主管:中华人民共和国应急管理部
主办:应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU

消防科学与技术 ›› 2023, Vol. 42 ›› Issue (10): 1408-1412.

• • 上一篇    下一篇

基于图像识别技术的被困人员智能探测定位系统

张博1, 蒋慧灵2, 孙敬1   

  1. (1. 西安市消防救援支队,陕西 西安 710000;2. 北京科技大学 金属冶炼重大事故防控技术支撑基地,北京 100083)
  • 出版日期:2023-10-15 发布日期:2023-10-15
  • 作者简介:张 博(1996- ),男,陕西西安人,西安市消防救援支队,硕士,主要从事智慧消防、人员疏散方面的工作,陕西省西安市雁塔区翔悦路与雁翔路交叉口西40米,710000。
  • 基金资助:
    基金项目:国家重点研发计划(2021YFC1523504);国家应急管理部科技计划(2021XFCX25)

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

Zhang Bo1, Jiang Huiling2, Sun Jing1   

  1. (1. Xi'an Fire and Rescue Division, Shaanxi Xi'an 710000, China; 2. Technical Support Center for Prevention and Control of Disastrous Accidents in Metal Smelting, CPAM, University of Science and Technology Beijing, Beijing 100083, China)
  • Online:2023-10-15 Published:2023-10-15

摘要: 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%。

关键词: 被困人员, 人员定位, 求救姿势, 应急救援

Abstract: The accurate acquisition of the location of trapped persons at various disaster scenes can provide decision support for the formulation of rescue plans and further enhance rescue efficiency. In order to obtain the location of people at disaster scenes more accurately, this paper explores an intelligent model for detect and locate the trapped person based on the analysis and summary of existing methods. The system is developed based on the image recognition can automatically analyses real-time video surveillance 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 testing, the detection accuracy of the system on the personnel posture test set is 94%, and the detection accuracy on the personnel status test set is 90%.

Key words: trapped person, personnel location, distress posture, emergency rescue