半监督YOLO在电梯检验视频合规性审查的应用

打开文本图片集

关键词：半监督学习；YOLOv11n模型；电梯检验；合规性审查；目标检测中图分类号：TP391.4;TQ171.1; TU857 文献标志码：A 文章编号：1674-2605（2025）05-0007-09DOI： 10.12475/aie.20250507 开放获取

Application of Semi-supervised YOLO in Compliance Review of Elevator Inspection Videos

LUO Weilil CHEN Guilong² LIU Guixiong² CHEN Jianxun³

（1.Zhuhai Anyue Technology Co.，Ltd.， Zhuhai 519080， China2.School of Mechanical and Automotive Engineering，South China University of Technology， Guangzhou 51o640， China 3.Zhuhai Branch， Guangdong Institute of Special Equipment Inspection and Research， Zhuhai 5190o2， China）

Abstract：Addressing the isues of high labor and resource costsassciated with the manualreviewof elevator inspection videos，as wellas tedicultyisuingjectivitadosistecytispaperpropoesautomaticompanceevieethod forkeyelements inelevatorinspectionvideosbasedonYOLOvlln.The methodconstructsaninitialtrainingdatasetfolowing the principlesoforthogonalexperimentaldesignandintroducesasemi-supervisedleaming strategy toeducemanualannotationcostsand enhancemodelgeneralizationcapabilty.Diferentiatedcompliancereviewalgorithmsaredesignedaccordingtothecharacteristicsof variou keyelements，achevingfullautomatinoftedetectionndreviepipelie.Experimentalsultsindicatethatepropsed method achieve P=0.9586，R=0.9783，mAP@50=0.9795，mAP@50：95=0.8256 in image-level object detection;and in videolevel compliance review， P=Sp=1.00 ，ensuring a review process with zero false positives. The method not only demonstrates advantages indtectioaccuracybtalsoalanesrea-teperfomanceandaghtweghtdesigrovdingapracticalandfeasible technical pathway for the automatic compliance review of key elements in elevator inspection videos.

Keywords： semi-supervised learning; YOLOv11n model; elevator inspection; compliance review; object detection

0 引言

电梯广泛应用于城市建筑、交通枢纽、居民住宅等场所，其安全性直接关乎公共安全与民生福祉[]。（剩余11940字）