一种改进YOLOv8的密集行人检测算法  

A dense pedestrian detection algorithm with improved YOLOv8

作　　者：高昂 梁兴柱[1,2] 夏晨星 张春炯 GAO Ang;LIANG Xing-zhu;XIA Chen-xing;ZHANG Chun-jiong(School of Computer Science and Engineering,Anhui University of Science and Technology,Huainan Anhui 232001,China;Institute of Environment-friendly Materials and Occupational Health,Anhui University of Science and Technology,Wuhu Anhui 241003,China;College of Electronics and Information Engineering,Tongji University,Shanghai 201804,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001 [2]安徽理工大学环境友好材料与职业健康研究院(芜湖),安徽芜湖241003 [3]同济大学电子与信息工程学院,上海201804

出　　处：《图学学报》2023年第5期890-898,共9页Journal of Graphics

基　　金：国家自然科学基金项目(62102003);安徽理工大学环境友好材料与职业健康研究院研发专项(ALW2021YF04);芜湖市科技计划项目(2020yf48)。

摘　　要：针对密集场景中小尺度的遮挡行人容易漏检的问题,提出一种改进YOLOv8检测算法。首先,针对小尺度行人特征提取问题,采用由可变形卷积改进的骨干网络增强网络对特征的提取能力,并设计遮挡感知注意力机制增强遮挡行人可见部分特征;其次,针对密集行人场景检测头定位不准的问题,设计动态解耦头增强对多尺度行人特征的关注,提高检测头的表达能力;最后,针对模型训练效率低的问题,训练时采用Wise-Io U与分布式聚焦损失结合的回归损失,提高模型的收敛能力。通过实验结果分析,改进YOLOv8算法在2个具有挑战性的密集行人数据集Crowd Human和WiderPerson上性能优秀,AP50分别达到90.6%和92.3%,AP50:95分别达到62.5%和68.2%。相较原算法有了较大提升,且与其他先进行人检测模型进行比较时表现出了很强的竞争力。所提算法在密集行人检测任务中具有广泛的应用前景。In response to the challenge of detecting small-scale,occluded pedestrians in dense scenes,where they are prone to being missed,we proposed an improved YOLOv8 detection algorithm.First,to address the issue of extracting features from small-scale pedestrians,a backbone network improved by deformable convolution was employed to enhance the feature extraction capability of the network,and an occlusion-aware attention mechanism was designed to enhance the visible part of the occluded pedestrian features.Second,to address imprecise localization of the detection head in dense pedestrian scenes,a dynamic decoupling head was designed to enhance attention to multi-scale pedestrian features,thereby improving the expression capability of the detection head.Finally,to address the problem of low model training efficiency,the regression loss that combined Wise-IoU with distributed focus loss was utilized for training,thereby enhancing the convergence ability of the model.Through the analysis of experimental results,the improved YOLOv8 algorithm demonstrated exceptional performance on two challenging and dense pedestrian datasets,namely CrowdHuman and WiderPerson,achieving an AP50 of 90.6%and 92.3%and an AP50:95 of 62.5%and 68.2%,respectively.In contrast to the original algorithm,the improvements were substantial,establishing robust competitiveness when compared with other state-of-the-art pedestrian detection models.The proposed algorithm exhibited a wide range of applications in dense pedestrian detection tasks.

关 键 词：YOLOv8 密集行人检测 遮挡感知注意力 可变形卷积 动态解耦头 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]