智能科学与技术学报2025，Vol.7Issue(3)：350-360,11.DOI:10.11959/j.issn.2096-6652.202526
基于YOLOv7-Tiny的密集行人检测模型
Dense pedestrian detection model based on improved YOLOv7-Tiny
赵世礼 1莫红 1杨澳男 1欧阳玉琦1
作者信息
- 1. 长沙理工大学电气与信息工程学院,湖南 长沙 410114
- 折叠
摘要
Abstract
In response to the issues of large parameter quantity and low accuracy in the existing dense pedestrian detec-tion models,YOLOv7-TPMC(you only look once version 7-tiny partial minimum cross)based on YOLOv7-Tiny was proposed.Firstly,the ELAN-PP(efficient layer aggregation networks-partial and pointwise)module combining PConv(partial convolution)and PWConv(pointwise convolution)was proposed.Secondly,a cross-level fusion feature pyramid structure was designed to improve the accuracy of pedestrian detection in dense scenes through shallow feature reuse.Fi-nally,in order to solve the problem that the CIOU(complete intersection over union)loss function was not accurate in po-sitioning under certain conditions,the MF-IOU(minimum point distance and focaler-intersection over union)loss func-tion was introduced.Experiments were carried out on the WiderPerson and CrowdHuman datasets.Compared with the baseline model,YOLOv7-TPMC had the number of parameters reduced by 20.5%,FPS(frame per second)improved by 12.2%,and the value of mAP@0.5 increased by 1.2%on the WiderPerson dataset.It increased by 2.0%on the CrowdHu-man dataset,which can be well applied to dense pedestrian detection.关键词
行人检测/YOLOv7-Tiny/特征金字塔/部分卷积/注意力机制Key words
pedestrian detection/YOLOv7-Tiny/FPN/partial convolution/attention分类
信息技术与安全科学引用本文复制引用
赵世礼,莫红,杨澳男,欧阳玉琦..基于YOLOv7-Tiny的密集行人检测模型[J].智能科学与技术学报,2025,7(3):350-360,11.
