HUO Jiuyuan1,2,3, LIU Meng1
（1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China；2. Lanzhou Ruizhiyuan Information Technology Co., Ltd., Lanzhou 730070, China;3. National Cryosphere Desert Data Center, Lanzhou 730070, China）
Abstract： In order to make full use of texture information and neighborhood information provided by remote sensing images to improve the accuracy of change detection, a change detection method of remote sensing images is proposed based on principal component analysis (PCA) information entropy fusion of texture and neighborhood features from the perspective of feature fusion. Firstly, texture features of remote sensing images are extracted by gray-level co-occurrence matrix (GLCM), and neighborhood features are extracted by logarithmic ratio of neighborhood. Then, the texture features and neighborhood features are fused by PCA method to obtain principal feature information. Secondly, the information entropy of each principal feature is calculated, and the entropy weight method is used to assign weight to each principal feature to obtain the fusion difference image. Finally, fuzzy c-means (FCM) clustering algorithm is used to divide the fusion difference image into two categories to obtain the change detection results. Experimental results show that the proposed method can make full use of texture features and neighborhood features, reduce the influence brought by speckle noises, and significantly improve the accuracy of change detection of remote sensing image.
Key words： principal component analysis information entropy; remote sensing images; gray-level co-occurrence matrix (GLCM); texture feature; neighborhood feature
References
［1］SAXENA R, WATSON L T, WYNNE R H, et al. Towards a polyalgorithm for land use change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 144: 217-234.
［2］GONG M G, SU L Z, Li H, et al. A survey on change detection in synthnetic aperture radar imagery. Journal of Computer Research and Development, 2016, 53(1): 123-137.
［3］TEWKESBURY A P, COMBER A J, TATE N J, et al. A critical synthesis of remotely sensed optical image change detection techniques. Remote Sensing of Environment, 2015, 160: 1-14.
［4］DIAN Y Y, FANG S H, YAO C H. Change detection for hing-resolution images using multilevel segment method. Journal of Remote Sensing, 2016, 20(1): 133-141.
［5］GUIRADO E, BLANCO-SACRISTAN J, RIGOL J P, et al. A multi-temporal object-based image analysis to detect long-lived shrub coverchanges in drylands. Remote Sensing, 2019, 11(22): 2649.
［6］SHENG Y, SONG C, WANG J, et al. Representative lake water extent mapping at continental scales using multi-temporal Landsat-8 imagery. Remote Sensing of Environment, 2016, 185: 129-141.
［7］SUI H G, LIU C X, HUANG L H, et al. Refecion and exploration of rapid remote sensing emergency response for typical natural disasters. Geomatios and lnformation Science of Wuhan Univerity, 2019, 44(7): 1008-1019.
［8］LI Z B, SHI W Z, MYINT S W, et al. Semi-automated landslide inventory mapping from bitemporal aerial photographs using change detection and level set method. Remote Sensing of Environment, 2016, 175: 215-230.
［9］SUBLIME J, KALINICHEVA E. Automatic post-disaster damage mapping using deep-learning techniques for change detection: case study of the tohoku tsunami. Remote Sensing, 2019, 11(9): 1123.
［10］ZELINSKI M E, HENDERSON J, SMITH M, et al. Use of landsat 5 for change detection at 1998 indian and pakistani nuclear test sites. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(8): 3453-3460.
［11］ZHANG L P, WU C. Advance and future development of change detection for multi-temporal remote sensing imagery. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1447-1459.
［12］TONG G F, LI Y, DING W L, et al. Review of remote sensing image change detection. Journal of Image and Graphics, 2015, 20(12): 1561-1571.
［13］LUIS M, LUIS M P, ERICK M, et al. Novel unsupervised classification of collapsed buildings using satellite imagery, hazard scenarios and fragility functions. Remote Sensing, 2018, 10(2): 296.
［14］REN Q R, YANG W Z, WANG C J, et al. Review of remote sensing image change detection. Journal of Computer Applications, 2021, 41(8): 2294-2305.
［15］HUANG F H, YU Y, FENG T H. Hyperspectral remote sensing image change detection based on tensor and deep learning. Journal of Visual Communication and Image Representation, 2019, 58: 233-244.
［16］WANG Y H, GAO L R, CHEN Z C, et al. Deep learning and superpixel-based method for high-resolution remote sensing image change detection. Journal of Image and Graphics, 2020, 25(6): 1271-1282.
［17］WANG M C, ZHU C Y, CHEN X Y, et.al. Building change detectionin high resolution remote sensing images based on FPN Res-Unet. Journal of Jilin University (Earth Science Edition), 2021, 51(1): 296-306.
［18］SUI H G, FENG W Q, LI W Z, et al. Review of change detection methods for multi-temporal remote sensing lmagery. Geomatios and lnformation Science of Wuhan Univerity, 2018, 43(12): 1885-1898.
［19］YANG M J, JIAO L C, LIU F, et al. Transferred deep learning-based change detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9): 6960-6973.
［20］CELIK T. Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geoscience and Remote Sensing Letters, 2009, 6(4): 772-776.
［21］GONG M, CAO Y, WU Q. A neighborhood-based ratio approach for change detection in sar images. IEEE Geoscience and Remote Sensing Letters, 2012, 9(2): 307-311.
［22］LI H C, CELIK T, LONGBOTHAM N, et al. Gabor feature based unsupervised change detection of multitemporal SAR images based on two-level clustering. IEEE Geoscience and Remote Sensing Letters, 2015, 12(12): 2458-2462.
［23］JIA L, LI M, ZHANG P, et al. SAR Image change detection based on multiple kernel k-means clustering with local-neighborhood information. IEEE Geoscience and Remote Sensing Letters, 2017, 3(6): 856-860.
［24］ZHUANG H H, DENG K Z, FAN H D. SAR images unsupervised change detection based on combination of texture feature vector with maximum entropy principle. Acta Geodaetica et Cartographica Sinica, 2016, 45(3): 339-346.
［25］LI Q, GONG L X, ZHANG J F. A correlation change detection method integrating PCA and multi-texture features of SAR image for building damage detection. European Journal of Remote Sensing, 2019, 52(1): 435-447.
［26］ZHANG X L, CHEN X W, LI F, et al. Change detection method for high resolution remote sensing images using deep learning. Acta Geodaetica et Cartographica Sinica, 2017, 46(8): 999-1008.
［27］HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification. Studies in Media and Communication, 1973, SMC-3(6): 610-621.
［28］BO H, MA F L, JIAO L C. Reaearch on computation of GLCM of image texture. Acta Electronica Sinica, 2006, 34(1): 155-158.
［29］SHI L, SUN W D, YANG J, et al. Building collapse assessment by the use of postearthquake Chinese VHR airborne SAR. IEEE Geoscience and Remote Sensing Letters, 2015, 12(10): 2021-2025.
［30］SUN W D, SHI L, YANG J, et al. Building collapse assessment in urban areas using texture information from postevent SAR data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(8): 3792-3808.
［31］LIU B Q, ZHAO Z,WEI J J. A method of sar image change detection based on relative entropy within neighborhood. Remote Sensing Information, 2018, 33(3): 91-97.
［32］CUI B, ZHANG Y H, YAN L, et al. Dual-thresholds change detection in GF-3 sar images. Journal of Remote Sensing, 2020, 24(1): 1-10.
［33］HUANG X Y, LI L, XIN Y H. WPCA-LDA: new method of data classification. Application Research of Computers, 2017, 34(6): 1650-1653.
［34］PENG D, BRUZZONE L, ZHANG Y, et al. SemiCDNet: a semisupervised convolutional neural network for change detection in high resolution remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7): 5891-5906.
［35］HALL D L, LLINAS J. An introduction to multisensor data fusion. Proceedings of the IEEE, 1997, 85(10): 6-23.
［36］JIA Y H. Fusion of landsat TM and SAR image based on principal component analysis. Remote Sensing Technology and Application, 1998, 13(1): 4649-4654.
基于PCA信息熵特征融合的遥感影像变化检测
火久元1,2,3， 刘梦1
（1. 兰州交通大学 电子与信息工程学院， 甘肃 兰州 730070； 2. 兰州瑞智元信息技术有限责任公司， 甘肃 兰州 730070；3. 国家冰川冻土沙漠科学数据中心， 甘肃 兰州 730070）
摘要：为提高遥感影像变化检测的准确率， 本研究结合遥感影像中丰富的纹理信息与邻域信息， 引入信息论中信息熵的概念， 从特征融合的角度提出了一种基于主成分分析（PCA）信息熵融合纹理特征与邻域特征的遥感影像变化检测方法。 首先， 通过灰度共生矩阵提取遥感影像的纹理特征， 邻域对数比算子提取遥感影像的邻域特征， 然后， 利用PCA将纹理特征与邻域特征进行特征融合获得主特征信息。 其次， 计算每个主特征的信息熵， 以熵权法为各个主特征分别赋予权重， 获得融合后的差异图。 最后， 利用模糊C均值（FCM）聚类将融合差异图划分为两类， 得到变化检测结果。 实验结果表明， 该方法能够充分利用纹理特征与邻域特征， 减小斑点噪声带来的影响， 显著提高遥感影像变化检测的精度。
关键词：PCA信息熵； 遥感影像（GLCM）； 灰度共生矩阵； 纹理特征； 邻域特征
HUO Jiuyuan， LIU Meng． Remote sensing images change detection based on PCA information entropy feature fusion． Journal of Measurement Science and Instrumentation， 2023， 14（4）： 398-412. DOI： 10．3969／j．issn．1674-8042．2023．04．003
[full text view]
