改进卷积网络的高分遥感图像城镇建成区提取
Urban built-up area extraction using high-resolution remote sensing images with an improved convolutional neural network
查看参考文献33篇
|
文摘
|
目的城镇建成区是城镇研究重要的基础信息,也是实施区域规划、落实城镇功能空间布局的前提。但是遥感影像中城镇建成区的环境复杂,同时不同城镇建成区在坐落位置、发展规模等方面存在许多差异,导致其信息提取存在一定困难。方法本文基于面向图像语义分割的深度卷积神经网络,使用针对特征图的强化模块和通道域的注意力模块,对原始DeepLab网络进行改进,并通过滑动窗口预测、全连接条件随机场处理方法,更准确地实现城镇建成区提取。同时,针对使用深度学习算法容易出现过拟合和鲁棒性不强的问题,采用数据扩充增强技术进一步提升模型能力。结果实验数据是三亚和海口部分地区的高分二号遥感影像。结果表明,本文方法的正确率高于93%,Kappa系数大于0.837,可以有效地提取出大尺度高分辨率遥感影像中的城镇建成区,且提取结果最为接近实际情况。结论针对高分辨率遥感卫星影像中城镇建成区的光谱信息多样化、纹理结构复杂化等特点,本文算法能在特征提取网络中获取更多特征信息。本文使用改进的深度学习方法,提出两种处理方法,显著提高了模型的精度,在实际大幅遥感影像的使用中表现优秀,具有重要的实用价值和广阔的应用前景。 |
|
其他语种文摘
|
Objective The urban built-up area is an important source of basic information for urban research and serves as a prerequisite for the regional planning and implementation of the spatial layout of urban functions.Given the recent developments in Earth observational technologies and improvements in the resolution of remote sensing images,accurately and efficiently extracting information on urban built-up areas has become possible.However,due to the complex environment of urban built-up areas in high-resolution remote sensing images and the variations in their locations and development scales, various forms of remote sensing image representations increase the difficulty of using traditional information extraction methods for urban built-up areas.Recent studies show that deep learning algorithms have significant advantages in processing of large-scale images.This paper then examines these deep learning algorithms and reviews previous research that apply deep convolutional neural network methods,which have been widely used in computer vision to extract information on urban built-up areas from high-resolution satellite images.This article also improves the application of computer image processing technology in the field of remote sensing.Method Semantic image segmentation is crucial in image processing and computer vision.This process recognizes an image at the pixel level and then labels the object category to which each pixel in the image belongs.Based on the deep convolutional neural network oriented to semantic image segmentation,this paper uses the refinement module for the feature map and the attention module of the channel domain to improve the original DeepLab v3 network.The feature refinement module accurately obtains relevant information between pixels and reduces the grid effect.Afterward,the network model processes the feature map through atrous spatial pyramid pooling.The decoding part of the network extracts the attention information of the channel domain and then weighs the low-level features to achieve a better representation and to restore the detailed information.Afterward,the urban built-up area is extracted via the sliding window prediction and full connection conditional random fields methods,both of which can be applied to extract urban built-up areas with better accuracy.However,the use of deep learning algorithms is prone to overfitting and poor robustness.Accordingly,data augmentation and extension are used to enhance the capabilities of the model.Specifically,we use rotation and filter operations while cutting the original training and verification data into 256 ×256 samples.Result Extracting information from remote sensing images involves an effective mining and category judgment of such information.The experimental data are taken from Gaofen-2 remote sensing images of Sanya and Haikou cities in Hainan Province,China.These images are specifically taken at the Qiongshan District of Haikou City and at the Tianya District,Jiyang District,and the sea surrounding the Jiaotouding Island of Sanya City.Given their weak sample processing ability,traditional classification algorithms have achieved an accuracy rate of no higher than 85% in the experiments.Meanwhile,deep learning methods, such as SegNet and DeepLab v3,have relatively high accuracy and better performance in extracting urban built-up area information from remote sensing satellite images.By using the refinement module for the feature map and the attention module of the channel domain,this paper improves the accuracy rate of the original DeepLab v3 network by 1.95%.Meanwhile, the proposed method has an accuracy rate of above 93%,a Kappa coefficient of greater than 0.837,a missed detection rate of less than 4.9%,and a false alarm rate of below 2.1%.This method can effectively extract urban built-up areas from large-scale high spatial resolution remote sensing images,and its extraction results are the closest to the actual situation. |
|
来源
|
中国图象图形学报
,2020,25(12):2677-2689 【核心库】
|
|
DOI
|
10.11834/jig.190539
|
|
关键词
|
卷积神经网络
;
注意力机制
;
遥感图像
;
城镇建成区
;
信息提取
|
|
地址
|
1.
中国科学院西安光学精密机械研究所, 西安, 710119
2.
中国科学院大学, 北京, 100049
3.
中国科学院空天信息创新研究院, 北京, 100094
4.
三亚中科遥感研究所, 海南省地球观测重点实验室, 三亚, 572029
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1006-8961 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
海南省重点研发计划项目
|
|
文献收藏号
|
CSCD:6869951
|
参考文献 共
33
共2页
|
|
1.
Chen L C.
Semantic image segmentation with deep convolutional nets and fully connected CRFs,2014
|
CSCD被引
50
次
|
|
|
|
|
2.
Chen L C.
Rethinking Atrous convolution for semantic image segmentation,2017
|
CSCD被引
234
次
|
|
|
|
|
3.
陈磊士. 基于深度学习的滇中城市多光谱影像建设用地信息提取.
软件导刊,2018,17(11):177-180,186
|
CSCD被引
2
次
|
|
|
|
|
4.
Chen Z J. An IHS-based change detection approach for assessment of urban expansion impact on arable land loss in China.
International Journal of Remote Sensing,2003,24(6):1353-1360
|
CSCD被引
3
次
|
|
|
|
|
5.
邓刘洋. 城市建成区遥感影像边界提取与扩张分析.
地球信息科学学报,2018,20(7):996-1003
|
CSCD被引
18
次
|
|
|
|
|
6.
高常鑫. 基于深度学习的高分辨率遥感影像目标检测.
测绘通报,2014(S1):108-111
|
CSCD被引
22
次
|
|
|
|
|
7.
过林. 基于Radon和树型小波变换的遥感影像居民地提取.
测绘与空间地理信息,2012,35(1):150-153
|
CSCD被引
2
次
|
|
|
|
|
8.
He K M. Deep residual learning for image recognition.
Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778
|
CSCD被引
577
次
|
|
|
|
|
9.
Hu F. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery.
Remote Sensing,2015,7(11):14680-14707
|
CSCD被引
99
次
|
|
|
|
|
10.
Hu J. Squeeze-and-excitation networks.
Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:7132-7141
|
CSCD被引
167
次
|
|
|
|
|
11.
胡晓曦. 无人机低空数码航测与高分辨率卫星遥感测图精度试验分析.
测绘工程,2010,19(4):68-70,74
|
CSCD被引
5
次
|
|
|
|
|
12.
Klonowski J. Two level image interpretation based on Markov random fields.
Semantic Modeling for the Acquisition of Topographic Information from Images and Maps,1997:37-55
|
CSCD被引
1
次
|
|
|
|
|
13.
Krizhevsky A. ImageNet classification with deep convolutional neural networks.
Proceedings of the 25th International Conference on Neural Information Processing Systems,2012:1097-1105
|
CSCD被引
593
次
|
|
|
|
|
14.
LeCun Y. Gradient-based learning applied to document recognition.
Proceedings of the IEEE,1998,86(11):2278-2324
|
CSCD被引
2341
次
|
|
|
|
|
15.
李德仁. 论21世纪遥感与GIS的发展.
武汉大学学报·信息科学版,2003,28(2):127-131
|
CSCD被引
56
次
|
|
|
|
|
16.
李石华. 遥感图像分类方法研究综述.
国土资源遥感,2005,17(2):1-6
|
CSCD被引
34
次
|
|
|
|
|
17.
Lin C G. Building detection and description from a single intensity image.
Computer Vision and Image Understanding,1998,72(2):101-121
|
CSCD被引
30
次
|
|
|
|
|
18.
Long J. Fully convolutional networks for semantic segmentation.
Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440
|
CSCD被引
157
次
|
|
|
|
|
19.
Mnih V. Learning to detect roads in high-resolution aerial images.
Proceedings of the 11th European Conference on Computer Vision,2010:210-223
|
CSCD被引
9
次
|
|
|
|
|
20.
Pesaresi M. A robust built-up area presence index by anisotropic rotation-invariant textural measure.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2008,1(3):180-192
|
CSCD被引
35
次
|
|
|
|
|
了解气象卫星更多信息，请访问