基于无人机遥感的伐区造林坑穴数量与参数提取  

Number and Parameters Extraction of Tree Well Based on UAV Remote Sensing in Cutting Area

作　　者：周小成[1] 王锋克 黄洪宇[1] 冯芝清 肖祥希[3] 李媛[1] ZHOU Xiaocheng;WANG Fengke;HUANG Hongyu;FENG Zhiqing;XIAO Xiangxi;LI Yuan(Key Laboratory of Spatial Data Mining and Information Sharing,Ministry of Education,Fuzhou University,Fuzhou 350108,China;Fujian Jinsen Forestry Co.,Ltd.,Sanming 353300,China;Fujian Academy of Forestry Sciences,Fuzhou 350012,China)

机构地区：[1]福州大学空间数据挖掘与信息共享教育部重点实验室,福州350108 [2]福建金森林业股份有限公司,三明353300 [3]福建省林业科学研究院,福州350012

出　　处：《农业机械学报》2021年第12期201-206,共6页Transactions of the Chinese Society for Agricultural Machinery

基　　金：福建省林业局重点科技攻关项目(2021FKJ01);国家重点研发计划项目(2017YFB0504202)。

摘　　要：为了挖掘无人机遥感在核查造林成果中的应用潜力,采用无人机遥感技术对福建省将乐县一伐区造林坑穴数量和参数进行自动化提取实验。采用大疆精灵4 Pro型无人机,获取空间分辨率0.01 m的可见光遥感数据,经处理后得到正射影像(DOM)、数字表面模型(DSM)和无人机影像点云数据;分别采用基于DOM人工目视解译、基于DOM模板匹配法和基于DSM圆形霍夫变换法进行各类信息提取,比较各种方法在造林坑穴数量和宽度、深度参数提取上的精度和实用性。结果表明:基于DOM模板匹配法得到的坑穴数量正确率为92.60%。基于DSM数据的圆形霍夫变换法坑穴数量正确率为95.15%,坑穴宽度和深度提取值与测量值的决定系数(R^(2))分别为0.93和0.92,均方根误差(RMSE)分别为1.02 cm和1.67 cm,该方法不仅可以得到优于模板匹配的数量精度,还可有效提取坑穴宽度和深度参数信息,提高了坑穴参数提取的效率。无人机遥感技术在提取坑穴数量、宽度和深度参数方面能够满足造林坑穴指标核查需求。In order to explore the application potential of unmanned aerial vehicle(UAV)remote sensing in the verification of afforestation results,unmanned aerial vehicle(UAV)remote sensing technique was used to extract the parameters and the number of tree well in a cutting area of Jiangle County,Fujian Province.Phantom 4 Pro UAV equipped with a digital camera was used to obtain 0.01 m resolution aerial images.DOM,DSM and point cloud data were acquired after pre-processing.They were interpreted by artificial visual interpretation,template matching method,circular Hough transform,respectively,by which all the parameters of tree well were extracted and then analyzed and the applicability and classification accuracy of each method was evaluated in the parameters extraction of tree well in afforestation project.The correctness of tree well number obtained by template matching was 92.60%.The correctness of holes number obtained by circular Hough transform was 95.15%.At the same time,the measurement of tree well width and depth got a good results with the R^(2)of 0.93 and 0.92,root mean square error(RMSE)values of 1.02 cm and 1.67 cm.It not only had high precision,and the results were consistent with template matching method,but also extracted the width and depth of tree well and improved the processing speed of big data.Remote sensing based on UAV could be used for number,width and depth parameters extraction of tree well.The circular Hough transform method could get precision parameters of tree well,which providing a technical plan for quality checking of tree well and extending UAVRS application in afforestation project.

关 键 词：造林坑穴 无人机遥感 数字表面模型 模板匹配 圆形霍夫变换 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]