基于深度学习的高分辨率遥感影像光伏用地提取

doi:10.13474/j.cnki.11-2246.2021.0150

测绘通报 ›› 2021, Vol. 0 ›› Issue (5): 96-101.doi: 10.13474/j.cnki.11-2246.2021.0150

基于深度学习的高分辨率遥感影像光伏用地提取

吴永静¹, 吴锦超¹, 林超¹, 窦宝成^2,3, 黎珂²

1. 广东省国土资源技术中心, 广东广州 510075;
2. 北京吉威数源信息技术有限公司, 北京 100040;
3. 中国科学院计算技术研究所, 北京 100190

收稿日期:2020-06-08 发布日期:2021-05-28
作者简介:吴永静(1976-),女,教授级高级工程师,研究方向为GIS、地理空间大数据建设、省级卫星应用技术中心建设等。E-mail:1522350708@qq.com

Photovoltaic land extraction from high-resolution remote sensing images based on deep learning method

WU Yongjing¹, WU Jinchao¹, LIN Chao¹, DOU Baocheng^2,3, LI Ke²

1. Land Resource and Information Center of Guangdong Province, Guangzhou 510075, China;
2. Beijing Geoway Information Technology Inc., Beijing 100040, China;
3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

Received:2020-06-08 Published:2021-05-28

摘要/Abstract

摘要： 近年来我国光伏产业发展迅猛,随之也产生了诸多用地问题,通过遥感技术提取光伏用地,监测光伏用地分布与用地状况,对于光伏产业健康发展具有重要意义。本文提出一套基于深度学习方法的高分辨率遥感影像光伏用地自动提取方法,该方法利用GF-1等卫星影像和Google Earth影像构建光伏用地样本,基于ResNeSt-50作为骨干网络的DeepLab V3+模型实现深度学习语义分割算法,并结合计算机图形学方法对深度学习结果进行后处理,实现了面向高分辨率遥感影像较通用的且高精度的光伏用地自动提取。该方法的深度学习模型验证精度mIoU值达0.899 2,提取结果具有良好的边缘精度且具有广泛的适用性,支持GF-1、ZY-3、GF-6、GF-2和Google Earth等影像。

关键词: 高分卫星, 光伏用地, 深度学习, 语义分割, 分隔注意力机制

Abstract: In recent years, the rapid development of China’s photovoltaic industry has caused a lot of land use problems. Extracting photovoltaic land through remote sensing technology and monitoring the distribution and status of photovoltaic land are of great significance for the healthy development of the photovoltaic industry. This research proposes a set of automatic photovoltaic land extraction methods for high-resolution remote sensing images. Satellite images such as GF-1 and Google Earth images are used to construct photovoltaic land samples. A deep learning semantic segmentation algorithm based on the ResNeSt-50 and DeepLab V3+model is proposed. The deep learning results are post-processed with computer graphic methods and the general-purpose and high-precision automatic extraction of photovoltaic land for high-resolution remote sensing images are achieved. The proposed deep learning model has a verification accuracy of mIoU of 0.899 2, and the extraction results have good edge accuracy. The method has wide applicability, and supports images such as GF-1, ZY-3, GF-6, GF-2, and Google Earth images.

Key words: GF satellite, photovoltaic land, deep learning, semantic segmentation, separate attention mechanism

中图分类号:

P237

吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.

WU Yongjing, WU Jinchao, LIN Chao, DOU Baocheng, LI Ke. Photovoltaic land extraction from high-resolution remote sensing images based on deep learning method[J]. Bulletin of Surveying and Mapping, 2021, 0(5): 96-101.

参考文献

[1] MOSER G, SERPICO S B, BENEDIKTSSON J A. Land-cover mapping by Markov modeling of spatial-contextual information in very-high-resolution remote sensing images[J]. Proceedings of the IEEE, 2012, 101(3):631-651.
[2] LONGBOTHAM N, CHAAPEL C, BLEILER L, et al. Very high resolution multiangle urban classification analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 50(4):1155-1170.
[3] DALPONTE M, BRUZZONE L, GIANELLE D. Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data[J]. Remote sensing of environment, 2012, 123:258-270.
[4] MNIH V, HINTON G E. Learning to detect roads in high-resolution aerial images[C]//Proceedings of European Conference on Computer Vision. Berlin:Springer, 2010:210-223.
[5] XU Y, WU L, XIE Z, et al. Building extraction in very high resolution remote sensing imagery using deep learning and guided filters[J]. Remote Sensing, 2018, 10(1):144.
[6] YANG H, WU P, YAO X, et al. Building extraction in very high resolution imagery by dense-attention networks[J]. Remote Sensing, 2018, 10(11):1768.
[7] 陈亮, 刘希, 张元. 结合光谱角的最大似然法遥感影像分类[J]. 测绘工程, 2007, 16(3):40-42.
[8] 郑刚, 彭世揆, 戎慧, 等. 基于KNN方法的森林蓄积量遥感估计和反演概述[J]. 遥感技术与应用, 2010, 25(3):124-131.
[9] 李颖, 李耀辉, 王金鑫, 等. SVM和ANN在多光谱遥感影像分类中的比较研究[J]. 海洋测绘, 2016,36(5):19-22.
[10] 李彦甫,刘勇.基于对象影像分析方法支持下的多源遥感影像光伏电场提取[J].测绘与空间地理信息,2016,39(3):68-72.
[11] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 40(4):834-848.
[12] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.
[S.l.]:IEEE, 2017:6230-6239.
[13] YANG M, YU K, ZHANG C, et al. Denseaspp for semantic segmentation in street scenes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
[S.l.]:IEEE, 2018:3684-3692.
[14] ZHANG H, WU C R, ZHANG Z Y, et al. ResNeSt:split-attention networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
[S.l.]:IEEE, 2020.

[1]	董迪, 魏征, 曾纪胜. 1995—2019年北莉岛人工水产养殖遥感监测[J]. 测绘通报, 2022, 0(7): 1-6.
[2]	刘立, 董先敏, 刘娟, 文学虎. 人机融合智能的遥感解译生产新方法[J]. 测绘通报, 2022, 0(7): 118-123,137.
[3]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[4]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[5]	张晋赫, 秦育罗, 张在岩, 宋伟东, 朱洪波. 复杂场景下农村道路裂缝分割方法[J]. 测绘通报, 2022, 0(5): 74-78,88.
[6]	刘小玉, 刘扬, 杜明义, 张敏, 贾竞珏, 杨恒. 基于DeeplabV3+的建筑垃圾堆放点识别[J]. 测绘通报, 2022, 0(4): 16-19,43.
[7]	师芸, 石龙龙, 牛敏杰, 赵侃. 基于单阶段实例分割网络的黄土滑坡多任务自动识别[J]. 测绘通报, 2022, 0(4): 26-31.
[8]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[9]	高鸣, 周鑫鑫, 刘琦, 杨光迪, 吴长彬. 深度学习网络支持下的农房侵占耕地自动化监测[J]. 测绘通报, 2022, 0(3): 47-53.
[10]	孙琴琴, 蔡国印, 杨柳忠, 张宁, 杜明义. 城市尺度典型地表要素综合提取方法研究[J]. 测绘通报, 2022, 0(2): 62-66.
[11]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[12]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[13]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[14]	淳锦, 张新长, 郭海京, 张建国, 金诗程. 基于多源信息与深度学习特征提取的人口空间抽样方法[J]. 测绘通报, 2021, 0(8): 42-47.
[15]	李梓豪, 唐超. 基于高清工业相机的盾构隧道裂缝智能识别算法分析[J]. 测绘通报, 2021, 0(8): 83-87,101.

基于深度学习的高分辨率遥感影像光伏用地提取

Photovoltaic land extraction from high-resolution remote sensing images based on deep learning method

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价