A New Semi-supervised Change Detection Method of Fusing Spatial Information

doi:10.13474/j.cnki.11-2246.2018.0009

Abstract

Abstract:

Based on the improved semi-supervised fuzzy c-means (SSFCM) algorithm and Markov random field, this paper presents a new semi-supervised change detection method considering spatial information. The difference image is firstly obtained by subtracting two original remote sensing images, and a novel labelling method is introduced by the values of band 4. Then difference image is clustered by SSFCM and labeled samples. To find good monitoring result and remove noise points, this work considers the spatial information of pixels and markov random field. The final monitoring result is obtained by updating the membership matrix. In order to show the validity of the proposed method, two TM remote sensing images are chosen to feed our method to detect the change of forest. The experimental results indicate that the improved semi-supervised FCM algorithm can reduce the missed alarm rate, and Markov random field method can remove the noise points in the process of clustering and reduce the false alarm rate.

Key words: change detection, semi-supervised FCM algorithm, Markov random field, remote sensing image classification

CLC Number:

XIE Fuding, YU Shanshan, YANG Jun. A New Semi-supervised Change Detection Method of Fusing Spatial Information[J]. 测绘通报, 2018, 0(1): 50-54.

References

[1] 周启鸣. 多时相遥感影像变化检测综述[J]. 地理信息世界, 2011, 9(2):28-33.
[2] 贾彩杰. 基于模糊聚类算法的遥感图像变化检测的研究[D]. 西安:西安电子科技大学, 2013.
[3] 刘乐乐,汪云甲,陈国良,等.基于多源遥感数据的城市变化监测研究——以郑州市为例[J].地域研究与开发,2010,29(1):136-140.
[4] 韦玮,崔丽娟, 李胜男,等. 基于偏差平均值的乌梁素海湿地变化监测研究[J]. 林业科学研究, 2012, 25(6):719-725.
[5] 夏双,阮仁宗,颜梅春,等.洪泽湖区土地利用/覆盖变化分析[J].遥感信息,2013,28(1):54-59.
[6] 杜培军,柳思聪. 融合多特征的遥感影像变化检测[J]. 遥感学报, 2012, 16(4):663-677.
[7] YUAN Y, LV H, LU X. Semi-supervised Change Detection Method for Multi-temporal Hyperspectral Images[J]. Neurocomputing, 2015, 148:363-375.
[8] MISHRA N S, GHOSH S, GHOSH A.Fuzzy Clustering Algorithms Incorporating Local Information for Change Detection in Remotely Sensed Images[J]. Applied Soft Computing Jarnal, 2012, 12(8):2683-2692.
[9] 杨红磊,彭军还.基于马尔可夫随机场的模糊c-均值遥感影像分类[J].测绘学报,2012,41(2):213-218.
[10] 郝明. 基于空间信息准确性增强的遥感影像变化检测方法研究[D]. 徐州:中国矿业大学, 2015.
[11] 罗旺. 遥感图像的变化检测与标注方法研究[D]. 西安:电子科技大学, 2012.
[12] PEDRYCZ W,WALETZKY J.Fuzzy Clustering with Partial Supervision[J].IEEE Transactions on Systems Man,and Cybernetics,1997,27(5):787-795.
[13] 谢福鼎,李壮.基于改进的半监督FCM算法的高光谱遥感影像分类[J].测绘通报,2016(9):60-62.
[14] SHAO P, SHI W, HE P, et al. Novel Approach to Unsupervised Change Detection Based on a Robust Semi-supervised FCM Clustering Algorithm[J]. Remote Sensing, 2016, 8(3):264.
[15] SUBUDHI B N, BOVOLO F, GHOSH A, et al. Spatio-contextual Fuzzy Clustering with Markov Random Field Model for Change Detection in Remotely Sensed Images[J].Optics & Laser Technology,2014,57(1):284-292.
[16] GONG Maoguo, LI Yu, JIAO L,et al.SAR Change Detection Based on Intensity and Texture Changes[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,93(93):123-135.