Construction of building automatic extraction process based on image-aided nDSM of BJ-2

doi:10.13474/j.cnki.11-2246.2022.0091

Abstract

Abstract: Aiming at the problem of lack of generalization of the building method of extraction,seven-channel images of nDSM,BJ-2 image,NDVI,and BAI are combined as the data source extraction method in this paper.Random forest,gradient boosting machine,support vector machine,BP neural network classifiers are applied to extract buildings to obtain the best classifier model;Binarization,opening and closing operations are applied,using the ratio of the area of the building to the area of the smallest enclosing rectangle is used as the threshold,and the smallest enclosing rectangle and DP algorithm are used to fit the buildings respectively to optimize the building extraction results.The experimental results show that the gradient booster (GBDT) has higher F-score accuracy when extracting buildings in different scenarios.

Key words: nDSM;gradient booster;BP neural network;DP algorithm

CLC Number:

P237

MAO Bin, HAN Wenquan, XIE Hongquan, LÜ Haiyang. Construction of building automatic extraction process based on image-aided nDSM of BJ-2[J]. Bulletin of Surveying and Mapping, 2022, 0(3): 132-137.

References

[1] 叶敏,王斌,王思远,等.多特征分量结合的WorldView-3影像建筑容积率分类提取[J].武汉大学学报(信息科学版), 2019, 44(11):1674-1684.
[2] ALSHEHHI R, MARPU P R, WOON W L, et al. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130:139-149.
[3] 董保根.机载LiDAR点云与遥感影像融合的地物分类技术研究[D].郑州:信息工程大学, 2013.
[4] NOTARANGELO N M, MAZZARIELLO A, ALBANO R, et al. Comparing three machine learning techniques for building extraction from a digital surface model[J]. Applied Sciences, 2021, 11(13):6072.
[5] ZAREA A, MOHAMMADZADEH A. A novel building and tree detection method from LiDAR data and aerial images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(5):1864-1875.
[6] 李亮,王成,李世华,等.基于机载LiDAR数据的建筑屋顶点云提取方法[J].中国科学院大学学报, 2016, 33(4):537-541.
[7] 许慧敏,齐华,南轲,等.结合nDSM的高分辨率遥感影像深度学习分类方法[J].测绘通报, 2019(8):63-67.
[8] HUANG J F, ZHANG X C, XIN Q C, et al. Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 151:91-105.
[9] 吴秀芸.基于高分辨率遥感影像的建筑物提取及轮廓矢量化研究[D].南京:南京大学, 2011.
[10] 肖湘文,沈校熠,柯长青,等.基于Sentinel-1A数据的多种机器学习算法识别冰山的比较[J].测绘学报, 2020, 49(4):509-521.
[11] 周志华.机器学习[M].北京:清华大学出版社, 2016.
[12] 朱江洪,李江风,叶菁.利用决策树工具的土地利用类型遥感识别方法研究[J].武汉大学学报(信息科学版), 2011, 36(3):301-305.
[13] 吕飞.遥感图像分类问题的集成学习方法与优化[D].大连:大连理工大学, 2020.
[14] 周建伟,吴一全. MRELBP特征、Franklin矩和SVM相结合的遥感图像建筑物识别方法[J].测绘学报, 2020, 49(3):355-364.
[15] 黄万里,戴文远,余珊.基于面积保持的DouglasPeucker改进算法的多边形化简[J].科学技术与工程, 2009, 9(24):7325-7328.