图像语义分割方法在高分辨率遥感影像解译中的研究综述

doi:10.3778/j.issn.1673-9418.2211015

摘要/Abstract

摘要： 快速获取遥感信息对图像语义分割方法在遥感影像解译应用发展具有重要的研究意义。随着卫星遥感影像记录的数据种类越来越多，特征信息越来越复杂，精确有效地提取遥感影像中的信息，成为图像语义分割方法解译遥感图像的关键。为了探索快速高效解译遥感影像的图像语义分割方法，对大量关于遥感影像的图像语义分割方法进行了总结。首先，综述了传统的图像语义分割方法，并将其划分为基于边缘检测的分割方法、基于区域的分割方法、基于阈值的分割方法和结合特定理论的分割方法，同时分析了传统图像语义分割方法的局限性。其次，详细阐述了基于深度学习的语义分割方法，并以每种方法的基本思想和技术特点作为划分标准，将其分为基于FCN的方法、基于编解码器的方法、基于空洞卷积的方法和基于注意力机制的方法四类，概述了每类方法中包含的子方法，并对比分析了这些方法的优缺点。然后，简单介绍了遥感图像语义分割常用数据集和性能评价指标，给出了经典网络模型在不同数据集上的实验结果，同时对不同模型的性能进行了评估。最后，分析了图像语义分割方法在高分辨率遥感图像解译上面临的挑战，并对未来的发展趋势进行了展望。

关键词: 遥感图像, 图像语义分割, 深度学习语义分割, 特征融合, 注意力机制

Abstract: Rapid acquisition of remote sensing information has important research significance for the development of image semantic segmentation methods in remote sensing image interpretation applications. With more and more types of data recorded by satellite remote sensing images and more and more complex feature information, accurate and effective extraction of information in remote sensing images has become the key to interpret remote sensing images by image semantic segmentation methods. In order to explore the image semantic segmentation method for fast and efficient interpretation of remote sensing images, a large number of image semantic segmentation methods for remote sensing images are summarized. Firstly, the traditional image semantic segmentation methods are reviewed and divided into edge detection-based segmentation methods, region-based segmentation methods, threshold-based segmentation methods and segmentation methods combined with specific theories. At the same time, the limitations of traditional image semantic segmentation methods are analyzed. Secondly, the semantic segmentation methods based on deep learning are elaborated in detail, and the basic ideas and technical characteristics of each method are used as the classification criteria. They are divided into four categories: FCN-based methods, codec-based methods, dilated convolution-based methods and attention-based methods. The sub-methods contained in each type of method are summarized, and the advantages and disadvantages of these methods are compared and analyzed. Then, the common datasets and performance evaluation indexes of remote sensing image semantic segmentation are briefly introduced. Experimental results of classical network models on different datasets are given, and the performance of different models is evaluated. Finally, the challenges of image semantic segmentation methods in high-resolution remote sensing image interpretation are analyzed, and the future development trend is prospected.

Key words: remote sensing images, image semantic segmentation, deep learning semantic segmentation, feature fusion, attention module

马妍, 古丽米拉·克孜尔别克. 图像语义分割方法在高分辨率遥感影像解译中的研究综述[J]. 计算机科学与探索, 2023, 17(7): 1526-1548.

MA Yan, Gulimila·Kezierbieke. Research Review of Image Semantic Segmentation Method in High-Resolution Remote Sensing Image Interpretation[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(7): 1526-1548.

参考文献

[1] LONG J, SHELHAMER E, DARRELL T. Fully convolutio-nal networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[2] RONNEBERGER O, FISCHER P, BROX T. U-Net: convo-lutional networks for biomedical image segmentation[C]//LNCS 9351: Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Interven-tion, Munich, Germany, Oct 5-9, 2015. Cham: Springer, 2015: 234-241.
[3] 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.
[4] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Seman-tic image segmentation with deep convolutional nets and fully connected CRFs[J]. Computer Science, 2014(4): 357-361.
[5] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Deep-Lab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intel-ligence, 2018, 40(4): 834-848.
[6] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethin-king atrous convolution for semantic image segmentation[J]. arXiv:1706.05587, 2017.
[7] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//LNCS 11211: Proceedings of the 15th Euro-pean Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 833-851.
[8] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing net-work[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 2881-2890.
[9] FU J, LIU J, TIAN H, et al. Dual attention network for scene segmentation[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 3146-3154.
[10] 段瑞玲, 李庆祥, 李玉和. 图像边缘检测方法研究综述[J].光学技术， 2005, 31(3): 415-419.
DUAN R L, LI Q X, LI Y H. Summary of image edge detection[J]. Optical Technique, 2005, 31(3): 415-419.
[11] 王爱民, 赵忠旭, 沈兰荪. 基于矢量Prewitt算子的多尺度彩色图象边缘检测方法[J]. 中国图象图形学报: A辑, 1999, 4(12): 12-16.
WANG A M, ZHAO Z X, SHEN L S. Multi-scale color edge detection based on vector order Prewitt operators[J]. Journal of Image and Graphics, 1999, 4(12): 12-16.
[12] 袁春兰, 熊宗龙, 周雪花, 等. 基于Sobel算子的图像边缘检测研究[J]. 激光与红外, 2009, 39(1): 85-87.
YUAN C L, XIONG Z L, ZHOU X H, et al. Study of infrared image edge detection based on Sobel operator[J]. Laser & Infrared, 2009, 39(1): 85-87.
[13] 王李娟, 牛铮, 赵德刚, 等. 基于ETM遥感影像的海岸线提取与验证研究[J]. 遥感技术与应用, 2010, 25(2): 235-239.
WANG L J, NIU Z, ZHAO D G, et al. The study of coast-line extraction and validation using ETM remote sensing image[J]. Remote Sensing Technology and Application, 2010, 25(2): 235-239.
[14] 吴俐民, 於雪琴, 黄亮. FCM聚类算法协同Canny算子的遥感影像边缘检测方法[J]. 测绘工程, 2014, 23(12): 1-4.
WU L M, YU X Q, HUANG L. Edge detection method of remote sensing based on FCM clustering algorithm and Canny operator[J]. Engineering of Surveying and Mapping, 2014, 23(12): 1-4.
[15] 康牧, 许庆功, 王宝树. 一种Roberts自适应边缘检测方法[J]. 西安交通大学学报, 2008, 42(10): 1240-1244.
KANG M, XU Q G, WANG B S. A Roberts?? adaptive edge detection method[J]. Journal of Xi??an Jiaotong University, 2008, 42(10): 1240-1244.
[16] 陈志强, 郭永亮, 陈诗哲. 基于小波变换与改进的Roberts算子融合的图像边缘检测[J]. 传感器世界, 2011, 17(4): 15-18.
CHEN Z Q, GUO Y L, CHEN S Z. Image edge detection based on wavelet transform and improved Roberts operator[J]. Sensor World, 2011, 17(4): 15-18.
[17] 陈云波, 於雪琴. 一种结合数学形态学和LOG算子的遥感图像边缘检测方法[J]. 河南科学, 2013, 31(12): 2182-2185.
CHEN Y B, YU X Q. An edge detection method of remote sensing image based on mathematical morphology and LOG operator[J]. Henan Science, 2013, 31(12): 2182-2185.
[18] 冯兰娣, 孙效功, 胥可辉. 利用海岸带遥感图像提取岸线的小波变换方法[J]. 青岛海洋大学学报(自然科学版), 2002(5): 777-781.
FENG L D, SUN X G, XU K H. Edge detection of coast-line based on wavelet transform method[J]. Periodical of Ocean University of China, 2002(5): 777-781.
[19] 田岩岩, 齐国清. 基于小波变换模极大值的边缘检测方法[J]. 大连海事大学学报, 2007, 33(1): 102-106.
TIAN Y Y, QI G Q. Edge detection based on wavelet trans-form module maxima[J]. Journal of Dalian Maritime Univer-sity, 2007, 33(1): 102-106.
[20] 郭敏茹. 基于小波变换的遥感图像融合算法的研究[D]. 北京化工大学, 2006.
GUO M R. The research of multispectral image fusion algorithm based on wavelet transform[D]. Beijing: Beijing University of Chemical Technology, 2006.
[21] 张跃进, 谢昕. 基于IHS和小波变换的遥感图像融合方法研究[J]. 华东交通大学学报, 2008, 25(1): 49-52.
ZHANG Y J, XIE X. Remote sensing image fusion based on IHS and wavelet transform[J]. Journal of East China Jiaotong University, 2008, 25(1): 49-52.
[22] 袁华, 章皖秋. 基于小波变换遥感图像融合技术研究[J]. 电脑知识与技术, 2011, 7(2): 421-423.
YUAN H, ZHANG W Q. Remote sensing image fusion based on wavelet transform technique[J]. Computer Know-ledge and Technology, 2011, 7(2): 421-423.
[23] 李利伟, 刘吉平, 尹作为. 基于数学形态学的高分辨率遥感影像道路提取[J]. 遥感信息, 2005(5): 9-11.
LI L W, LIU J P, YIN Z W. Road extraction from high reso-lution remote sensing image based on mathematic morpho-logy[J]. Remote Sensing Information, 2005(5): 9-11.
[24] 邢超, 闫秋玲. 一种基于数学形态学的彩色图像边缘检测方法[J]. 电脑与信息技术, 2008, 16(5): 4-6.
XING C, YAN Q L. A method for color image edge detec-tion based on mathematical morphology[J]. Computer and Information Technology, 2008, 16(5): 4-6.
[25] 欧阳平, 张玉方. 形态学开闭运算在居民地边缘检测中的应用[J]. 测绘通报, 2009(1): 40-41.
OUYANG P, ZHANG Y F. Application of morphology open and close operation in resident edge detection[J]. Bulletin of Surveying and Mapping, 2009(1): 40-41.
[26] 姜涌, 曹杰, 谢求成, 等. 一种基于形态学梯度矢量和自适应模糊的目标边缘提取算法[J]. 武汉大学学报(信息科学版), 2006, 31(6): 484-488.
JIANG Y, CAO J, XIE Q C, et al. A target edge segmenta-tion algorithm based on morphological gradient vector and adaptive fuzziness[J]. Geomatics and Information Science of Wuhan University, 2006, 31(6): 484-488.
[27] 王金凤, 焦斌亮. 基于数学形态学的彩色图像边缘检测[J]. 工程图学学报, 2011, 32(6): 43-46.
WANG J F, JIAO B L. Color image edge detection based on mathematical morphology[J]. Journal of Engineering Graphics, 2011, 32(6): 43-46.
[28] 胡荣明, 黄小兵, 黄远程. 增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取[J]. 测绘学报, 2014, 43(5): 514-520.
HU R M, HUANG X B, HUANG Y C. An enhanced mor-phological building index for building extraction from high-resolution images[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5): 514-520.
[29] 林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报, 2017, 46(6): 724-733.
LIN X G, ZHANG J X. Object-based morphological buil-ding index for building extraction from high resolution remote sensing imagery[J]. Acta Geodaetica et Cartogra-phica Sinica, 2017, 46(6): 724-733.
[30] 王蒙, 吕建平. 基于边缘检测和自动种子区域生长的图像分割算法[J]. 西安邮电学院学报, 2011, 16(6): 16-19.
WANG M, LV J P. An image segmentation algorithm based on edge extraction with automatic seeded region growing[J]. Journal of Xi??an University of Posts and Telecommuni-cations, 2011, 16(6): 16-19.
[31] 范伟. 基于区域生长的彩色图像分割算法[J]. 计算机工程,2010, 36(13): 192-193.
FAN W. Color image segmentation algorithm based on region growth[J]. Computer Engineering, 2010, 36(13): 192-193.
[32] 许凯, 秦昆, 黄伯和, 等. 基于云模型的图像区域分割方法[J]. 中国图象图形学报, 2010, 15(5): 757-763.
XU K, QIN K, HUANG B H, et al. A new method of region based image segmentation based on cloud model[J]. Journal of Image and Graphics, 2010, 15(5): 757-763.
[33] 张学良, 冯学智, 肖鹏峰. 基于区域合并的高分辨率遥感图像多尺度分割[J]. 南京大学学报(自然科学), 2015, 51(5): 1030-1038.
ZHANG X L, FENG X Z, XIAO P F. Multiscale segmenta-tion of high-resolution remote sensing images based on re-gion merging[J]. Journal of Nanjing University (Natural Science), 2015, 51(5): 1030-1038.
[34] 黄卉, 檀结庆. 一种基于区域分割的图像融合方法[J]. 合肥工业大学学报(自然科学版), 2005, 28(6): 577-580.
HUANG H, TAN J Q. Image fusion based on region-seg-mentation[J]. Journal of Hefei University of Technology (Natural Science), 2005, 28(6): 577-580.
[35] 李晖晖, 郭雷, 刘航. 基于区域分割的遥感图像融合方法[J]. 光子学报, 2005, 34(12): 1901-1905.
LI H H, GUO L, LIU H. A region based remote sensing image fusion method[J]. Acta Photonica Sinica, 2005, 34(12): 1901-1905.
[36] 孙萍, 邓磊, 聂娟. 一种基于区域分割的多尺度遥感图像融合方法[J]. 遥感技术与应用, 2012, 27(6): 844-849.
SUN P, DENG L, NIE J. Multi-scale remote sensing image fusion method based on region segmentation[J]. Remote Sensing Technology and Application, 2012, 27(6): 844-849.
[37] 黄猛, 唐琳, 胡世安, 等. 一种改进的分裂合并图像分割算法[J]. 现代电子技术, 2009, 32(22): 102-105.
HUANG M, TANG L, HU S A, et al. Improved image seg-mentation algorithm based on combination split algorithm[J]. Modern Electronic Technology, 2009, 32(22): 102-105.
[38] 林敏, 陈建新, 陈哲亮. 基于边缘检测与分裂合并的图像分割算法[J]. 电子技术应用, 2011, 37(7): 130-133.
LIN M, CHEN J X, CHEN Z L. An image segmentation algorithm based on edge detection and split-merge[J]. App-lication of Electronic Technique, 2011, 37(7): 130-133.
[39] 丁海勇, 王雨轩, 毛宇琼, 等. 基于动态阈值区域分裂合并算法的高分辨率遥感图像分割研究[J]. 测绘通报, 2016(8): 145-146.
DING H Y, WANG Y X, MAO Y Q, et al. Research on high resolution remote sensing image segmentation based on dynamic threshold region splitting and merging algorithm[J]. Bulletin of Surveying and Mapping, 2016(8): 145-146.
[40] OTSU N. A thresholding selection method from gray level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[41] KITTLER J, ILLINGWORTH J. Minimum error threshol-ding[J]. Pattern Recognition, 1986, 19(1): 41-47.
[42] KAPUR J N, SAHOO P K, WONG A K C. A new method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics, and Image Pro-cessing, 1985, 29(3): 273-285.
[43] 刘健庄, 栗文青. 灰度图像的二维Otsu自动阈值分割法[J]. 自动化学报, 1993, 19(1): 101-105.
LIU J Z, LI W Q. The automatic thresholding of gray-level pictures via two-dimensional Otsu method[J]. Acta Automa-tica Sinica, 1993, 19(1): 101-105.
[44] 范九伦, 赵凤, 张雪峰. 三维Otsu阈值分割方法的递推算法[J]. 电子学报, 2007, 35(7): 1398-1402.
FAN J L, ZHAO F, ZHANG X F. Recursive algorithm for three-dimensional Otsu??s thresholding segmentation me-thod[J]. Acta Electronica Sinica, 2007, 35(7): 1398-1402.
[45] 韩青松, 贾振红, 杨杰, 等. 基于改进的Otsu算法的遥感图像阈值分割[J]. 激光杂志, 2010, 31(6): 33-34.
HAN Q S, JIA Z H, YANG J, et al. Remote sensing image thresholding segmentation based on the modified Otsu algo-rithm[J]. Laser Journal, 2010, 31(6): 33-34.
[46] 刘文静, 贾振红, 郜青梅. 基于小波包与Otsu的含噪遥感图像分割算法[J]. 计算机工程, 2011, 37(15): 203-204.
LIU W J, JIA Z H, GAO Q M. Noisy remote sense image segmentation algorithm based on wavelet packet and Otsu[J]. Computer Engineering, 2011, 37(15): 203-204.
[47] 朱言江, 韩震, 和思海, 等. 基于最大类间方差法和数学形态学的遥感图像潮沟提取方法[J]. 上海海洋大学学报, 2017, 26(1): 146-153.
ZHU Y J, HAN Z, HE S H, et al. Remote sensing image extraction of tidal channels based on Otsu and mathema-tical morphology[J]. Journal of Shanghai Ocean University, 2017, 26(1): 146-153.
[48] 龙建武, 申铉京, 陈海鹏. 自适应最小误差阈值分割算法[J]. 自动化学报, 2012, 38(7): 1134-1144.
LONG J W, SHEN X J, CHEN H P. Adaptive minimum error thresholding algorithm[J]. Acta Automatica Sinica, 2012, 38(7): 1134-1144.
[49] 刘金, 余志斌, 金炜东. 三维最小误差阈值法及其快速递推算法[J]. 电子与信息学报, 2013, 35(9): 2073-2080.
LIU J, YU Z B, JIN W D. Three dimensional minimum error threshold algorithm and its fast recursive method[J]. Journal of Electronics & Information Technology, 2013, 35(9): 2073-2080.
[50] 张新明, 冯云芝, 闰林, 等. 一种改进的二维最小误差闭值分割方法[J]. 计算机科学, 2012, 39(8): 259-262.
ZHANG X M, FENG Y Z, YAN L, et al. Improved two-dimensional minimum error image thresholding method[J]. Computer Science, 2012, 39(8): 259-262.
[51] 吴一全, 张晓杰, 吴诗婳, 等. 二维直方图θ-划分最小误差图像阈值分割[J]. 上海交通大学学报, 2012, 46(6): 892-899.
WU Y Q, ZHANG X J, WU S H, et al. Image thresholding based on 2-D histogram θ-division and minimum error[J]. Journal of Shanghai Jiao Tong University, 2012, 46(6): 892-899.
[52] ABUTALEB A S. Automatic thresholding of gray-level pic-tures using two-dimensional entropy[J]. Computer Vision Graphics & Image Processing, 1989, 47(1): 22-32.
[53] 李琳琳. 遥感图像分割中阈值的自动选取技术研究[D]. 兰州: 兰州大学, 2012.
LI L L. A study on auto-thresholding selection methods for image segmentation[D]. Lanzhou: Lanzhou University, 2012.
[54] 吴一全, 孟天亮, 吴诗婳, 等. 基于二维倒数灰度熵的河流遥感图像分割[J]. 华中科技大学学报(自然科学版), 2014 (12): 70-74.
WU Y Q, MENG T L, WU S H, et al. Remote sensing images segmentation of rivers based on two dimensional reciprocal gray entropy[J]. Journal of Huazhong Univer-sity of Science and Technology (Natural Science Edition), 2014(12): 70-74.
[55] 张新明, 张爱丽, 郑延斌, 等. 改进的最大熵阈值分割及其快速实现[J]. 计算机科学, 2011, 38(8): 278-283.
ZHANG X M, ZHANG A L, ZHENG Y B, et al. Improved two-dimensional maximum entropy image thresholding and its fast recursive realization[J]. Computer Science, 2011, 38(8): 278-283.
[56] PAL N R, PAL S K. A review on image segmentation tech-niques[J]. Pattern Recognition, 1993, 26(9): 1277-1294.
[57] DUNN J C. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters[J]. Journal of Cybernetics, 1973: 32-57.
[58] BEZDEK J C, EHRLICH R, FULL W. FCM: the fuzzy C-means clustering algorithm[J]. Computers & Geosciences, 1984, 10(2/3): 191-203.
[59] 秦昆, 徐敏. 基于云模型和 FCM 聚类的遥感图像分割方法[J]. 地球信息科学, 2008, 10(3): 302-307.
QIN K, XU M. Remote sensing image segmentation based on cloud model and FCM[J]. Journal of Geo-Information Science, 2008, 10(3): 302-307.
[60] 路彬彬, 贾振红, 何迪, 等. 基于新的遗传算法的模糊C均值聚类用于遥感图像分割[J]. 激光杂志, 2010, 31(6): 15-17.
LU B B, JIA Z H, HE D, et al. A new FCM algorithm based on monkey-king genetic algorithm for remote sensing image segmengtation[J]. Laser Journal, 2010, 31(6): 15-17.
[61] 彭立军. 基于模糊聚类的遥感图像分割方法的研究[D]. 杭州: 中国计量学院, 2013.
PENG L J. Research on remote sensing image segmenta-tion method based on the fuzzy clustering[D]. Hangzhou: China Jiliang University, 2013.
[62] 徐秋晔, 李玉, 林文杰, 等. 基于信息聚类的遥感图像分割[J]. 中国矿业大学学报, 2017, 46(1): 209-214.
XU Q Y, LI Y, LIN W J, et al. Remote sensing image seg-mentation based on information clustering[J]. Journal of China University of Mining & Technology, 2017, 46(1): 209-214.
[63] 孙志田, 张建梅, 霍丽芳. 基于最小生成树的图像融合算法[J]. 计算机仿真, 2012, 29(3): 277-279.
SUN Z T, ZHANG J M, HUO L F. Image fusion based on minimum spanning tree[J]. Computer Simulation, 2012, 29(3): 277-279.
[64] 周四龙. 基于图论的遥感图像分割算法研究[D]. 合肥: 安徽大学, 2010.
ZHOU S L. Research on algorithms of remote sensing image segmentation based on graph theory[D]. Hefei: Anhui University, 2010.
[65] 黄煌, 肖鹏峰, 王结臣. 多尺度归一化割用于遥感图像分割[J]. 遥感信息, 2015(5): 20-25.
HUANG H, XIAO P F, WANG J C. Remote sensing image segmentation based on multi-scale normalized cut[J]. Remote Sensing Information, 2015(5): 20-25.
[66] 王晓飞, 郭敏. 结合模糊C均值聚类与图割的图像分割方法[J]. 计算机应用, 2009, 29(7): 1918-1920.
WANG X F, GUO M. Image segmentation approach of combining fuzzy clustering and graph cuts[J]. Journal of Computer Applications, 2009, 29(7): 1918-1920.
[67] 周四龙, 粱栋, 王慧, 等. 基于四叉树与图割的遥感图像分割方法[J]. 计算机工程, 2010, 36(8): 224-226.
ZHOU S L, LIANG D, WANG H, et al. Remote sensing image segmentation approach based on quarter-tree and graph cut[J]. Computer Engineering, 2010, 36(8): 224-226.
[68] 张满, 颜普. 一种基于图割和支持向量机的彩色遥感图像分割[J]. 电脑知识与技术, 2012, 8(6): 3958-3961.
ZHANG M, YAN P. A color remote sensing image segmen-tation algorithm based on graph cut and support vector machince[J]. Computer Knowledge and Technology, 2012, 8(6): 3958-3961.
[69] 党耀国, 刘思峰, 方志耕. 网络最大流的割集矩阵算法[J]. 系统工程理论与实践, 2003, 23(9): 125-128.
DANG Y G, LIU S F, FANG Z G. Algorithm of cutting set matrix on the maximum flows of network[J]. Systems Engi-neering-Theory & Practice, 2003, 23(9): 125-128.
[70] 严子恒. 最小割最大流算法的研究与应用[D]. 南京: 南京邮电大学, 2016.
YAN Z H. Research and applications for the problem of mi-nimum cut/maximum flow algorithms[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2016.
[71] 秦婵婵. 基于随机游走算法的图像分割方法研究[D]. 武汉: 华中师范大学, 2014.
QIN C C. Research on random walksi mage segmentation method[D]. Wuhan: Central China Normal University, 2014.
[72] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[73] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409.1556, 2014.
[74] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 770-778.
[75] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[76] 邓国徽, 高飞, 罗志鹏. 基于改进的全卷积神经网络高分遥感数据语义分割研究[C]//第四届高分辨率对地观测学术年会论文集, 武汉, 2017: 1125-1137.
DENG G H, GAO F, LUO Z P. Research on semantic seg-mentation of high-resolution remote sensing data based on improved fully convolution neural network[C]//4th China High Resolution Earth Observation Conference, Wuhan, 2017: 1125-1137.
[77] 任志淼. 基于全卷积神经网络和动态自适应区域生长法的红外图像目标分割方法[J]. 半导体光电, 2019, 40(4): 564-570.
REN Z M. Infrared image target segmentation algorithm based on full convolutional neural network and dynamic adaptive region growth[J]. Semiconductor Optoelectronics, 2019, 40(4): 564-570.
[78] LIU Y, GROSS L, LI Z, et al. Automatic building extraction on high-resolution remote sensing imagery using deep con-volutional encoder-decoder with spatial pyramid pooling[J]. IEEE Access, 2019, 7(1): 128774-128786.
[79] 潘旭冉, 杨帆, 潘国峰. 采用改进全卷积网络的“高分一号”影像居民地提取[J]. 电讯技术, 2018, 58(2): 119-125.
PAN X R, YANG F, PAN G F. Extraction of residential areas in GF-1 remote sensing images based on improved fully convolutional network[J]. Telecommunication Engi-neering, 2018, 58(2): 119-125.
[80] PIRAMANAYAGAM S, SCHWARTZKOPF W, KOEHLER F W, et al. Classification of remote sensed images using ran-dom forests and deep learning framework[C]//Proceedings Volume 10004: Image and Signal Processing for Remote Sensing XXII, Edinburgh, Oct 18, 2016. San Francisco: SPIE, 2016.
[81] GUO R, LIU J, LI N, et al. Pixel-wise classification method for high resolution remote sensing imagery using deep neural networks[J]. International Journal of Geo-Information, 2018, 7(3): 110.
[82] PAPADOMANOLAKI M, VAKALOPOULOU M, KARA-NTZALOS K. A novel object-based deep learning frame-work for semantic segmentation of very high-resolution re-mote sensing data: comparison with convolutional and fully convolutional networks[J]. Remote Sensing, 2019, 11(6): 684.
[83] 李宝奇, 贺昱曜, 何灵蛟, 等. 基于全卷积神经网络的非对称并行语义分割模型[J]. 电子学报, 2019, 47(5): 1058-1064.
LI B Q, HE Y Y, HE L J, et al. Asymmetric parallel semantic segmentation model based on full convolutional neural net-work[J]. Acta Electronica Sinica, 2019, 47(5): 1058-1064.
[84] 官申珂, 林晓, 郑晓妹, 等. 结合超像素分割的多尺度特征融合图像语义分割算法[J]. 图学学报, 2021, 42(3): 406-413.
GUAN S K, LIN X, ZHENG X M, et al. A semantic seg-mentation algorithm using multi-scale feature fusion with combination of superpixel segmentation[J]. Journal of Graphics, 2021, 42(3): 406-413.
[85] PASZKE A, CHAURASIA A, KIM S, et al. ENet: a deep neural network architecture for real-time semantic segmen-tation[J]. arXiv:1606.02147, 2016.
[86] PAN X, YANG F, GAO L, et al. Building extraction from high-resolution aerial imagery using a generative adversarial network with spatial and channel attention mechanisms[J]. Remote Sensing, 2019, 11(8): 917.
[87] 许玥, 冯梦如, 皮家甜, 等. 基于深度学习模型的遥感图像分割方法[J]. 计算机应用, 2019, 39(10): 2905-2914.
XU Y, FENG M R, PI J T, et al. Remote sensing image segmentation method based on deep learning model[J]. Journal of Computer Applications, 2019, 39(10): 2905-2914.
[88] 陈天华, 郑司群, 林宇骁. 基于改进深度神经网络的遥感影像语义分割[J]. 计算机仿真, 2021, 38(12): 27-32.
CHEN T H, ZHENG S Q, LIN Y X. Semantic segmenta-tion of remote sensing images based on improved deep neural network[J]. Computer Simulation, 2021, 38(12): 27-32.
[89] 杨建宇, 周振旭, 杜贞容, 等. 基于SegNet语义模型的高分辨率遥感影像农村建设用地提取[J]. 农业工程学报, 2019, 35(5): 251-258.
YANG J Y, ZHOU Z X, DU Z R, et al. Rural construction land extraction from high spatialresolution remote sensing image based on SegNet semantic segmentation model[J]. Transactions of the Chinese Society of Agricultural Engi-neering, 2019, 35(5): 251-258.
[90] 张春森, 葛英伟, 蒋萧. 基于稀疏约束SegNet的高分辨率遥感影像建筑物提取[J]. 西安科技大学学报, 2020, 40(3): 441-448.
ZHANG C S, GE Y W, JIANG X. High-resolution remote sensing image building extraction based on sparsely cons-trained SegNet[J]. Journal of Xi??an University of Science and Technology, 2020, 40(3): 441-448.
[91] 张哲晗, 方薇, 杜丽丽, 等. 基于编码-解码卷积神经网络的遥感图像语义分割[J]. 光学学报, 2020, 40(3): 40-49.
ZHANG Z H, FANG W, DU L L, et al. Semantic segmen-tation of remote sensing image based on encoder-decoder convolutional neural network[J]. Acta Optica Sinica, 2020, 40(3): 40-49.
[92] 王曦, 于鸣, 任洪娥. UNET与FPN相结合的遥感图像语义分割[J]. 液晶与显示, 2021, 36(3): 475-483.
WANG X, YU M, REN H E. Remote sensing image seman-tic segmentation combining UNET and FPN[J]. Chinese Journal of Liquid Crystals and Displays, 2021, 36(3): 475-483.
[93] 宝音图, 刘伟, 李润生, 等. 遥感图像语义分割的空间增强注意力U型网络[J/OL]. 北京航空航天大学学报[2022-08-13]. DOI: 10.13700/j.bh.1001-5965.2021.0544.
BAO Y T, LIU W, LI R S, et al. Semantic segmentation of remote sensing images based on U-shaped network combined with spatial enhance attention[J/OL]. Journal of Beijing University of Aeronautics and Astronautics [2022-08-13]. DOI: 10.13700/j.bh.1001-5965.2021.0544.
[94] 岱超, 刘萍, 史俊才, 等. 利用U型网络的遥感影像建筑物规则化提取[J]. 计算机工程与应用, 2023, 59(8): 105-116.
DAI C, LIU P, SHI J C, et al. Regularized extraction of remotely sensed image buildings using U-shaped networks[J]. Computer Engineering and Applications, 2023, 59(8): 105-116.
[95] 金澍, 关沫, 边玉婵, 等. 基于改进 U-Net 的遥感影像建筑物提取方法[J]. 激光与光电子学进展, 2023, 60(4): 49-55.
JIN S, GUAN M, BIAN Y C, et al. Building extraction from remote sensing image based on improved U-Net[J]. Laser & Optoelectronics Progress, 2023, 60(4): 49-55.
[96] 李娇娇, 刘志强, 宋锐, 等. 一种改进Unet网络的遥感影像分割算法[J]. 西安电子科技大学学报, 2022, 49(6): 67-75.
LI J J, LIU Z Q, SONG R, et al. Algorithm for segmenta-tion of remote sensing imagery using the improved Unet[J]. Journal of Xidian University, 2022, 49(6): 67-75.
[97] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[J]. arXiv:1511.07122, 2015.
[98] 陈天华, 郑司群, 于峻川. 采用改进 DeepLab 网络的遥感图像分割[J]. 测控技术, 2018, 37(11): 34-39.
CHEN T H, ZHENG S Q, YU J C. Remote sensing image segmentation based on improved DeepLab network[J]. Mea-surement & Control Technology, 2018, 37(11): 34-39.
[99] 蔡烁, 胡航滔, 王威. 基于深度卷积网络的高分遥感图像语义分割[J]. 信号处理, 2019, 35(12): 2010-2016.
CAI S, HU H T, WANG W. Semantic segmentation of high-resolution remote sensing image based on deep convolu-tional network[J]. Journal of Signal Processing, 2019, 35(12): 2010-2016.
[100] 王蓝玉. 基于 Deeplab V3+网络的遥感地物图像语义分割研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.
WANG L Y. Research on semantic segmentation of remote sensing images of the ground objects based on Deeplab V3+ network[D]. Harbin: Harbin Institute of Technology, 2020.
[101] 熊风光, 张鑫, 刘欢乐, 等. 一种基于深度学习的遥感图像语义分割方法: CN112489054A[P]. 2021.
XIONG F G, ZHANG X, LIU H L, et al. A remote sensing image semantic segmentation method based on deep lear-ning: CN112489054A[P]. 2021.
[102] 熊风光, 张鑫, 韩燮, 等. 改进的遥感图像语义分割研究[J]. 计算机工程与应用, 2022, 58(8): 185-190.
XIONG F G, ZHANG X, HAN X, et al. Research on im-proved semantic segmentation of remote sensing[J]. Compu-ter Engineering and Applications, 2022, 58(8): 185-190.
[103] 郭新, 张斌, 程坤. 面向小目标提取的改进DeepLabV3+模型遥感图像分割[J]. 遥感信息, 2022, 37(2): 34-44.
GUO X, ZHANG B, CHENG K. Semantic segmentation of remote sensing images based on improved DeepLabV3+ model for small object extraction[J]. Remote Sensing Information, 2022, 37(2): 34-44.
[104] 李鑫. 基于深度学习的图像语义分割方法研究[D]. 绵阳: 西南科技大学, 2022.
LI X. Research on image semantic segmentation based on deep learning[D]. Mianyang: Southwest University of Science and Technology, 2022.
[105] 杨贞, 彭小宝, 朱强强, 等. 基于Deeplab V3 Plus的自适应注意力机制图像分割算法[J]. 计算机应用, 2022, 42(1): 230-238.
YANG Z, PENG X B, ZHU Q Q, et al. Image segmenta-tion algorithm with adaptive attention mechanism based on Deeplab V3 Plus[J]. Journal of Computer Applications, 2022, 42(1): 230-238.
[106] 孟俊熙, 张莉, 曹洋, 等. 基于Deeplab v3+的图像语义分割算法优化研究[J]. 激光与光电子学进展, 2022, 59(16): 161-170.
MENG J X, ZHANG L, CAO Y, et al. Optimization of image semantic segmentation algorithms based on Deeplab v3+[J]. Laser & Optoelectronics Progress, 2022, 59(16): 161-170.
[107] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Com-puter Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 7132-7141.
[108] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//LNCS 11211: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 3-19.
[109] HAUT J M, FERNANDEZ-BELTRAN R, PAOLETTI M E, et al. Remote sensing image superresolution using deep residual channel attention[J]. IEEE Transactions on Geo-science and Remote Sensing, 2019, 57(11): 9277-9289.
[110] DING L, TANG H, BRUZZONE L. LANet: local attention embedding to improve the semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(1): 426-435.
[111] 赵斐. 基于金字塔注意力机制的遥感图像语义分割[J]. 国外电子测量技术, 2019, 38(8): 150-154.
ZHAO F. Semantic segmentation of remote sensing images based onpyramid attention mechanism[J]. Foreign Electronic Measurement Technology, 2019, 38(8): 150-154.
[112] 王敏, 陈金勇, 杨文, 等. 基于上下文信息和注意力机制的遥感影像语义分割方法: CN110197182A[P]. 2019.
WANG M, CHEN J Y, YANG W, et al. Semantic segmen-tation method of remote sensing image based on context information and attention mechanism: CN110197182A[P]. 2019.
[113] 周勇, 何欣, 赵佳琦, 等. 基于注意力多尺度特征融合的遥感图像语义分割方法: CN111127493A[P]. 2020.
ZHOU Y, HE X, ZHAO J Q, et al. Remote sensing image semantic segmentation method based on attention multi-scale feature fusion: CN111127493A[P]. 2020.
[114] 刘文祥, 舒远仲, 唐小敏, 等. 采用双注意力机制Deeplab v3+算法的遥感影像语义分割[J]. 热带地理, 2020, 40(2): 303-313.
LIU W X, SHU Y Z, TANG X M, et al. Remote sensing image segmentation using dual attention mechanism Deeplabv3+ algorithm[J]. Tropical Geography, 2020, 40(2): 303-313.
[115] 张汉, 张德祥, 陈鹏, 等. 并行注意力机制在图像语义分割中的应用[J]. 计算机工程与应用, 2022, 58(9): 151-160.
ZHANG H, ZHANG D X, CHEN P, et al. Application of parallel attention mechanism in image semantic segmenta-tion[J]. Computer Engineering and Applications, 2022, 58(9): 151-160.
[116] 云飞, 殷雁君, 张文轩, 等. 融合注意力机制的对抗式半监督语义分割[J]. 计算机工程与应用, 2023, 59(8): 254-262.
YUN F, YIN Y J, ZHANG W X, et al. Adversarial semi-supervised semantic segmentation with attention mecha-nism[J]. Computer Engineering and Applications, 2023, 59(8): 254-262.
[117] 高世伟, 张长柱, 王祝萍. 基于可分离金字塔的轻量级实时语义分割算法[J]. 计算机应用, 2021, 41(10): 2937-2944.
GAO S W, ZHANG C Z, WANG Z P. Lightweight real-time semantic segmentation algorithm based on separable pyramid[J]. Journal of Computer Applications, 2021, 41(10): 2937-2944.
[118] 后云龙. 基于金字塔模型和注意力机制的遥感影像地物提取研究[D]. 武汉: 武汉科技大学, 2021.
HOU Y L. Research on remote sensing image feature ext-raction based on pyramid model and attention mechanism[D]. Wuhan: Wuhan University of Science and Techno-logy, 2021.
[119] 田萱, 王亮, 丁琪. 基于深度学习的图像语义分割方法综述[J]. 软件学报, 2019, 30(2): 440-468.
TIAN X, WANG L, DING Q. Review of image semantic segmentation based on deep learning[J]. Journal of Soft-ware, 2019, 30(2): 440-468.
[120] 王宇, 张焕君, 黄海新. 基于深度学习的图像语义分割算法综述[J]. 电子技术应用, 2019, 45(6): 23-27.
WANG Y, ZHANG H J, HUANG H X. A survey of image semantic segmentation algorithms based on deep learning[J]. Application of Electronic Technique, 2019, 45(6): 23-27.
[121] 梁新宇, 罗晨, 权冀川, 等. 基于深度学习的图像语义分割技术研究进展[J]. 计算机工程与应用, 2020, 56(2): 18-28.
LIANG X Y, LUO C, QUAN J C, et al. Research on pro-gress of image semantic segmentation based on deep learning[J]. Computer Engineering and Applications, 2020, 56(2): 18-28.
[122] 王施云, 杨帆. 基于U-Net特征融合优化策略的遥感影像语义分割方法[J]. 计算机科学, 2021, 48(8): 162-168.
WANG S Y, YANG F. Optimization strategy remote sensing image semantic segmentation method based on U-Net fea-ture fusion[J]. Computer Science, 2021, 48(8): 162-168.
[123] 徐长友, 樊绍胜, 朱航. 采用通道域注意力机制Deeplabv3+算法的遥感影像语义分割[J]. 控制工程, 2023, 30(2): 368-375.
XU C Y, FAN S S, ZHU H. Semantic segmentation of remote sensing images using the channel domain attention mechanism Deeplabv3+ algorithm[J]. Control Enginee-ring of China, 2023, 30(2): 368-375.
[124] 徐丽, 王铭磊, 屈立成. 基于改进双U-Net的遥感影像道路提取方法[J]. 信息技术, 2021(10): 20-25.
XU L, WANG M L, QU L C. Road extraction from remote sensing image based on improved dual U-Net[J]. Informa-tion Technology, 2021(10): 20-25.
[125] 李明龙. 基于深度学习的遥感图像语义分割技术研究[D]. 北京: 中国科学院大学, 2021.
LI M L. Research on semantic segmentation technology of aerial images based on deep learning[D]. Beijing: Uni-versity of Chinese Academy of Sciences, 2021.
[126] 李伟. 基于深度学习的遥感图像语义分割方法研究[D]. 哈尔滨: 东北农业大学, 2021.
LI W. Research on semantic segmentation method of remote sensing image basedon deep learning[D]. Haerbin: Northeast Agricultural University, 2021.
[127] 林锦发. 基于深度学习的遥感图像语义分割方法研究[D]. 广州: 广东工业大学, 2019.
LIN J F. Research on semantic segmentation of remote sensing image based on deep learning[D]. Guangzhou: Guangdong University of Technology, 2019.
[128] 罗咏潭. 基于深度学习的遥感图像道路提取与语义分割[D]. 厦门: 厦门大学, 2019.
LUO Y T. Semantic segmentation and road extraction from remotesensing images based on deep learning[D]. Xiamen: Xiamen University, 2019.
[129] 徐翔. 基于深度学习的遥感影像语义分割方法研究[D]. 贵阳: 贵州大学, 2021.
XU X. Semantic segmentation of remote sensing image based on deep learning[D]. Guiyang: Guizhou University, 2021.
[130] 苏志鹏, 李景文, 姜建武, 等. 基于改进DeepLabV3+的遥感影像语义分割方法[J]. 激光与光电子学进展, 2023, 60(6): 359-366.
SU Z P, LI J W, JIANG J W, et al. Semantic segmentation method for remote sensing images based on improved DeepLabV3+[J]. Laser & Optoelectronics Progress, 2023, 60(6): 359-366.
[131] 黄恒青. 基于深度学习的高分辨率遥感图像建筑物分割方法研究[D]. 南宁: 广西大学, 2020.
HUANG H Q. Research on high resolution remote sen-sing image building segmentation based on deep learning[D]. Nanning: Guangxi University, 2020.
[132] 田雪伟. 基于深度学习的遥感图像语义分割算法研究[D]. 上海: 上海海洋大学, 2022.
TIAN X W. Research on the semantic segmentation algori-thm of remote sensing images based on deep learning[D]. Shanghai: Shanghai Ocean University, 2022.