 • 上一篇    下一篇

基于改进YOLOv5的复杂路况密集行人检测方法

  



  1. (1.河海大学能源与电气学院,江苏 南京 211100; 2.痕迹科学与技术公安部重点实验室,北京 100038)
  • 出版日期:2024-05-29 发布日期:2024-06-12
  • 作者简介:孙睿琦(1998—),男,江苏南京人,硕士研究生,研究方向:机器视觉与图像处理,E-mail: sunruiqi601@163.com;窦修超(1995—),男,江苏仪征人,工程师,硕士,研究方向:现场勘查,E-mail: douxiuchao@cifs.gov.cn; 通信作者:李志华(1965—),男,江苏兴化人,教授,博士,研究方向:人工智能与复杂系统故障诊断,E-mail: zhli@hhu.edu.cn。

An Improved YOLOv5-based Method for Dense Pedestrian Detection Under Complex Road Conditions


  1. (1. College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China;
    2. Key Laboratory of Traces Science and Technology, Ministry of Public Security, Beijing 100038, China)
  • Online:2024-05-29 Published:2024-06-12

摘要:
摘要:针对复杂街景环境下行人检测精度低的问题,基于YOLOv5网络,提出一种改进的行人检测网络YOLO-BEN。该网络将残差分级,利用连接模块Res2Net与C3模块进行融合,加强细粒度级别的多尺度特征表示。采用双层路由注意力模块,构建和修剪区域级有向图,在路由区域的联合中应用细粒度的注意力,使网络具备动态的查询感知稀疏性,提高对模糊图像的特征提取能力。改进原网络Neck部分进一步保留局部角区域信息,弥补被遮挡行人的信息丢失问题。使用NWD度量与原有的IoU度量形成联合损失函数,同时增加小目标检测头,提高远距离行人检测效果。实验中该方法在自制数据集和部分WiderPerson数据集上取得了较好的效果,改进后比原始网络的精确率、召回率、平均精度分别提高了2.8、4.3、3.9个百分点。




关键词: 关键词:行人检测, 多尺度特征, 双层路由注意力机制, 角区域特征, 小目标检测

Abstract: Abstract: Aiming at the problem of low pedestrian detection accuracy in complex street scene environment, a new network YOLO-BEN is proposed based on the improvement of YOLOv5 network. The network uses a residual connection module Res2Net with hierarchical system to integrate with C3 module,enhancing fine-grained multi-scale feature representation. The paper adopts the Bi-level routing attention module to construct and prune a region level directed graph, and applies fine-grained attention in the union of routing regions, enabling the network to have dynamic query aware sparsity and improving the feature extraction ability of fuzzy images. We incorporate the EVC module to preserve local corner area information and compensate for the problem of information loss caused by occluded pedestrians. In this paper, NWD metric and original IoU metric are used to form a joint loss function, and a small target detection head is added to improve the effect of long-distance pedestrian detection. In the experiment, the method has achieved good results on self-made data sets and some WiderPerson data sets. Compared with the original network, the accuracy, recall and average accuracy of the improved network are increased by 2.8, 4.3 and 3.9 percentage points respectively.

Key words: Key words: pedestrian detection, multi scale features, double layer routing attention mechanism, angular areal feature, small target detection

中图分类号: