Rural buildings extraction based on deep learning model with dilated convolution and pyramid representation

doi:10.13474/j.cnki.11-2246.2022.0111

Abstract

Abstract: Automatic extraction rural buildings faces many difficulties because of the diverse structure and complex spatial distribution, etc. Aiming at this problem, this paper proposes a neural network model with dilated convolution and pyramid representation for automatic extracting rural buildings in remote sensing images. In the dilated convolution neural network module, the feature information with different receptive fields is obtained by changing the size of the dilated hole. In the pyramid representation, each module inputs different scale information, and the rate of down sampling is also different, which obtains multi-dimensional pyramid scale features. Finally, the model is fused shallow feature and deep feature to construct improved deep learning model for rural building automatic extraction. Compared with FCN-8s and DeepLab models, the experiment results show that this method performs better in the extraction of rural buildings. The accuracy of the extraction is obviously improved, the boundary details are better retention and the noise is little.

Key words: deep learning, dilated convolution, pyramid representation, rural buildings extraction, remote sensing images

CLC Number:

P237

WANG Xue, LIANG Ke, SUI Lichun, ZHONG Mianqing, ZHU Jianfeng. Rural buildings extraction based on deep learning model with dilated convolution and pyramid representation[J]. Bulletin of Surveying and Mapping, 2022, 0(4): 61-65.

References 15

[1]	贺晓璐, 刘振华, 胡月明. 基于面向对象的建筑物信息提取方法研究[J]. 河南理工大学学报(自然科学版), 2020, 39(2):53-61.
[2]	陶超, 谭毅华, 蔡华杰, 等. 面向对象的高分辨率遥感影像城区建筑物分级提取方法[J]. 测绘学报, 2010, 39(1):39-45.
[3]	DRĂGUŢ L, CSILLIK O, EISANK C, et al. Automated parameterisation for multi-scale image segmentation on multiple layers[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 88:119-127.
[4]	JUNG C R, SCHRAMM R. Rectangle detection based on a windowed Hough transform[C]//Proceedings of the 17th Brazilian Symposium on Computer Graphics and Image Processing. Curitiba:IEEE, 2004:113-120.
[5]	崔有祯, 吴露露, 辛星, 等. 基于改进Harris算法的高分辨率遥感影像建筑物角点检测研究[J]. 测绘通报, 2013(9):24-26.
[6]	赵翠晓, 陈曦, 杨辽, 等. 建筑物边界约束的航空影像DSM优化[J]. 遥感信息, 2016, 31(4):16-21.
[7]	SPORTOUCHE H, TUPIN F, DENISE L. Building extraction and 3D reconstruction in urban areas from high-resolution optical and SAR imagery[C]//Proceedings of 2009 Joint Urban Remote Sensing Event. Shanghai:IEEE, 2009:1-11.
[8]	王宏涛, 王变利. 融合LiDAR和多光谱影像的建筑物自动检测[J]. 测绘科学, 2015, 40(8):64-67.
[9]	程国旗, 张继贤, 李阳春, 等. 高分影像建筑物阴影优化提取与高度估算[J]. 测绘科学, 2020, 45(8):103-109.
[10]	SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[11]	BITTNER K, CUI S, REINARTZ P. Building extraction from remote sensing data using fully convolutional networks[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-1/W1:481-486.
[12]	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 and Machine Intelligence, 2018, 40(4):834-848.
[13]	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2021-04-20]. https://arxiv.org/abs/1409.1556.
[14]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Proceedings of 2014 IEEE Transactions on Pattern Analysis and Machine Intelligence.[S.l.]:IEEE,2014:1904-1916.
[15]	YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL].[2021-04-20].https://arxiv.org/pdf/1511.07122.pdf.