多分支细化的拥挤行人检测算法  

Multi-Branch Thinning Congested Pedestrian Detection Algorithm

作　　者：袁姮 王嘉丽 张晟翀[2] YUAN Heng;WANG Jiali;ZHANG Shengchong(School of Software,Liaoning Technical University,Huludao,Liaoning 125105,China;Key Laboratory of Optoelectronic Information Control and Safety Technology,Tianjin 300308,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105 [2]光电信息控制和安全技术重点实验室,天津300308

出　　处：《计算机工程与应用》2024年第22期230-239,共10页Computer Engineering and Applications

基　　金：国家部委预研基金;辽宁省自然科学基金(20170540426);辽宁省教育厅重点基金(LJYL049)。

摘　　要：拥挤行人检测是目前小目标检测领域的研究热点,针对拥挤行人检测场景中人物密集以及遮挡造成的漏检问题,提出一种改进SSD(single shot multi-box detector)目标检测算法。将浅层Vgg(visual geometry group)网络平原结构使用多分支细化联合归一化(batch normalization,BN)操作增加分支结构,并重命名为多分支细化(multibranch thinning)网络结构,使其可以细化浅层语义信息,提高网络泛化能力,充分表达行人信息;将改进后的Ghost模型替换多分支细化网络中的3×3卷积,利用Ghost模型中cheap_operation卷积降低因多分支结构增加的模型参数量,使用primary_conv提升浅层网络的特征提取能力,加强网络识别能力;使用二范式取代差值平方的形式改进Huber损失函数,增强网络训练的稳定性,使其达到较优的收敛效果。在Wider_Person拥挤行人检测数据集上的检测结果表明,提出的改进SSD目标检测算法MAP50达到72.9%,领先YOLO-X算法7.4个百分点,领先基线算法3.5个百分点,领先其他先进算法平均14.4个百分点,验证了该算法在行人检测中的可行性,满足遮挡行人场景的检测要求。Crowded pedestrian detection is a research hotspot in the field of small target detection.Aiming at the problem of missing detection caused by dense people and occlusion in crowded pedestrian detection scenes,an improved SSD(single shot multibox detector)target detection algorithm is proposed.Firstly,the shallow Vgg(visual geometry group)network plain structure uses batch normalization(BN)operation to increase the branch structure,and renames multi-branch thin-ning network structure,so that it can refine shallow semantic information,improve network generalization ability,and fully express pedestrian information.Secondly,the improved Ghost model is used to replace the 3×3 convolution in the multi-branch thinning network,the cheap_operation convolution in the Ghost model is used to reduce the number of model parameters increased due to the multi-branch structure,and the primary_conv is used to improve the feature extraction capability of shallow networks and strengthen the network recognition capability.Finally,the Huber loss function is improved by using the two-normal form instead of the difference square,which enhances the stability of network training and makes it achieve better convergence effect.The detection results on Wider_Person crowded pedestrian detection dataset show that the proposed improved SSD target detection algorithm MAP50 reaches 72.9%,which is 7.4 percentage points ahead of YOLO-X algorithm,3.5 percentage points ahead of baseline algorithm,and 14.4 percentage points ahead of other advanced algorithms on average.The feasibility of the algorithm in pedestrian detection is verified,and it meets the detection requirements of the scene of blocking pedestrians.

关 键 词：行人检测 目标检测 SSD GhostModule 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]