计算机应用与软件2025，Vol.42Issue(4)：166-173,207,9.DOI:10.3969/j.issn.1000-386x.2025.04.025
结合细粒度特征与注意力机制的行人检测
PEDESTRIAN DETECTION COMBINING FINE-GRAINED FEATURE AND ATTENTION MECHANISM
摘要
Abstract
The pedestrian is easy to be blocked and the scale is different,so the pedestrian missed detection rate is high.In view of this,the pedestrian detection algorithm based on Anchor-free idea is improved.Aimed at the problem that convolutional neural network was sensitive to target scale changes when extracting features,a fine-grained feature fusion strategy was proposed to obtain rich pedestrian feature information.The spatial attention mechanism was used to study the weight of different regions of the feature map to improve the expression ability of the model.Using multi-scale detection method,the model adaptively detected pedestrians of different scales and enhanced the robustness of model detection.The experimental results show that MR-2 of 11.33％,6.81％,11.52％and 50.09％are obtained on Reasonable,Bare,Partial and Heavy subsets of Cityperson dataset,respectively,which is better than other pedestrian detection algorithms.关键词
行人检测/无锚框/特征融合/多尺度/注意力机制Key words
Pedestrian detection/Anchor-free/Feature fusion/Multi-scale/Attention mechanism分类
信息技术与安全科学引用本文复制引用
肖顺亮,强赞霞,李丹阳,刘卫光..结合细粒度特征与注意力机制的行人检测[J].计算机应用与软件,2025,42(4):166-173,207,9.基金项目
国家自然科学基金项目(61802454) （61802454）
河南省科技攻关项目(182102210126). （182102210126）
