基于自适应半监督模糊C均值的遥感变化检测

doi:10.12082/dqxxkx.2022.210237

地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (3): 508-521.doi: 10.12082/dqxxkx.2022.210237

基于自适应半监督模糊C均值的遥感变化检测

邵攀¹^,²(), 范红梅¹^,²^,^*(), 高梓昂¹^,²

1.三峡大学湖北省农田环境监测工程技术研究中心, 宜昌 443002
2.三峡大学计算机与信息学院, 宜昌 443002

收稿日期:2021-04-29 修回日期:2021-07-05 出版日期:2022-03-25 发布日期:2022-05-25
通讯作者: *范红梅(1997— ),女,湖北咸宁人,硕士生,主要从事遥感图像处理,变化检测研究。E-mail: fanhm@ctgu.edu.cn
作者简介:邵攀(1985— ),男,河南安阳人,博士,副教授,主要从事遥感图像处理,人工智能,信息融合研究。E-mail: panshao@whu.edu.cn
基金资助:
国家自然科学基金项目(41901341)

An Adaptive and Semi-Supervised Fuzzy C-means Clustering Algorithm for Remotely Sensed Change Detection

SHAO Pan¹^,²(), FAN Hongmei¹^,²^,^*(), GAO Ziang¹^,²

1. Hubei Engineering Technology Research Center for Farmland Environment Monitoring, China Three Gorges University, Yichang 443002, China
2. College of Computer and Information Technology, China Three Gorges University, Yichang 443002, China

Received:2021-04-29 Revised:2021-07-05 Online:2022-03-25 Published:2022-05-25
Contact: FAN Hongmei
Supported by:
National Natural Science Foundation of China(41901341)

摘要/Abstract

摘要：

遥感变化检测是开展对地观测应用的关键技术之一,在城市研究、灾害评估以及资源调查等领域发挥着重要的作用。本文针对基于差分影像的遥感变化检测展开研究,提出一种基于自适应半监督模糊C均值(Adaptive and Semi-Supervised Fuzzy C-means, ASFCM)聚类的变化检测技术。① ASFCM根据“差分影像像素灰度值越大,则对应区域发生变化可能性越大”的性质,通过阈值技术自适应、自动地分析差分影像灰度直方图并将其划分为两部分：几乎可确定类别区域和不确定区域;② 将差分影像像素灰度值、空间上下文信息和几乎可确定类别区域像素的伪类别标签信息集成到模糊聚类过程,生成差分影像的模糊隶属度函数;③ 通过最大隶属度原则生成变化检测图。ASFCM通过半监督策略利用伪类别标签信息指导聚类过程,通过空间引力模型优化的模糊因子自适应地利用差分影像的空间相关性,能够得到更加准确的模糊隶属度函数和更优的变化检测结果。3组真实遥感数据的实验结果验证了ASFCM的有效性：ASFCM在Bangladesh数据上的kappa系数为0.9188,比其它方法提高3.5%~16.4%;在Madeirinha数据上的Kappa系数为0.9379,比其他方法提高2.18%~7.13%;在黑龙江数据上的Kappa系数为0.8696,比其它方法提高2.88%~22.02%。

关键词: 遥感, 变化检测, 模糊聚类算法, 自适应, 伪标签, 空间信息, 模糊因子, 半监督

Abstract:

Remote sensing change detection plays an important role in earth observation. This paper presents a novel Adaptive and Semi-Supervised Fuzzy C-Means (ASFCM) clustering algorithm for remote sensing change detection. The proposed ASFCM method integrates semi-supervised technique, spatial attraction model, and fuzzy factor into fuzzy clustering process, and thus can make full use of the characteristics of difference image. ASFCM consists of three main steps. Firstly, according to the property “the larger the gray values of the pixels in difference image, the more likely the pixels belong to the change region”, the difference image is partitioned into two parts-the nearly certain part and the uncertain part-by analyzing the histogram of difference image using thresholds, which are adaptively and automatically obtained. The pixels in the nearly certain part possess a high probability of belonging to the unchanged or changed class. Secondly, the gray values of pixels, the spatial-contextual information, and the pseudo labels of the nearly certain pixels are jointly exploited in the well-designed ASFCM algorithm to compute the membership functions of difference image. Finally, a change detection map is generated by applying the maximum membership principle to the computed membership functions. On the one hand, ASFCM uses the labeling information of the nearly certain pixels to guide the clustering process through semi-supervised scheme. As a result, the change information is enhanced and more accurate membership is achieved. On the other hand, ASFCM employs the spatial attraction model to improve the traditional fuzzy factor. The improved fuzzy factor is then used to integrate the spatial information adaptively, for reducing the effect of noise and outliers. Owing to the above two aspects, the proposed ASFCM method can obtain more accurate change detection result. Three real remote sensing datasets were used to evaluate the performance of the proposed ASFCM method. Eight state-of-the-art change detection methods were used as the comparative methods. The first dataset consists of two synthetic aperture radar images acquired by Envisat in April 2007 and July 2007. For the first dataset, the proposed ASFCM produced the lowest overall error rate (1.99%) and highest Kappa coefficient (91.88%). The second dataset is made up of two Landsat Thematic Mapper images acquired in July 2000 and July 2006. For the second dataset, ASFCM generated the lowest overall error rate (1.69%) and highest Kappa coefficient (93.79%). The third dataset contains two Landsat-7 ETM+ images acquired in August 2001 and August 2002. For the third dataset, ASFCM also gave the lowest overall error rate (2.71%) and highest Kappa coefficient (86.96%). Experimental results demonstrated the effectiveness of the proposed ASFCM method for change detection.

Key words: remote sensing, change detection, fuzzy clustering algorithm, adaptive, pseudo labels, spatial information, fuzzy factor, semi-supervised

邵攀, 范红梅, 高梓昂. 基于自适应半监督模糊C均值的遥感变化检测[J]. 地球信息科学学报, 2022, 24(3): 508-521.DOI:10.12082/dqxxkx.2022.210237

SHAO Pan, FAN Hongmei, GAO Ziang. An Adaptive and Semi-Supervised Fuzzy C-means Clustering Algorithm for Remotely Sensed Change Detection[J]. Journal of Geo-information Science, 2022, 24(3): 508-521.DOI:10.12082/dqxxkx.2022.210237

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

表4

参考文献 27

[1]	邵攀. 非监督遥感变化检测模糊方法研究[D]. 武汉:武汉大学, 2016.
	[ Shao P. Study on fuzzy unsupervised change detection methods based on remotely sensed image[D]. Wuhan: Wuhan University, 2016. ]
[2]	公茂果, 苏临之, 李豪, 等. 合成孔径雷达影像变化检测研究进展[J]. 计算机研究与发展, 2016, 53(1):123-137.
	[ Gong M G, Su L Z, Li H, et al. Research progress of SAR image change detection[J]. Journal of Computer Research and Development, 2016, 53(1):123-137. ] DOI: 10.7544/issn1000-1239.2016.20150662
[3]	吴瑞娟, 何秀凤, 王静. 结合像元级与对象级的滨海湿地变化检测方法[J]. 地球信息科学学报, 2020, 22(10):2078-2087. doi: 10.12082/dqxxkx.2020.190417
	[ Wu R J, He X F, Wang J. Coastal wetlands change detection combining pixel-based and object-based methods[J]. Journal of Geo-information Science, 2020, 22(10):2078-2087. ] DOI: 10.12082/dqxxkx.2020.190417
[4]	Liu G, Gousseau Y, Tupin F. A Contrario comparison of local descriptors for change detection in very high spatial resolution satellite images of urban areas[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(6):3904-3918. DOI: 10.1109/TGRS.2018.2888985 doi: 10.1109/TGRS.36
[5]	Gong M G, Zhou Z Q, Ma J J. Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering[J]. IEEE Transactions on Image Processing, 2012, 21(4):2141-2151. doi: 10.1109/TIP.2011.2170702
[6]	Patra S, Ghosh S, Ghosh A. Histogram thresholding for unsupervised change detection of remote sensing images[J]. International Journal of Remote Sensing, 2011, 32(21):6071-6089. DOI: 10.1080/01431161.2010.507793 doi: 10.1080/01431161.2010.507793
[7]	Bruzzone L, Prieto D F. Automatic analysis of the difference image for unsupervised change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3):1171-1182. DOI: 10.1109/36.843009 doi: 10.1109/36.843009
[8]	Ghosh A, Mishra N S, Ghosh S. Fuzzy clustering algorithms for unsupervised change detection in remote sensing images[J]. Information Sciences, 2011, 181(4):699-715. DOI: 10.1016/j.ins.2010.10.016 doi: 10.1016/j.ins.2010.10.016
[9]	Liu L Y, Jia Z H, Yang J E, et al. SAR image change detection based on mathematical morphology and the K-means clustering algorithm[J]. IEEE Access, 2019, 7:43970-43978. DOI: 10.1109/ACCESS.2019.2908282 doi: 10.1109/Access.6287639
[10]	Bezdek J C. Pattern recognition with fuzzy objective function algorithms[M]. New York: Springer, Boston, MA, 1981.
[11]	王建明, 史文中, 邵攀. 自适应距离和模糊拓扑优化的模糊聚类SAR影像变化检测[J]. 测绘学报, 2018, 47(5):611-619.
	[ Wang J M, Shi W Z, Shao P. Fuzzy clustering SAR image change detection based on adaptive distance and fuzzy topology optimization[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(5):611-619. ] DOI: 10.11947/j.AGCS.2018.20160607
[12]	Gong M, Su L, Jia M, et al. Fuzzy clustering with a modified MRF energy function for change detection in synthetic aperture radar images[J]. IEEE Transactions on Fuzzy Systems, 2014, 22(1):98-109. DOI: 10.1109/TFUZZ.2013.2249072 doi: 10.1109/TFUZZ.2013.2249072
[13]	Hao M, Zhang H, Shi W, et al. Unsupervised change detection using fuzzy C-means and MRF from remotely sensed images[J]. Remote Sensing Letters, 2013, 4(12):1185-1194. DOI: 10.1109/ICAPR.2009.82 doi: 10.1080/2150704X.2013.858841
[14]	Hao M, Hua Z, Li Z X, et al. Unsupervised change detection using a novel fuzzy c-means clustering simultaneously incorporating local and global information[J]. Multimedia Tools and Applications, 2017, 76(19):20081-20098. DOI: 10.1007/s11042-017-4354-1 doi: 10.1007/s11042-017-4354-1
[15]	Shao P, Shi W Z, He P F, et al. Novel approach to unsupervised change detection based on a robust semi-supervised FCM clustering algorithm[J]. Remote Sensing, 2016, 8(3):264. DOI: 10.3390/rs8030264 doi: 10.3390/rs8030264
[16]	Ahmed M N, Yamany S M, Mohamed N, et al. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data[J]. IEEE Transactions on Medical Imaging, 2002, 21(3):193-199. DOI: 10.1109/42.996338 pmid: 11989844
[17]	Chen S C, Zhang D Q. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[J]. IEEE Transactions on Systems, Man, and Cybernetics, 2004, 34(4):1907-1916. DOI: 10.1109/TSMCB.2004.831165
[18]	Cai W L, Chen S C, Zhang D Q. Fast and robust fuzzy C-means clustering algorithms incorporating local information for image segmentation[J]. Pattern Recognition, 2007, 40(3):825-838. DOI: 10.1016/j.patcog.2006.07.011 doi: 10.1016/j.patcog.2006.07.011
[19]	Krinidis S, Chatzis V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5):1328-1337. DOI: 10.1109/TIP.2010.2040763 doi: 10.1109/TIP.2010.2040763 pmid: 20089475
[20]	Ma J, Gong M, Zhou Z. Wavelet fusion on ratio images for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(6):1122-1126. DOI: 10.1109/LGRS.2012.2191387 doi: 10.1109/LGRS.2012.2191387
[21]	Zhang H, Wang Q M, Shi W Z, et al. A novel adaptive fuzzy local information C-means clustering algorithm for remotely sensed imagery classiﬁcation. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(9):5057-5068. DOI: 10.1109/TGRS.2017.2702061 doi: 10.1109/TGRS.2017.2702061
[22]	季欣然, 黄亮, 陈朋弟. 结合变化向量分析和直觉模糊聚类的遥感影像变化检测方法[J]. 全球定位系统, 2020, 45(6):100-106.
	[ Ji X R, Huang L A, Chen P D. Change detection in remote sensing images combined with intuitionistic fuzzy clustering and change vector analysis[J]. GNSS World of China, 2020, 45(6):100-106. ] DOI: 10.13442/j.gnss.1008-9268.2020.06.015
[23]	Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66. doi: 10.1109/TSMC.1979.4310076
[24]	Bovolo F, Bruzzone L, Marconcini M. A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(7):2070-2082. DOI: 10.1109/TGRS.2008.916643 doi: 10.1109/TGRS.2008.916643
[25]	Yetgin Z. Unsupervised change detection of satellite images using local gradual descent[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(5):1919-1929. DOI: 10.1109/TGRS.2011.2168230 doi: 10.1109/TGRS.2011.2168230
[26]	Gao F, Wang X A, Gao Y H, et al. Sea ice change detection in SAR images based on convolutional-wavelet neural networks[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(8):1240-1244. DOI: 10.1109/LGRS.201 9.2895656 doi: 10.1109/LGRS.8859
[27]	Mishra N S, Ghosh S, Ghosh A. Fuzzy clustering algorithms incorporating local information for change detection in remotely sensed images[J]. Applied Soft Computing, 2012, 12(8):2683-2692. DOI: 10.1016/j.asoc.2012.03.060 doi: 10.1016/j.asoc.2012.03.060

算法	虚检	虚检率	漏检	漏检率	整体错误	整体错误率	Kappa系数	时间/s
FCM	6	0.0001	4756	0.3558	4762	0.0529	0.7548	0.29
FLICM	9	0.0001	4580	0.3427	4589	0.0510	0.7653	3.04
RFLICM	16	0.0002	4497	0.3365	4513	0.0501	0.7699	2.05
AFLICM	5	0.0001	4478	0.3350	4483	0.0498	0.7708	1.66
FatFLICM	268	0.0035	2217	0.1659	2485	0.0276	0.8838	4.51
RSFCM	11	0.0001	4140	0.3097	4151	0.0461	0.7910	1.36
CVA-IFCM	673	0.0088	1904	0.1425	2577	0.0286	0.8823	6.49
CWNN	21	0.0003	4076	0.3050	4097	0.0455	0.7942	>450
ASFCM	358	0.0047	1430	0.1070	1788	0.0199	0.9188	1.82

算法	虚检	虚检率	漏检	漏检率	整体错误	整体错误率	Kappa系数	时间/s
FCM	142	0.0009	6127	0.1959	6269	0.0335	0.8697	0.69
FLICM	175	0.0011	6234	0.1993	6409	0.0343	0.8666	8.06
RFLICM	193	0.0012	5884	0.1882	6077	0.0325	0.8742	4.55
AFLICM	164	0.0011	5551	0.1775	5715	0.0306	0.8822	3.73
FatFLICM	3944	0.0253	612	0.0196	4556	0.0244	0.9161	9.65
RSFCM	178	0.0011	5463	0.1747	5641	0.0302	0.8839	3.16
CVA-IFCM	1031	0.0066	4202	0.1344	5233	0.0280	0.8953	13.58
CWNN	3208	0.0206	1419	0.0454	4627	0.0247	0.9132	>500
ASFCM	722	0.0046	2442	0.0781	3164	0.0169	0.9379	3.97

算法	虚检	虚检率	漏检	漏检率	整体错误	整体错误率	Kappa系数	时间/s
FCM	6093	0.0042	49 366	0.2457	55 459	0.0336	0.8268	4.66
FLICM	3358	0.0023	56 085	0.2792	59 443	0.0360	0.8101	89.66
RFLICM	3899	0.0027	53 293	0.2653	57 192	0.0347	0.8187	82.43
AFLICM	5923	0.0041	46 704	0.2325	52 627	0.0319	0.8366	36.63
FatFLICM	527	0.0004	82 848	0.4124	83 375	0.0505	0.7131	95.38
RSFCM	8171	0.0056	43 729	0.2177	51 900	0.0315	0.8408	42.50
CVA-IFCM	37 778	0.0261	23 207	0.1155	60 985	0.0370	0.8324	121.75
CWNN	137 700	0.0950	17 807	0.0886	155 507	0.0942	0.6494	>2000
ASFCM	16 088	0.0111	28 684	0.1428	44 772	0.0271	0.8696	47.81

	算法	虚检	虚检率	漏检	漏检率	整体错误	整体错误率	Kappa系数
Bangladesh 数据	RSFCM	11	0.0001	4140	0.3097	4151	0.0461	0.7910
	SSFCM	106	0.0014	2579	0.1930	2685	0.0298	0.8723
	ASFCM	358	0.0047	1430	0.1070	1788	0.0199	0.9188
Madeirinha 数据	RSFCM	178	0.0011	5463	0.1747	5641	0.0302	0.8839
	SSFCM	1061	0.0068	3101	0.0992	4162	0.0223	0.9180
	ASFCM	722	0.0046	2442	0.0781	3164	0.0169	0.9379
黑龙江数据	RSFCM	8171	0.0056	43 729	0.2177	51 900	0.0315	0.8408
	SSFCM	9243	0.0063	38 171	0.1900	47 314	0.0287	0.8570
	ASFCM	16 088	0.0111	28 684	0.1428	44 772	0.0271	0.8696

基于自适应半监督模糊C均值的遥感变化检测

An Adaptive and Semi-Supervised Fuzzy C-means Clustering Algorithm for Remotely Sensed Change Detection

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 27

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	杨颖频, 吴志峰, 黄启厅, 骆剑承, 吴田军, 董文, 胡晓东, 肖文菊. 协同遥感与统计数据的粤西甘蔗种植分布提取及时空分析[J]. 地球信息科学学报, 2023, 25(5): 1012-1026.
[2]	刘潇, 刘智, 林雨准, 王淑香, 左溪冰. 面向遥感影像场景分类的类中心知识蒸馏方法[J]. 地球信息科学学报, 2023, 25(5): 1050-1063.
[3]	衡雪彪, 许捍卫, 唐璐, 汤恒, 许怡蕾. 基于改进全卷积神经网络模型的土地覆盖分类方法研究[J]. 地球信息科学学报, 2023, 25(3): 495-509.
[4]	高建文, 管海燕, 彭代锋, 许正森, 康健, 季雅婷, 翟若雪. 基于局部-全局语义特征增强的遥感影像变化检测网络模型[J]. 地球信息科学学报, 2023, 25(3): 625-637.
[5]	高鹏飞, 曹雪峰, 李科, 游雄. 融合多元稀疏特征与阶层深度特征的遥感影像目标检测[J]. 地球信息科学学报, 2023, 25(3): 638-653.
[6]	秦肖伟, 程博, 杨志平, 李林, 董文, 张新, 杨树文, 靳宗义, 薛庆. 基于时序遥感影像的西南山区地块尺度作物类型识别[J]. 地球信息科学学报, 2023, 25(3): 654-668.
[7]	陈凯, 雷少华, 代文, 王春, 刘爱利, 李敏. 基于开源数据和条件生成对抗网络的地形重建方法[J]. 地球信息科学学报, 2023, 25(2): 252-264.
[8]	饶子昱, 卢俊, 郭海涛, 余东行, 侯青峰. 利用视角转换的跨视角影像匹配方法[J]. 地球信息科学学报, 2023, 25(2): 368-379.
[9]	王龙号, 蓝朝桢, 姚富山, 侯慧太, 武蓓蓓. 多源遥感影像深度特征融合匹配算法[J]. 地球信息科学学报, 2023, 25(2): 380-395.
[10]	甘聪聪, 邱炳文, 张建阳, 姚铖鑫, 叶智燕, 黄姮, 黄莹泽, 彭玉凤, 林艺真, 林多多, 苏中豪. 基于Sentinel-1/2动态耦合移栽期特征的水稻种植模式识别[J]. 地球信息科学学报, 2023, 25(1): 153-162.
[11]	华一新, 赵鑫科, 张江水. 地理信息系统研究新范式[J]. 地球信息科学学报, 2023, 25(1): 15-24.
[12]	骆钰波, 陈碧宇. 面向路网轨迹的自适应数据模型与索引结构[J]. 地球信息科学学报, 2023, 25(1): 63-76.
[13]	于明洋, 陈肖娴, 张文焯, 刘耀辉. 融合网格注意力阀门和特征金字塔结构的高分辨率遥感影像建筑物提取[J]. 地球信息科学学报, 2022, 24(9): 1785-1802.
[14]	吴亚楠, 郭长恩, 于东平, 段爱民, 刘玉, 董士伟, 单东方, 吴耐明, 李西灿. 基于不确定性分析的遥感分类空间分层及评估方法[J]. 地球信息科学学报, 2022, 24(9): 1803-1816.
[15]	吕爱锋, 亓珊珊. 遥感及再分析降水产品在缺资料干旱内陆盆地的适用性评估[J]. 地球信息科学学报, 2022, 24(9): 1817-1834.