| 基于深度学习的高分辨率遥感影像土地覆盖自动分类方法 |
| |
| 引用本文： | 李国清,柏永青,杨轩,陈正超,余海坤.基于深度学习的高分辨率遥感影像土地覆盖自动分类方法[J].地球信息科学,2021,23(9):1690-1704. |
| |
| 作者姓名： | 李国清 柏永青 杨轩 陈正超 余海坤 |
| |
| 作者单位： | 1. 河南省遥感测绘院,郑州 4500032. 中国科学院空天信息创新研究院 中国科学院航空遥感中心, 北京 1000943. 中国科学院空天信息创新研究院 中国科学院数字地球重点实验室,北京 1000944. 河南省自然资源卫星遥感科技创新中心,郑州 450003 |
| |
| 基金项目： | 国家自然科学基金项目(42071407);国家重点研发计划项目(2016YFB0500304);中国科学院战略性先导科技专项(XDA23100304) |
| |
| 摘 要： | 土地覆盖变化是全球变化研究的核心,而精准分类是开展土地覆盖变化研究的基础。高分辨率遥感卫星技术的快速发展对地表分类的速度和精度提出了双重挑战,近年来人工智能等新技术的发展为图像自动分割提供了实现途径,而以卷积神经网络为代表的深度学习方法在遥感图像分类领域也具有独特的优势。为对比深度学习模型设计对高分辨率图像分类结果的影响,本文以郑州市2019年高分1号影像作为输入,对比研究了基于UNet模型改进的4种不同深度学习网络模型在高分辨率影像土地覆盖自动分类应用中的差异,探讨了残差网络、模型损失函数、跳层连接和注意力机制模块等编码和解码设定对于分类精度的影响机制。研究发现：同时加入多尺度损失函数、跳层连接和注意力机制模块的MS-EfficientUNet模型对郑州市土地覆盖分类结果最优,基于像元评价的整体分类精度可达0.7981。通过在解码器中引入多尺度损失函数可有效提高林地、水体和其他类别的分类精度;而对编码器进行改进,加入跳层连接和注意力机制可进一步提高草地、水体和其他类别地物的分类精度。研究结果表明,深度学习技术在高分辨率遥感影像自动分类中具有潜在应用价值,但分类结果精度的进一步提高和多级别大范围的精细分类方法仍是下一步研究的重点。
|
| 关 键 词： | 深度学习 土地覆盖分类 高分辨率 编码解码架构 卷积神经网络 自动分类 残差网络 多尺度损失函数 |
| 收稿时间： | 2020-12-31 |
Automatic Deep Learning Land Cover Classification Methods of High-resolution Remotely Sensed Images |
| |
| LI Guoqing,BAI Yongqing,YANG Xuan,CHEN Zhengchao,YU Haikun.Automatic Deep Learning Land Cover Classification Methods of High-resolution Remotely Sensed Images[J].Geo-information Science,2021,23(9):1690-1704. |
| |
| Authors: | LI Guoqing BAI Yongqing YANG Xuan CHEN Zhengchao YU Haikun |
| |
| Institution: | 1. Institute of Remote Sensing and Surveying and Mapping Henan, Zhengzhou 450003, China2. Airborne Remote Sensing Center, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China3. Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China4. Natural Resources and Satellite Remote Sensing Center for Technology and Innovation of Henan Province, Zhengzhou 450003, China |
| |
| Abstract: | Land cover change refers to the areal change and type transformation between vegetation cover and non-vegetation cover caused by climate change and human activities, which is closely related to human survival and development, ecological environment evolution, and material energy cycle. Accurate classification is the basis of land cover change while land cover change is the core of global change research. The rapid development of high-resolution remote sensing technology poses a dual challenge to the speed and accuracy of land surface classification. In recent years, the development of new artificial intelligence technology has realized the automatic segmentation of natural scene images. Intelligent image processing technology has become an important force to promote the improvement of remote sensing information service level in the era of big data. The deep learning method represented by the convolution neural network also has significant advantages in the field of remote sensing image classification. To compare the impacts of deep learning model design on the classification results of high-resolution remote sensing images, this paper takes Gaofen-1 images of Zhengzhou City in Henan Province in 2019 as an example. This paper compares and studies the differences of four diverse deep learning network models, improved based on UNet model, in the application of automatic land cover classification of high-resolution images. Furthermore, this paper discusses the influence mechanism of encoder and decoder architecture settings, such as residual network, multi-scale loss function, skip-layer connection, and attention mechanism module, on classification accuracy. The results show that the MS-EfficientUNet model with multi-scale loss function, skip-layer connection, and attention mechanism module is the best for Zhengzhou City land cover classification, with an overall classification accuracy, based on pixel evaluation, of 0.7981. By introducing multi-scale loss function into the decoder, the classification accuracy of the forest, water, and other categories can be effectively improved. Moreover, by improving the encoder, adding skip-layer connection and attention mechanism, the classification accuracy of grassland, water, and other categories can be further improved. The results show that the powerful generalization ability of deep learning technology can effectively break through the spectral and time-phased differences between images, and realize the feature adaptive enhancement and intelligent decision-making, which has great potential in the field of high-resolution remote sensing image segmentation. However, further improvement of classification accuracy and multi-level and large-scale fine classification method are still the focus of the next step. At the same time, the unification of image sequence and the expansion of training samples are also the key factors to further improve the classification accuracy. |
| |
| Keywords: | deep learning land cover classification high resolution encode and decode architecture convolutional neural network automatic classification residual network multi scale loss function |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《地球信息科学》浏览原始摘要信息 |
| 点击此处可从《地球信息科学》下载免费的PDF全文 |
|
