摘 要：：针对传统的森林火险监测存在盲点、实时性差、运营成本高、资源消耗大等问题，提出一种基于无人机的森林火险监测系统。利用图像处理方法设计森林火险监测算法，对无人机采集的图像数据进行处理，及时判断是否有森林火险并发出预警。试验结果表明，文章算法的相对判定准确率为81.97%，相对于其他4 种方法，相对判定准确率较高，该文算法性能优于其他算法，可最终实现森林火险的监测和预警功能。
关键词：无人机；森林；火险
DOI:10.19850/j.cnki.2096-4706.2021.21.004
基金项目：广东省重点领域研发计划项目（2019B020214003）；广州市科技计划项目创新平台建设与共享专项（201605030013）；2021 年广东省科技创新战略专项资金立项项目（pdjh2021b0850）； 广东生态工程职业学院2020 年科研课题（2020kyktxj-zk10）；广东省林业科技创新项目（2018KJCX003）；广东省林业科技创新项目（2020KJCX003）
中图分类号：TP391 文献标识码：A 文章编号：2096-4706（2021）21-0016-05
Design of Forest Fire Risk Monitoring and Early Warning System Based on UAV
ZHENG Shaoxiong1,2, WANG Weixing1,3, ZHOU Yufei4, WU Zepeng4, LIU Zeqian1
(1.College of Electronic Engineering, South China Agricultural University, Guangzhou 510642, China; 2.Guangdong Eco-Engineering Polytechnic, Guangzhou 510520, China; 3.Guangdong Provincial Agricultural Information Monitoring Engineering Technology Research Center, Guangzhou 510642, China; 4.Guangdong Provincial Key Laboratory of Silviculture, Protection and Utilization/Guangdong Academy of Forestry, Guangzhou 510520, China)
Abstract: Aiming at the problems of blind spot, poor real-time performance, high operation cost and large resource consumption in traditional forest fire risk monitoring, a forest fire risk monitoring system based on UAV is proposed. Using the image processing method to design the forest fire risk monitoring algorithm, process the image data collected by UAV, judge whether there is forest fire risk in time and send out early warning. The experimental results show that the relative judgment accuracy of the algorithm used in this paper is 81.97%, compared with the other four methods, the relative judgment accuracy is higher. The performance of this algorithm is better than other algorithms, and can finally realize the function of forest fire risk monitoring and early warning.
Keywords: UAV; forest; fire risk
参考文献：
[1] 曹毅超，吴泽鹏，周宇飞，等. 基于循环神经网络的森林火灾识别研究 [J]. 林业与环境科学，2020，36（5）：34-40.
[2] CHEN M，ANG Y T，ZOU X，et al. 3D global mapping of large-scale unstructured orchard integrating eye-in-hand stereo vision and SLAM [J]. Computers and Electronics in Agriculture，2021，187：106237.https://doi.org/10.1016/j.compag.2021.106237.
[3] ZHENG S X，WANG W X，LIU Z Q，et al.Forest Farm Fire Drone Monitoring System Based on Deep Learning and Unmanned Aerial Vehicle Imagery [J]. Mathematical Problems in Engineering，vol. 2 0 2 1 ，Article ID3 2 2 4 1 6 4 ， 1 3pages， 2 0 2 1.https:/ /doi.org/10.1155/2021/3224164.
[4] 陈再励，李丽丽，钟震宇. 面向丘陵山地果树植株的植保无人机轨迹跟踪控制器设计 [J]. 自动化与信息工程，2018，39（3）：1-6.
[5] TRAN B N，TANASE M A，BENNETT L，et al. Evaluation
of spectral indices for assessing fire severity in Australian temperate forests [J]. Remote Sensing，2018（10）：1680. DOI:10.3390/rs10111680.
[6] AL-SA’D M F，AL-ALI A，MOHAMED A，et al.RF-based drone detection and identification using deep learning approaches：An initiative towards a large open source drone database [J].Future Generation Computer Systems，2019，100：86–97. https://doi. org/10.1016/j.future.2019.05.007.[7] FERNANDEZ-CARRILLO A，MCCAW L，TANASE M
A. Estimating prescribed fire impacts and post-fire tree survival in eucalyptus forests of Western Australia with L-band SAR data [J].Remote Sensing of Environment，2019，224：133-144.
[8] 李旺枝，陆健强，王卫星，等. 基于卷积神经网络的热红外图像检测模型 [J]. 自动化与信息工程，2020，41（6）：1-5.https://doi.org/10.1016/j.rse.2019.02.005.
[9] TANG Y ，CHEN M，WANG C，et al. Recognition and Localization Methods for Vision-Based Fruit Picking Robots：A Review [J].Frontiers in Plant Science，2020，11：510. DOI:10.3389/
fpls.2020.00510.
[10] 姜冰，陆健强，王卫星，等. 适用于多场景的ResNet 单幅图像去雾算法 [J]. 自动化与信息工程，2019，40（2）：14-19.
作者简介：郑少雄（1990—），男，汉族，广东饶平人，讲师，博士研究生，研究方向：电子信息技术；通讯作者：王卫星（1963—），男，汉族，河北宣化人，教授，博士研究生导师，博士研究生，研究方向：电子信息技术在农业中的应用。