远距离情形下的改进YOLOv8行人检测算法  

Improved YOLOv8 Pedestrian Detection Algorithm for Long-Distance Situations

作　　者：汤静雯 赖惠成[1] 王同官 TANG Jingwen;LAl Huicheng;WANG Tongguan(College of Computer Science and Technology,Xinjiang University,Urumqi 830000,Xinjiang,China;College of Informatics,Huazhong Agricultural University,Wuhan 430070,Hubei,China)

机构地区：[1]新疆大学计算机科学与技术学院,新疆乌鲁木齐830000 [2]华中农业大学信息学院,湖北武汉430070

出　　处：《计算机工程》2025年第4期303-313,共11页Computer Engineering

基　　金：新疆维吾尔自治区重点研发计划项目(2022B01008);国家自然科学基金与新疆联合基金重点项目(U1903213)。

摘　　要：智慧社区场景下的行人检测需要精准识别行人以应对各类情况的发生,然而面对遮挡和远距离行人的情景,现有检测器会出现漏检、误检以及模型过大不易部署的问题。针对以上问题,提出基于YOLOv8的行人检测算法ME-YOLO。设计一种高效特征提取模块(EM),使得网络更好地学习行人特征和捕捉行人特点,在减少网络参数量的同时提高检测精度。设计一个重构的检测头模块,重新整合后的检测层增强了网络对小目标的识别能力,有效检测小目标行人。引入双向特征金字塔网络来设计新的颈部网络,即双向扩张残差-特征金字塔网络(BDR-FPN),利用扩张残差模块和附权注意力机制来扩展感受野及有所侧重地学习行人特征,缓解网络对遮挡行人不敏感问题。实验结果表明,在CityPersons数据集上进行训练和验证,相比原算法YOLOv8,ME-YOLO算法的AP_(50)提高了5.6百分点,模型参数量减少了41%,模型大小压缩了40%,在TinyPerson数据集上验证算法的有效性和泛化性,AP_(50)提高了4.1百分点,AP_(50∶95)提高了1.7百分点。该算法在大幅度减少模型参数和大小的同时,有效提高了检测精度,在智慧社区场景中有较好的应用价值。Pedestrian detection in intelligent community scenarios needs to accurately recognize pedestrians to address various situations.However,for persons who are occluded or at long distances,existing detectors exhibit problems such as missed detection,detection error,and large models.To address these problems,this paper proposes a pedestrian detection algorithm,Multiscale Efficient-YOLO(ME-YOLO),based on YOLOv8.An efficient feature Extraction Module(EM)is designed to improve network learning and capture pedestrian features,which reduces the number of network parameters and improves detection accuracy.The reconstructed detection head module reintegrates the detection layer to enhance the network's ability to recognize small targets and effectively detect small target pedestrians.A Bidirectional Feature Pyramid Network(BiFPN)is introduced to design a new neck network,namely the Bidirectional Dilated Residual-Feature Pyramid Network(BDR-FPN),and the expanded residual module and weighted attention mechanism expand the receptive field and learn pedestrian features with emphasis,thereby alleviating the problem of network insensitivity to occluded pedestrians.Compared with the original YOLOv8 algorithm,ME-YOLO increases the AP_(50) by 5.6 percentage points,reduces the number of model parameters by 41%,and compresses the model size by 40%after training and verification based on the CityPersons dataset.ME-YOLO also increases the AP_(50) by 4.1 percentage points and AP_(50:95) by 1.7 percentage points on the TinyPerson dataset.Moreover,the algorithm significantly reduces the number of model parameters and model size and effectively improves detection accuracy.This method has a considerable application value in intelligent community scenarios.

关 键 词：行人检测 智慧社区 小目标行人 特征金字塔网络 YOLOv8算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]