基于无人机影像和深度学习的渭北旱塬区土地利用精准分类  

Precise classification of land use in Weibei Dryland using UAV images and deep learning

作　　者：张志博 赵西宁[2] 姜海晨 袁浩 杨龙 高晓东[2] 石亮亮 牛雨婷 Zhang Zhibo;Zhao Xining;Jiang Haichen;Yuan Hao;Yang Long;Gao Xiaodong;Shi Liangliang;Niu Yuting(Key Laboratory of Agricultural Soil and Water Engineering in Arid and Semiarid Areas,Ministry of Education,Northwest A&F University,Yangling 712100,China;Institute of Soil and Water Conservation,CAS&MWR,Yangling 712100,China;College of Natural Resources and Environment,Northwest A&F University,Yangling 712100,China;College of Information Engineering,Northwest A&F University,Yangling 712100,China;College of Economics&Management,Northwest A&F University,Yangling 712100,China)

机构地区：[1]西北农林科技大学旱区农业水土工程教育部重点实验室,杨凌712100 [2]中国科学院水利部水土保持研究所,杨凌712100 [3]西北农林科技大学资源环境学院,杨凌712100 [4]西北农林科技大学信息工程学院,杨凌712100 [5]西北农林科技大学经济管理学院,杨凌712100

出　　处：《农业工程学报》2022年第22期199-209,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划项目(2021YFD1900700);国家杰出青年科学基金项目(42125705)。

摘　　要：为明确基于无人机影像的旱塬区土地利用精准分类方法,尤其是算法的选择,该研究通过获取渭北旱塬区白水县通积村不同航拍高度无人机正射遥感影像,利用多种深度学习算法和机器学习算法对土地利用分类进行研究。首先,采用大疆御2Pro获取研究区80和160 m不同高度航拍影像;然后对不同航拍高度目视解译结果和多种深度学习、机器学习模型预测结果进行对比分析;最后,基于表现最佳算法对其进行创新和改进。结果表明:深度学习算法的表现远远优于传统机器学习算法,其中深度学习算法中表现最好的DeepLabv3+像素精度为90.06%,比随机森林(Random Forest,RF)和支持向量机(Support Vector Machine,SVM)分别高出24.65和21.32个百分点。基于DeepLabv3+改进的DeepLabv3+_BA模型整体分类效果最好,其像素精度为91.37%,比FCN、SegNet、UNet和DeepLabv3+分别高出7.43、10.12、2.27和1.31个百分点。各种算法在160 m数据集上各指标精度高于80 m。改进模型DeepLabv3+_BA具有较高的地物分类精度及较强的鲁棒性,该研究可为基于无人机影像和深度学习的土地利用信息普查提供技术参考。Accurate land use classification is highly required using Unmanned Aerial Vehicle(UAV)images,especially the data selection.In this study,the UAV orthographic remote sensing images were acquired at different aerial heights in Tongji Village,Baishui County,Weibei dry land,China.The land use was then classified using a variety of deep learning and machine learning.The DJI Mavic 2Pro was used to obtain 80 and 160m aerial images in the study area.There were 96 routes,the total length of routes was 42.43 km,the heading overlap degree was 75%,the side overlap degree was 60%,and a total of 2248 original aerial photos were taken at a flight height of 80 m.At 160 m flight height,there were 20 routes with a total length of 17.90 km,the heading overlap degree was 70%,the side overlap degree was 55%,and a total of 502 original aerial images were taken in this case.The geo-positioning of the photo control points was performed on the Zhuolin A8 handheld Beidou GPS locator.Agisoft PhotoScan 1.4.5 software was used to splice and process the original single-image data.A comparison was made on the visual interpretation of different aerial photography heights and the prediction of various deep learning and machine learning models.Labelme4.5.6 software was used for the visual interpretation.As such,the best performance was achieved during this time.The results show that the performance of deep learning was far better than that of traditional machine learning.The best-performing of deep learning(Deep Labv3+)presented a pixel accuracy of 90.06%,which was 24.65,and 21.32 percentage points higher than that of random forest(RF)and support vector machine(SVM),respectively.The improved DeepLabv3+_BA model performed the best overall classification.The improvement of deep learning was attributed to two aspects.Firstly,the BN layer was removed after the first two separate convolution layers in the Entry flow in the encoder Xception part of the original DeepLabv3+model.The BN layer was removed in ASPP after the last three separate convolutional

关 键 词：无人机 遥感 土地利用 可见光影像 深度学习 机器学习 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]