张春森;葛英伟;蒋萧;

• 1:西安科技大学测绘科学与技术学院

摘要(Abstract)：

针对传统机器学习方法提取建筑物,耗时长和精度低的问题。文中选用深度学习中的SegNet语义分割模型进行算法改进,提出了一种基于稀疏约束SegNet的高分辨率遥感影像建筑物提取算法。首先对SegNet模型加入正则项和Dropout,大大降低了模型过拟合现象的发生;其次为了模型能够提取更丰富的语义特征,算法引入金字塔池化模块;最后对SPNet模型引入Lorentz函数稀疏约束因子,构造新的语义分割模型LSPNet.为了验证提出算法的可靠性和适用性,使用优化LSPNet模型对高分辨率数据集中的建筑物识别和提取。实验结果表明,该方法与传统机器学习方法相比较,有着快速收敛、精度高的优势,并且具有很好的应用前景。

关键词(KeyWords)： 深度学习;特征提取;语义分割;稀疏约束

Abstract:

Keywords:

基金项目(Foundation): 陕西省自然科学基金(2018JM5103)

作者(Author): 张春森;葛英伟;蒋萧;

Email:

DOI: 10.13800/j.cnki.xakjdxxb.2020.0309

参考文献(References)：

• [1] 刘文涛,李世华,覃驭楚.基于全卷积神经网络的建筑物屋顶自动提取[J].地球信息科学学报,2018,20(11):1562-1570.LIU Wen-tao,LI Shi-hua,QIN Yu-chu.Automatic building roof extraction with fully convolutional neural network[J].Journal of Geo-information Science,2018,20(11):1562-1570.
• [2] 秦志强.遥感图像中建筑物提取方法研究[D].哈尔滨:哈尔滨工业大学,2009.QIN Zhi-qiang.Research on building extraction methods in remote sensing images[D].Harbin:Harbin Institute of Technology,2009.
• [3] 左童春.基于高分辨率可见光遥感图像的建筑物提取技术研究[D].合肥:中国科学技术大学,2017.ZUO Tong-chun.Research on building extraction technology based on high resolution visible light remote sensing image[D].Hefei:University of Science and Technology of China,2017.
• [4] Mnih V.Machine learning for aerial image labeling[D].Toronto:University of Toronto,2013.
• [5] 陈磊士,赵俊三,董智文,等.基于深度学习的滇中城市多光谱影像建设用地信息提取[J].软件导刊,2018,17(11):177-180,186.CHEN Lei-shi,ZHAO Jun-san,DONG Zhi-wen,et al.Information extraction of urban multi spectral image construction land in Central Yunnan based on deep learning[J].Software Guide,2018,17(11):177-180,186.
• [6] 贺浩,王仕成,杨东方,等.基于Encoder-Decoder网络的遥感影像道路提取方法[J].测绘学报,2019,48(3):330-338.HE Hao,WANG Shi-cheng,YANG Dong-fang,et al.Road extraction method for remote sensing image based on Encoder-Decoder network[J].Journal of Surveying and Mapping,2019,48(3):330-338.
• [7] Badrinarayanan V,Kendall A,Cipolla R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
• [8] 于昕玉.基于稀疏约束卷积神经网络的高分辨率遥感影像分类[D].西安:长安大学,2018.YU Xin-yu.Classification of high resolution remote sensing images based on sparse constrained convolutional neural networks[D].Xi’an:Chang’an University,2018.
• [9] Perona P,Malik J.Scale-space and edge detection using anisotropic diffusion[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1990,12(7):629-639.
• [10] Sidike P,Sagan V,Maimaitijiang M.dPEN:deep Progressively Expanded Network for mapping heterogeneous agricultural landscape using WorldView-3 satellite imagery[J].Remote Sensing of Environment,2019,221:756-772.
• [11] Zhong C,Xu Q,Yang F.Building change detection for high resolution remotely sensed images based on a semantic dependency[C]//2015 IEEE International Geoscience and Remote Sensing Symposium(IGARSS).Milan:IEEE,2015:3345-3348.
• [12] Laliberte A S,Rango A.Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle(UAV) imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):761-770.
• [13] Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
• [14] 季顺平,魏世清.遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J].测绘学报,2019,48(4):448-459.JI Shun-ping,WEI Shi-qing.Building extraction via convolutional neural networks from an open remote sensing building dataset[J].Acta Geodaetica ET Cartographica Sinica,2019,48(4):448-459.
• [15] 徐芳.航空影像分割的支持向量机方法[D].武汉:武汉大学,2004.XU Fang.Support vector machine method for aerial image segmentation[D].Wuhan:Wuhan University,2004.
• [16] Hubel D H,Wiesel T.Receptive fields,binocular interaction,and functional architecture in the cat’s visual cortex[J].Journal of Physiology,1962,160(1):106-154.
• [17] 程璐.面向对象结合支持向量机(SVM)在露天矿区信息提取中的应用研究[D].西宁:青海大学,2017.CHENG Lu.Application of object-oriented combined support vector machine(SVM)in information extraction of open pit mining area[D].Xining:Qinghai University,2017.
• [18] 李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515,2565.LI Yan-dong,HAO Zong-bo,LEI Hang.Review of convolutional neural networks[J].Computer Applications,2016,36(9):2508-2515,2565.
• [19] Guo J,Pan Z,Lei B,et al.Automatic color correction for multisource remote sensing images with wasserstein CNN[J].Remote Sensing,2017,9(5):483.
• [20] Volpi M,Tuia D.Dense semantic labeling of sub decimeter resolution images with convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(2):881-893.
• [21] Sirmacek B,Unsalan C.Building detection from aerial images using invariant color features and shadow information[C]//2008 23rd International Symposium on Computer and Information Sciences.Istanbul:IEEE,2008:1-5.
• [22] Zhong S,Huang J,Xie W.A new method of building detection from a single aerial photograph[C]//2008 9th International Conference on Signal Processing,Beijing:IEEE,2008:1219-1222.
• [23] Gong L,Li Q,Zhang J.Earthquake building damage detection with object-oriented change detection[C]//2013 IEEE International Geoscience and Remote Sensing Symposium-IGARSS.Melbourne:IEEE,2013:3674-3677.