Remote sensing image building extraction based on deep learning and graph cut

doi:10.13474/j.cnki.11-2246.2019.0354

Abstract

Abstract: A method for automatically extracting buildings on high-resolution images based on convolutional neural networks and graph cuts is proposed. Firstly, the location of the contour of the building is located and detected by the convolutional neural network, and the outlines of the individual buildings are extracted one by one. The Gaussian mixture model (GMM) of the building and the non-building is respectively established by the detection result, and the minimum flow is minimized. The cut image segmentation method achieves global optimization, completes the preliminary extraction of the building, and finally optimizes with morphology. The feasibility of the method is proved by experiments.

Key words: high-resolution remote sensing image, deep learning, building information extraction, graph cuts, convolutional neural networks

CLC Number:

P237

LIU Ge, DENG Xingsheng. Remote sensing image building extraction based on deep learning and graph cut[J]. Bulletin of Surveying and Mapping, 2019, 0(11): 69-73.

References

[1] 李百寿,李灵芝,张强.一种MBR约束下的高分光学影像直角建筑物提取与标绘方法[J].测绘通报,2018(4):16-22.
[2] 丁亚洲,冯发杰,吏军平,等.多星形约束图割与轮廓规则化的高分遥感影像直角建筑物提取[J].测绘学报,2018,47(12):1630-1639.
[3] OK A O, SENARAS C, YUKSEL B, et al. Automated detection of arbitrarily shaped buildings in complex environments from monocular VHR optical satellite imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(3):1701-1717.
[4] HUANG X, ZHANG L. An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1):257-272.
[5] 伍广明,陈奇,SHIBASAKI R,等.基于U型卷积神经网络的航空影像建筑物检测[J].测绘学报,2018,47(6):864-872.
[6] MNIH V. Machine learning for aerial image labeling[D]. Toronto:University of Toronto, 2013.
[7] FUKUSHIMA K. Neocognitron:a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4):193-202.
[8] CLEVERT D, UNTERTHINER T, HOCHREITER S, et al. Fast and accurate deep network learning by exponential linear units (ELUs)[C]//International Conference on Learning Representations.[S.l.]:IEEE, 2016.
[9] SANTURKAR S, TSIPRAS D, ILYAS A, et al. How does batch normalization help optimization?[C]//32nd Conference on Neural Information Processing Systems. Montréal:[s.n.], 2018.
[10] CHEN Y, FAN R, BILAL M, et al. Multilevel cloud detection for high-resolution remote sensing imagery using multiple convolutional neural networks[J]. ISPRS International Journal of Geo-information, 2018, 7(5):267-290.
[11] MA X, WANG H, GENG J, et al. Spectral-spatial classification of hyperspectral image based on deep auto-encoder[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(9):4073-4085.
[12] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//Computer Vision and Pattern Recognition.[S.l.]:IEEE, 2017.
[13] SUZUKI S, ABE K. Topological structural analysis of digitized binary images by border following[J]. Graphical Models Graphical Models and Image Processing Computer Vision, Graphics, and Image Processing, 1985, 30(1):32-46.
[14] BOYKOV Y, JOLLY M. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]//International Conference on Computer Vision.[S.l.]:IEEE, 2001.
[15] BOYKOV Y, KOLMOGOROV V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.
[16] 杜守基,邹峥嵘,张云生,等.融合LiDAR点云与正射影像的建筑物图割优化提取方法[J].测绘学报,2018,47(4):519-527.
[17] MAGGIORI E, TARABALKA Y, CHARPIAT G, et al. Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark[C]//International Geoscience and Remote Sensing Symposium.[S.l.]:IEEE, 2017.
[18] RONNEBERGER O, FISCHER P, BROX T, et al. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//Medical Image Computing and Computer-Assisted Intervention. Berlin:Springer, 2015.