基于图像识别技术的被困人员智能探测定位系统

A trapped person detection and location model based on the image recognition technology

对各类灾害事故现场被困人员位置的准确掌握,能为救援人员制定救援方案提供科学的决策支持,进一步提高救援效率。为了更加快速精准地获取灾害事故现场被困人员位置,本文在对已有方法分析和总结的基础上,探索建立被困人员智能探测定位系统。该系统基于图像识别技术开发,通过自动获取并分析疏散通道上的视频监控画面,判断该监控对应区域下是否有人员作出特定的求救姿势或者处于被困状态,从而将被困位置和相关信息发送至救援人员,协助救援。经测试,系统在人员姿势测试集上的检测准确率为94%,在人员状态测试集上的探测准确度为90%。

The accurate acquisition of the location of trapped per-sons at various disaster scenes can provide decision support for the formulation of rescue plans and further enhance rescue effi-ciency.In order to obtain the location of people at disaster scenes more accurately,this paper explores an intelligent model for de-tect and locate the trapped person based on the analysis and sum-mary of existing methods.The system is developed based on the image recognition can automatically analyses real-time video sur-veillance footage and recognizes whether a person is in a specific distress posture or trapped,so as to send the trapped location and relevant information to rescue personnel for assistance.After test-ing,the detection accuracy of the system on the personnel posture test set is 94%,and the detection accuracy on the personnel sta-tus test set is 90%.