復(fù)雜場(chǎng)景下基于改進(jìn)的Y0L0v5-pose的異常行為檢測(cè)研究

打開文本圖片集

中圖分類號(hào)：TP391.4 文獻(xiàn)標(biāo)識(shí)碼：A 文章編號(hào)：2096-4706（2025）07-0071-06

Abstract： This paper proposes an abnormal behavior detection algorithm based on the improved YOLOv5-pose in complexscenes.ItusesFPTtoreplacetheFPN+PANmodule，enablingthefeaturemapstoachieve globalandlocalinteraction acrossscales and spaces，and improving the accuracyofjoint point detection.Inthe Neck module，askipconnection structure is employedto efectively fusethe information ofthe input featuresand the multi-scale features output through the network， improvingtheabilitytocapturedetailed informationandenancing theauracyofdetectingoluded jointpoints.Experimental results show that the improved algorithm achieves an average accuracy of 9 9 . 5 % on the CrowdPose dataset，which is 2 . 4 % higher thanthatoftheoriginalmodel.Theimprovedmodelnotonlyhashigherdetectionaccuracybutalsosignificantlyimprovesthe recognition performance of small targets.

Keywords： YOLOv5-pose; behavior recognition; joint point detection; FPT; skip connection

0 引言

在城市人員復(fù)雜、社會(huì)安全風(fēng)險(xiǎn)高的重點(diǎn)場(chǎng)所，極易發(fā)生群體沖突、極端暴力等社會(huì)安全突發(fā)事件，加劇民眾的心理恐慌，嚴(yán)重影響到社會(huì)穩(wěn)定。（剩余8613字）