基于机器视觉的口岸尾随行为检测方法研究

打开文本图片集

中图分类号：TP391.4；TP397 文献标识码：A 文章编号：2096-4706（2025）12-0063-06

Research on Port Tailgating Behavior Detection Method Based on Machine Vision

LIRunhan'，ZHANGMei² （1.Graduate College，China People'sPoliceUniversity，Langfang O65ooo，China; 2.College ofImmigration Management， China People's Police University，Langfang O65ooo，China）

Abstract：To detect the behavior of unauthorized individuals tailgating legitimate passengers at self-service border control gates，thispaper studies thedetectionoftailgating behaviorusingaschemeofanalyzingpedestrian motionattribute characteristicsbyTargetDetectionandtargetrackingmethod.First，thebehaviorisdefiedthroughaninterdisciplinaryotent. Then，a Target Detectionalgorithm isused to identifythelegitimate individuals passngthrough thegates.Atargetracking algorithmisappliedtoextractthemovement tajectoriesofthesubjects，obtainingthespatialrelationshipbetweensuspicious individualsandlegitimatepassngers.Themovementatributesofthetargetsarequantitativelystudied，thethresholdisset， the movementcharacteristicsof individuals are analyzed，and the folow-up judgmentresultsareobtained.This enables the representationof tailgatingbehaviorandtheconstructionofanautomaticrecognitionmodelfor tailgatingbehaviorin specific scenarios.Experimentalresultsshowthatthisalgorithmcanefectivelydetecttailgaters inborderinspectionhallandachieve safe management and control of risky behaviorswithin the area.

Keywords： Machine Vision; Target Detection; movement analysis; abnormal behavior

0 引言

在出入境安全管控中，尾随行为对口岸安全造成极大威胁。（剩余8530字）