Urban impervious surface extraction based on the deep features of high-resolution remote sensing image and ensemble learning

doi:10.11947/j.AGCS.2024.20220389

Abstract

Abstract:

The effective extraction of urban impervious surface is important on the application of high-resolution remote sensing. Focusing on existing issues, an urban impervious surface extraction method is proposed based on U-Net combining with ensemble machine learning. The impervious surface areas with different density are selected as the experimental areas. Firstly, the deep features of high-resolution images are extracted by U-Net with the GF-2 multispectral data. Then, the urban impervious surface is extracted by using the ensemble learning with stacking mechanism. The experimental results show that the ensemble learning based on deep features of high-resolution remote sensing image can obtain high accuracy of urban impervious surface extraction. In the experimental areas with different density of urban impervious surface, the overall accuracy is not less than 91.66%, and Kappa is not less than 0.83. The commission error is 7.83%~9.39%; the omission error is 7.22%~14.88%. Compared with the ensemble learning, random forest and support vector machine based on image spectral features, the overall accuracy and Kappa are increased in experimental areas with relatively sparse, medium dense, dense and complex distribution of impervious surface. The commission and omission errors are significantly reduced. This indicates that the deep features can effectively improve the mapping accuracy and user accuracy of integrated learning to extract impervious surface. Compared with U-Net and SegNet, the overall accuracy and Kappa are increased by in the four experimental areas with relatively sparse, medium dense, dense and complex distribution of impervious surface. The commission errors are significantly reduced. The integration ensemble learning with deep learning can effectively improve the mapping accuracy and user accuracy of impervious surface extraction. In general, the ensemble learning based on the deep features of high-resolution remote sensing image can obtain higher accuracy of urban impervious surface extraction, which has application prospects in urban land use/cover classification.

Key words: U-Net network, ensemble learning, deep features, urban impervious surface, high spatial resolution, GF-2

CLC Number:

P237

Xuetao LI, Pancheng WANG, Yongnian ZENG. Urban impervious surface extraction based on the deep features of high-resolution remote sensing image and ensemble learning[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(4): 700-711.

Figures/Tables 9

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Tab. 1

Fig. 7

Tab. 2

References 51

[1]	WENG Qihao. Remote sensing of impervious surfaces in the urban areas: requirements, methods, and trends[J]. Remote Sensing of Environment, 2012, 117:34-49.
[2]	徐涵秋, 王美雅. 地表不透水面信息遥感的主要方法分析[J]. 遥感学报, 2016, 20(5):1270-1289.
	XU Hanqiu, WANG Meiya. Remote sensing-based retrieval of ground impervious surfaces[J]. Journal of Remote Sensing, 2016, 20(5):1270-1289.
[3]	YUAN Fei, BAUER M E. Comparison of impervious surface area and normalized difference vegetation index as indicators of surface urban heat island effects in Landsat imagery[J]. Remote Sensing of Environment, 2007, 106(3):375-386.
[4]	曾永年, 张璎璎, 张鸿辉, 等. 城市扩展强度及其地表热特性遥感定量分析[J]. 测绘学报, 2010, 39(1):65-70,94.
	ZENG Yongnian, ZHANG Yingying, ZHANG Honghui, et al. A quantitative analysis of urban growth and associated thermal characteristics using remote sensing data[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(1):65-70,94.
[5]	YU Huafei, ZHAO Yaolong, FU Yingchun, et al. Spatiotemporal variance assessment of urban rainstorm waterlogging affected by impervious surface expansion: a case study of Guangzhou, China[J]. Sustainability, 2018, 10(10):3761.
[6]	宫鹏, 黎夏, 徐冰. 高分辨率影像解译理论与应用方法中的一些研究问题[J]. 遥感学报, 2006, 10(1):1-5.
	GONG Peng, LI Xia, XU Bing. Interpretation theory and application method development for information extraction from high resolution remotely sensed data[J]. Journal of Remote Sensing, 2006, 10(1):1-5.
[7]	HU Xuefei, WENG Qihao. Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method[J]. Geocarto International, 2011, 26(1):3-20.
[8]	李德仁, 童庆禧, 李荣兴, 等. 高分辨率对地观测的若干前沿科学问题[J]. 中国科学：地球科学, 2012, 42(6):805-813.
	LI Deren, TONG Qingxi, LI Rongxing, et al. Some frontier scientific problems of high-resolution earth observation[J]. Scientia Sinica (Terrae), 2012, 42(6):805-813.
[9]	张翰超, 宁晓刚, 王浩, 等. 基于高分辨率遥感影像的2000—2015年中国省会城市高精度扩张监测与分析[J]. 地理学报, 2018, 73(12):2345-2363.
	ZHANG Hanchao, NING Xiaogang, WANG Hao, et al. High accuracy urban expansion monitoring and analysis of China's provincial capitals from 2000 to 2015 based on high-resolution remote sensing imagery[J]. Acta Geographica Sinica, 2018, 73(12):2345-2363.
[10]	HUANG X, WANG Y, LI J, et al. High-resolution urban land-cover mapping and landscape analysis of the 42 major cities in China using ZY-3 satellite images[J]. Sci Bull (Beijing), 2020, 65(12):1039-1048.
[11]	NEYNS R, CANTERS F. Mapping of urban vegetation with high-resolution remote sensing: a review[J]. Remote Sensing, 2022, 14(4):1031.
[12]	BLASCHKE T, HAY G J, KELLY M, et al. Geographic object-based image analysis-towards a new paradigm[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87:180-191.
[13]	JOZDANI S E, JOHNSON B A, CHEN Dongmei. Comparing deep neural networks, ensemble classifiers, and support vector machine algorithms for object-based urban land use/land cover classification[J]. Remote Sensing, 2019, 11(14):1713.
[14]	JOHNSON B, XIE Zhixiao. Classifying a high resolution image of an urban area using super-object information[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 83:40-49.
[15]	MYINT S W, GOBER P, BRAZEL A, et al. Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery[J]. Remote Sensing of Environment, 2011, 115(5):1145-1161.
[16]	TREITZ P. High spatial resolution remote sensing data for forest ecosystem classification an examination of spatial scale[J]. Remote Sensing of Environment, 2000, 72(3):268-289.
[17]	WANG L, SOUSA W P, GONG P. Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery[J]. International Journal of Remote Sensing, 2004, 25(24):5655-5668.
[18]	YU Qian, GONG Peng, CLINTON N, et al. Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery[J]. Photogrammetric Engineering & Remote Sensing, 2006, 72(7):799-811.
[19]	HUANG Xin, ZHANG Liangpei. An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(12):4173-4185.
[20]	TRIAS-SANZ R, STAMON G, LOUCHET J. Using colour, texture, and hierarchial segmentation for high-resolution remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(2):156-168.
[21]	SU Wei, LI Jing, CHEN Yunhao, et al. Textural and local spatial statistics for the object-oriented classification of urban areas using high resolution imagery[J]. International Journal of Remote Sensing, 2008, 29(11):3105-3117.
[22]	MA Lei, LI Manchun, MA Xiaoxue, et al. A review of supervised object-based land-cover image classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130:277-293.
[23]	BELGIU M, DRAGUT L. Random forest in remote sensing: a review of applications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114:24-31.
[24]	杜培军, 阿里木·赛买提. 高分辨率遥感影像分类的多示例集成学习[J]. 遥感学报, 2013, 17(1):77-97.
	DU Peijun, SAMAT Alim. Multiple instance ensemble learning method for high-resolution remote sensing image classification[J]. Journal of Remote Sensing, 2013, 17(1):77-97.
[25]	MOUNTRAKIS G, IM J, OGOLE C. Support vector machines in remote sensing: a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(3):247-259.
[26]	周培诚, 程塨, 姚西文, 等. 高分辨率遥感影像解译中的机器学习范式[J]. 遥感学报, 2021, 25(1):182-197.
	ZHOU Peicheng, CHENG Gong, YAO Xiwen, et al. Machine learning paradigms in high-resolution remote sensing image interpretation[J]. National Remote Sensing Bulletin, 2021, 25(1):182-197.
[27]	YUAN Qiangqiang, SHEN Huanfeng, LI Tongwen, et al. Deep learning in environmental remote sensing: achievements and challenges[J]. Remote Sensing of Environment, 2020, 241:111716.
[28]	MA Lei, LIU Yu, ZHANG Xueliang, et al. Deep learning in remote sensing applications: a meta-analysis and review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 152:166-177.
[29]	HEYDARI S S, MOUNTRAKIS G. Meta-analysis of deep neural networks in remote sensing: a comparative study of mono-temporal classification to support vector machines[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 152:192-210.
[30]	GUO Mingqiang, LIU Heng, XU Yongyang, et al. Building extraction based on U-net with an attention block and multiple losses[J]. Remote Sensing, 2020, 12(9):1400.
[31]	XU Yongyang, WU Liang, XIE Zhong, et al. Building extraction in very high resolution remote sensing imagery using deep learning and guided filters[J]. Remote Sensing, 2018, 10(1):144.
[32]	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.
[33]	LÜ Xianwei, MING Dongping, LU Tingting, et al. A new method for region-based majority voting CNNs for very high resolution image classification[J]. Remote Sensing, 2018, 10(12):1946.
[34]	王斌, 陈占龙, 吴亮, 等. 兼顾连通性的U-Net网络高分辨率遥感影像道路提取[J]. 遥感学报, 2020, 24(12):1488-1499.
	WANG Bin, CHEN Zhanlong, WU Liang, et al. Road extraction of high-resolution satellite remote sensing images in U-Net network with consideration of connectivity[J]. National Remote Sensing Bulletin, 2020, 24(12):1488-1499.
[35]	FU Gang, LIU Changjun, ZHOU Rong, et al. Classification for high resolution remote sensing imagery using a fully convolutional network[J]. Remote Sensing, 2017, 9(5):498.
[36]	HU Yunfeng, ZHANG Qianli, ZHANG Yunzhi, et al. A deep convolution neural network method for land cover mapping: a case study of Qinhuangdao, China[J]. Remote Sensing, 2018, 10(12):2053.
[37]	陈妮, 应丰, 王静, 等. 基于U-Net的高分辨率遥感图像土地利用信息提取[J]. 遥感技术与应用, 2021, 36(2):285-292.
	CHEN Ni, YING Feng, WANG Jing, et al. Research on land use information extraction based on U-net[J]. Remote Sensing Technology and Application, 2021, 36(2):285-292.
[38]	徐知宇, 周艺, 王世新, 等. 面向GF-2遥感影像的U-Net城市绿地分类[J]. 中国图象图形学报, 2021, 26(3):700-713.
	XU Zhiyu, ZHOU Yi, WANG Shixin, et al. U-Net for urban green space classification in Gaofen-2 remote sensing images[J]. Journal of Image and Graphics, 2021, 26(3):700-713.
[39]	蔡博文, 王树根, 王磊, 等. 基于深度学习模型的城市高分辨率遥感影像不透水面提取[J]. 地球信息科学学报, 2019, 21(9):1420-1429.
	CAI Bowen, WANG Shugen, WANG Lei, et al. Extraction of urban impervious surface from high-resolution remote sensing imagery based on deep learning[J]. Journal of Geo-Information Science, 2019, 21(9):1420-1429.
[40]	HUANG Fenghua, YU Ying, FENG Tinghao. Automatic extraction of impervious surfaces from high resolution remote sensing images based on deep learning[J].Journal of Visual Communication and Image Representation, 2019, 58:453-461.
[41]	FU Yongyong, LIU Kunkun, SHEN Zhangquan, et al. Mapping impervious surfaces in town-rural transition belts using China's GF-2 imagery and object-based deep CNNs[J]. Remote Sensing, 2019, 11(3):280.
[42]	孙根云, 王鑫, 安娜, 等. 基于多源遥感的大尺度高分辨率不透水面深度学习提取方法[J]. 测绘学报, 2023, 52(2):272-282.DOI: 10.11947/j.AGCS.2023.20210546.
	SUN Genyun, WANG Xin, AN Na, et al. A method for large-scale and high-resolution impervious surface extraction based on multi-source remote sensing and deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(2):272-282.DOI: 10.11947/j.AGCS.2023.20210546.
[43]	CHANG Ruichun, HOU Dong, CHEN Zhe, et al. Automatic extraction of urban impervious surface based on SAH-unet[J]. Remote Sensing, 2023, 15(4):1042.
[44]	SHAO Zhenfeng, CHENG Tao, FU Huyan, et al. Emerging issues in mapping urban impervious surfaces using high-resolution remote sensing images[J]. Remote Sensing, 2023, 15(10):2562.
[45]	冯权泷, 陈泊安, 李国庆, 等. 遥感影像样本数据集研究综述[J]. 遥感学报, 2022, 26(4):589-605.
	FENG Quanlong, CHEN Boan, LI Guoqing, et al. A review for sample datasets of remote sensing imagery[J]. National Remote Sensing Bulletin, 2022, 26(4):589-605.
[46]	CHENG Gong, LI Zhenpeng, HAN Junwei, et al. Exploring hierarchical convolutional features for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(11):6712-6722.
[47]	许夙晖, 慕晓冬, 赵鹏, 等. 利用多尺度特征与深度网络对遥感影像进行场景分类[J]. 测绘学报, 2016, 45(7):834-840.DOI: 10.11947/J.AGCS.2016.20150623.
	XU Suhui, MU Xiaodong, ZHAO Peng, et al. Scene classification of remote sensing image based on multi-scale feature and deep neural network[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7):834-840.DOI: 10.11947/J.AGCS.2016.20150623.
[48]	余东行, 张保明, 赵传, 等. 联合卷积神经网络与集成学习的遥感影像场景分类[J]. 遥感学报, 2020, 24(6):717-727.
	YU Donghang, ZHANG Baoming, ZHAO Chuan, et al. Scene classification of remote sensing image using ensemble convolutional neural network[J]. Journal of Remote Sensing, 2020, 24(6):717-727.
[49]	LI Ruirui, LIU Wenjie, YANG Lei, et al. DeepUNet: a deep fully convolutional network for pixel-level sea-land segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11):3954-3962.
[50]	XU W, DENG X, GUO S, et al. High-resolution U-net: preserving image details for cultivated land extraction[J]. Sensors (Basel), 2020, 20(15):E4064.
[51]	RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Proceedings of 2005 International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin: Springer, 2005: 234-241.

密集程度	ACC/(%)	P/(%)	R/(%)	F₁值	Kappa系数
稀疏	98.26	91.51	85.12	0.88	0.87
中等密集	97.29	92.17	88.16	0.90	0.89
密集	91.66	90.61	92.78	0.92	0.83
复杂	93.91	91.41	90.25	0.91	0.86

方法	密集程度	ACC/(%)	P/(%)	R/(%)	F₁值	Kappa系数
本文方法	稀疏	98.26	91.51	85.12	0.88	0.87
	中等密集	97.29	92.17	88.16	0.90	0.89
	密集	91.66	90.61	92.78	0.92	0.83
	复杂	93.91	91.41	90.25	0.91	0.86
集成学习	稀疏	96.32	74.85	78.00	0.76	0.74
	中等密集	92.41	68.98	83.20	0.76	0.71
	密集	78.92	93.09	62.06	0.78	0.58
	复杂	88.84	85.44	80.46	0.83	0.75
随机森林	稀疏	62.51	97.10	75.86	0.69	0.66
	中等密集	59.11	89.24	74.89	0.66	0.60
	密集	90.16	78.02	62.47	0.74	0.67
	复杂	73.15	85.92	91.72	0.81	0.70
支持向量机	稀疏	67.31	95.66	83.89	0.75	0.72
	中等密集	65.00	91.24	80.99	0.72	0.67
	密集	92.12	72.03	47.63	0.63	0.44
	复杂	67.86	83.30	95.40	0.79	0.66
U-Net	稀疏	97.62	91.39	75.96	0.84	0.82
	中等密集	95.74	90.99	77.23	0.844	0.81
	密集	89.85	89.75	87.32	0.90	0.80
	复杂	89.78	87.72	80.86	0.83	0.77
SegNet	稀疏	92.74	71.11	81.02	0.76	0.72
	中等密集	96.25	76.69	73.16	0.75	0.73
	密集	84.95	85.60	83.71	0.85	0.70
	复杂	88.53	85.47	79.30	0.82	0.74