计算机与现代化Issue(9)：14-19,6.DOI:10.3969/j.issn.1006-2475.2025.09.002
面向密集场景的PB-YOLOv7行人检测方法
PB-YOLOv7 Pedestrian Detection Method for Dense Scenes
摘要
Abstract
Aiming at the problems of low detection speed and inaccurate localization of the dense crowd detection process in com-plex backgrounds,a dense scene pedestrian detection method PB-YOLOv7 is proposed.Firstly,the PP-LCNet-based network is used instead of the original backbone feature network to reduce the complexity of the model computing process by utilizing the depth-separable convolution.Secondly,the feature fusion idea of the bidirectional feature pyramid network BiFPN is used to en-hance the feature fusion network's utilization of the deeper,shallower,and the original feature information,and to reduce the loss of the important feature information in the process of convolution.Finally,the CBAM attention module is introduced to the junction location to enhance the feature extraction capability of the algorithm in order to make the network more concerned about the effective information.The experimental results show that the improved algorithm improves the mAP by 0.7 percentage points and the FPS value by 1.6 f/s compared with the original algorithm under the publicly available dense pedestrian dataset WiderPer-son,realizing the balance between detection accuracy and detection speed.关键词
密集行人检测/YOLOv7/PP-LCNet/双向特征金字塔网络/注意力机制Key words
intensive pedestrian detection/YOLOv7/PP-LCNet/bidirectional feature pyramid network/attention mechanism分类
信息技术与安全科学引用本文复制引用
郭金豪,王峰萍,王浩琦..面向密集场景的PB-YOLOv7行人检测方法[J].计算机与现代化,2025,(9):14-19,6.基金项目
陕西省省部级项目(2022JQ-624) （2022JQ-624）
