摘要
为解决传统森林火灾监测设备误报率高、实时性差的问题,研究利用物联网及嵌入式AI技术,使用烟雾传感器、光电式火焰检测传感器、摄像头数据及人工智能方法对林火进行综合识别和监测。研究结果表明,运用多源数据综合判断的方法可以很好地实现森林火灾及时、准确地监测。
In order to solve the problems of high false alarm rate and poor real-time performance of traditional forest fire monitoring equipment,the Internet of Things and embedded AI technology are used in this study to comprehensively identify and monitor forest fires using multiple sources of data including smoke sensors,photoelectric flame detection sensors,camera data as well as artificial intelligence methods.The research results show that the method of comprehensive judgment using multi-source data can well realize the timely and accurate monitoring of forest fires.
作者
祁瑞阳
刘志强
刘晨阳
朱弥雪
QI Ruiyang;LIU Zhiqiang;LIU Chenyang;ZHU Mixue(College of Information Engineering,Inner Mongolia University of Technology,Hohhot 010051,China)
出处
《内蒙古工业大学学报（自然科学版）》
2022年第3期232-240,共9页
Journal of Inner Mongolia University of Technology：Natural Science Edition
基金
国家级大学生创新创业培训计划项目(202110128001)
国家自然科学基金项目(61962044)
内蒙古自治区科技计划项目(2021GG0250)。
关键词
林火监测
物联网技术
目标检测
YOLOv5
forest fire monitoring
Internet of Things technology
target detection
YOLOv5
