基于优化权重的YOLOv7密集行人检测算法  

Dense pedestrian detection algorithm based on YOLOv7 with optimized weights

作　　者：曹洁[1,2] 牛瑜 梁浩鹏 CAO Jie;NIU Yu;LIANG Haopeng(College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730030,China;College of Information Engineering,Lanzhou City University,Lanzhou 730020,China;School of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,China)

机构地区：[1]兰州理工大学电气工程与信息工程学院,甘肃兰州730030 [2]兰州城市学院信息工程学院,甘肃兰州730020 [3]兰州理工大学计算机与通信学院,甘肃兰州730050

出　　处：《液晶与显示》2025年第3期505-515,共11页Chinese Journal of Liquid Crystals and Displays

基　　金：甘肃省重点研发计划(No.22YF7GA130)。

摘　　要：针对自然复杂场景中行人拥挤和相互遮挡,导致检测精度不佳的问题,提出了一种基于优化权重的YOLOv7密集行人检测算法。首先,针对遮挡行人特征提取问题,利用跨空间高效多尺度注意力机制(Efficient Multi-Scale Attention Module with Cross-Spatial Learning,EMA)重新分配主干网络的权重,并跨维度学习不同通道特征之间的相关性,以增强模型对行人目标可见区域的关注。其次,针对检测模型复杂性较高的问题,设计了高效轻量化连接模块(Efficient Lightweight Connection Module,ELCM),旨在提升模型表达能力的同时加快训练速度。最后,构建了聚焦边界框损失函数Focal-SIoU loss,该损失函数注重抑制低质量样本,同时添加角度损失提高模型的检测精度。实验结果表明,所提算法在行人检测数据集Wider-Person与Crowd Human数据集上的均值平均精度分别达到83.7%和82.6%,相比其他先进的算法,在密集拥挤人群检测任务中有显著检测优势。Aiming at the problem of poor detection accuracy caused by pedestrian crowding and occlusion in natural complex scenes,a dense pedestrian detection algorithm based on YOLOv7 with optimized weights is proposed.First,to address the occluded pedestrian feature extraction problem,the weights of the backbone network are redistributed by the algorithms for typical geometric figures of rectangle and circle.Measuring principles and algorithms of typical plane cross-space efficient multi-scale attention module with cross-spatial learning(EMA),and the correlations between different channel features are learned cross-dimensionally,which can enhance the model’s attention to the visible area of the pedestrian target.Second,to address the problem of high complexity of the detection model,the efficient lightweight connection module(ELCM)is designed to improve the model representation ability and speed up the training speed.Finally,a focused bounding box loss function,Focal-SIoU loss,is constructed,which focuses on suppressing low-quality samples and adds angular loss to improve the detection accuracy of the model.Experimental results demonstrate that the proposed algorithm achieves mean average precisions of 83.7%and 82.6%on the Wider-Person and Crowd Human datasets,respectively,showing significant advantages in dense crowded pedestrian detection tasks.

关 键 词：密集行人检测 优化权重 聚焦边界框损失函数 YOLOv7 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]