引用本文:李福根,段玉林※,史 云,吴文斌,黄 平.利用单次无人机影像的果树精准识别方法[J].中国农业信息,2019,31(4):10-22
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 273次   下载 164 本文二维码信息
码上扫一扫!
分享到: 微信 更多
利用单次无人机影像的果树精准识别方法
李福根1,2, 段玉林※3, 史 云3, 吴文斌3, 黄 平4
1.中国农业科学院农业资源与农业区划研究所/农业农村部农业信息技术重点实验室,北京100081;2.中国科学院遥感与数字地球研究所,北京100101;3.中国农业科学院农业资源与农业区划研究所/ 农业农村部农业遥感重点实验室,北京100081;4.四川省农业科学院遥感应用研究所,成都610066
摘要:
【目的】利用单次无人机飞行生成的正射影像和数字表面模型(DSM)对果树进行 精准识别。【方法】首先利用无人机正射影像计算5种归一化植被指数,并讨论5种植被 指数提取植被区域的精度,选用结果最好的植被指数对研究区植被进行提取;之后根据 影像的空间分辨率和已知果树直径范围对果树进行初识别确定果树实际位置和半径;再 将识别到的果树叠加到DSM中,利用果树在DSM中最大值和果树临近区域DSM最小值 求取果树高度;最后根据果树高度范围对初识别的果树进行再识别,提高果树识别精度。 【结果】该方法在美国加利福尼亚州弗雷斯诺县里德利市郊区的一个果园进行运用研究,发 现MRENDVI植被指数对研究区内植被提取精度最高;利用提取植被区域后影像和果树冠 层的直径范围对果树进行初识别的精度为94.8%;利用果树初识别影像与DSM影像结合求 取果树高度,并根据果树高度范围对果树进行再识别后,果树识别精度提高了5%,达到 99.8%。【结论】该方法原理简单,对果园果树识别有较高精度,有效消除了果园周围其他树 木和果园内部草丛对果树正确识别的影响,有较高的普适性。
关键词:  果树识别;无人机影像;数字表面模型;果树高度
DOI:10.12105/j.issn.1672-0423.20190402
分类号:
基金项目:中国农业科学院基本业务研究费专项“农业智能机器人技术与装备研发”(Y2018YJ14)
Accurate detection of fruit trees using a set of unmanned aerial vehicle(UAV)imageries
Li Fugen,Duan Yulin※,Shi Yun,Wu Wenbin,Huang Ping
1.Institute of Agricultural Resources and Regional Planning,Chinese Academy of Agricultural Sciences,Beijing 100081, China;2.The Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences,Beijing 100101,China;3.Institute of Remote Sensing Application,Sichuan Academy of Agricultural Sciences,Chengdu 610066,China
Abstract:
[ Purpose]Fruit trees detection is essential for monitoring the growth of fruit trees, estimating the yield of orchards and planting management for orchards. We proposed a method to accurately detect fruit trees using a set of Unmanned Aerial Vehicle(UAV)imageries (including an orthophoto imagery and digital surface model(DSM)) . [Method]Firstly,five normalized vegetation indices are calculated using a UAV orthophoto image. We discussed the accuracy of extracting vegetation area from five vegetation indices and chose the best vegetation area that extracted by one of the five vegetation indices in the study area. Secondly,the actual position and radius of fruit trees are determined by preliminary detection of fruit trees based on the spatial resolution of images and the specified canopy diameter range of fruit trees. Thirdly, combing preliminary detection of fruit trees and DSM,the height of fruit trees is calculated by the difference of the maximum value of fruit trees area and the minimum value of adjacent area of fruit trees in DSM. Finally,according to the height range of fruit trees and the preliminary detection of fruit trees,we are able to accurately detect the fruit trees. [Result]The method was applied to an orchard in the suburb of Ridley City,Fresno County,California,USA. It was found that Red Edge Normalized Vegetation Index(MRENDVI)had the highest accuracy in extracting vegetation area of this study. Then the image of vegetation area and the specified diameter range of fruit tree canopy were used to preliminarily detect the fruit trees. The accuracy of preliminary detection of fruit trees is 94.8%. Then the preliminary detection of fruit trees and DSM image were combined to calculate the fruit trees height,and the height range of fruit trees was used to accurately detect the fruit trees. The accurcy of fruit trees detection increased from 5% to 99.8%. [Conclusion]The method,which is simple in principle,has high accuracy in the fruit trees detection. It can effectively eliminate the error detection due to the other trees around the orchard and grass in the orchard according to specified diameter range of fruit trees canopy. This proves that the method has high universality.
Key words:  fruit trees detection;UAV imagery;digital surface model(DSM);fruit trees height