SAR影像变化检测的前景特征流形排序法

doi:10.11947/j.AGCS.2022.20200512

摘要/Abstract

摘要： SAR影像变化检测的差异图分析法存在的两个问题:①连通区域内的部分变化区域易被误判为未变化区域;②中心先验假设并不适用于检测位于SAR影像边界的变化区域。本文针对以上两个问题设计了一种超像素分割和前景特征流行排序(manifold ranking,MR)的SAR影像变化检测方法(MRSFCD)。首先,通过单像素和邻域对数比算子进行加权融合构造差异图,可以保持变化区域内部的一致性并抑制噪声干扰。其次,对差异图进行超像素分割。然后,改进超像素的无向图连接方式,不对边界四周的超像素进行连接,利用超像素分割结果和灰度信息进行三次邻接。最后,将基于前景特征流行排序后得到的显著性图与单像素对数差异图进行点乘,对其进行阈值分割得到最终的二值变化图。本文通过采用3组双时相影像进行试验。结果表明,相较于其他变化检测算法,本文方法有效地提高了变化检测的精度。

关键词: SAR影像, 变化检测, 差异图, 超像素, 流行排序

Abstract: There are two problems with the difference image analysis for the current SAR image change detection methods. Some of the changed areas in the connected area are easily misclassified as unchanged areas, and the central prior assumption cannot be well applied to detecting the changed regions located at the boundary of the SAR image. In order to avoid the above limitations, a method of manifold ranking based on superpixel segmentation and foreground features for change detection (MRSFCD) was designed. Firstly, the difference image was constructed by weighted fusion of single pixel and neighborhood logarithmic ratio operator, which can maintain consistency within the change areas and suppress noise interference. The difference image was then segmented by the superpixel model. After that, the improved undirected graph connection method of superpixels was proposed. The main idea is that superpixels on the boundary are not considered when connecting, and superpixel segmentation results and grayscale information are applied for three adjacencies. Finally, we do a dot product between the significance image by manifold ranking based on foreground features and the single-pixel logarithmic difference image, and the final binary change image is obtained by threshold segmentation. In this paper, three datasets of dual-phase images are tested. The results indicate that compared with other change detection algorithms, the proposed method can improve the accuracy of change detection effectively.

Key words: SAR image, change detection, foreground feature, superpixel, manifold ranking

中图分类号:

P237

罗卿莉, 崔峰志, 魏钜杰, 明磊. SAR影像变化检测的前景特征流形排序法[J]. 测绘学报, 2022, 51(11): 2365-2378.

LUO Qingli, CUI Fengzhi, WEI Jujie, MING Lei. Foreground feature manifold ranking method for SAR image change detection[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(11): 2365-2378.

参考文献

[1] XU Kunpeng, ZHAO Lei, LI Kun, et al.Estimation of crop biomass using GF-3 polarization SAR data based on genetic algorithm feature selection[J]. The Journal of Geodesy and Geoinformation Science,2020, 3 (4): 126-136.
[2] RIDD M K, LIU Jiajun. A comparison of four algorithms for change detection in an urban environment[J]. Remote Sensing of Environment, 1998, 63(2): 95-100.
[3] YAMAGUCHI Y, UMEMURA M, KANAI D, et al. ALOS-2 polarimetric SAR observation of Hokkaido-Iburi-Tobu earthquake 2018[J]. IEICE Communications Express, 2019, 8(2): 26-31.
[4] 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 Maoguo, SU Linzhi, LI Hao, et al. A survey on change detection in synthetic aperture radar imagery[J]. Journal of Computer Research and Development, 2016, 53(1): 123-137.
[5] 陈晋, 何春阳, 史培军, 等. 基于变化向量分析的土地利用/覆盖变化动态监测(Ⅰ): 变化阈值的确定方法[J]. 遥感学报, 2001, 5(4): 259-266, 323. CHEN Jin, HE Chunyang, SHI Peijun, et al. Land use/cover change detection with change vector analysis (CVA): change magnitude threshold determination[J]. Journal of Remote Sensing, 2001, 5(4): 259-266, 323.
[6] BAZI Y, BRUZZONE L, MELGANI F. An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4): 874-887.
[7] GONG Maoguo, CAO Yu, WU Qiaodi. A neighborhood-based ratio approach for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(2): 307-311.
[8] ZHENG Yaoguo, ZHANG Xiangrong, HOU Biao, et al. Using combined difference image and k-means clustering for SAR image change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(3): 691-69.
[9] MA Jingjing, GONG Maoguo, ZHOU Zhiqiang. Wavelet fusion on ratio images for change detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(6): 1122-1126.
[10] 徐德伟, 茹卉, 宋辉, 等. 基于直接密度比估计的SAR图像变化检测[J]. 现代雷达, 2015, 37(2): 28-32. XU Dewei, RU Hui, SONG Hui, et al. SAR image change detection based on direct density-ratio estimation[J]. Modern Radar, 2015, 37(2): 28-32.
[11] BARRETO T L M, ROSA R A S, WIMMER C, et al. Classification of detected changes from multitemporal high-res Xband SAR images: intensity and texture descriptors from superpixels[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(12): 5436-5448.
[12] GONG Maoguo, LI Yu, JIAO Licheng, et al. SAR change detection based on intensity and texture changes[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93: 123-135.
[13] CUI Bin, ZHANG Yonghong, YAN Li, et al. A SAR change detection method based on the consistency of single-pixel difference and neighbourhood difference[J]. Remote Sensing Letters, 2019, 10(5): 488-495.
[14] KITTLER J, ILLINGWORTH J. Minimum error thresholding[J]. Pattern Recognition, 1986, 19(1): 41-47.
[15] DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society Series B (Methodological), 1977, 39(1): 1-38.
[16] CELIK T, MA Kaikuang. Unsupervised change detection for satellite images using dual-tree complex wavelet transform[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(3): 1199-1210.
[17] GAGULA-PALALIC S, CAN M. Fuzzy C-means model and algorithm for data clustering[J].International Journal of Soft Computing,2012, 1(1): 115-119.
[18] HU Hongtao, BAN Yifang. Unsupervised change detection in multitemporal SAR images over large urban areas[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(8): 3248-3261.
[19] SU Linzhi, GONG Maoguo, SUN Bo, et al. Unsupervised change detection in SAR images based on locally fitting model and semi-EM algorithm[J]. International Journal of Remote Sensing, 2014, 35(2): 621-650.
[20] GONG Maoguo, SU Linzhi, JIA Meng, 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.
[21] 李亮, 龚龑, 李雪, 等. 像斑直方图相似性测度的高分辨率遥感影像变化检测[J]. 遥感学报, 2014, 18(1): 139-153. LI Liang, GONG Yan, LI Xue, et al. Change detection based on similarity measurement of object histogram using high-resolution remote sensing imagery[J]. Journal of Remote Sensing, 2014, 18(1): 139-153.
[22] WANG Guiting, ZHANG Fengyu, JIAO Licheng. Change detection in SAR image based on multiscale product and PCA[C]//Proceedings of 2009 Asian-Pacific Conference on Synthetic Aperture Radar. Xi’an, China: IEEE,2009: 872-875.
[23] LI Wei, CHEN Jiayu, YANG Pei, et al. Multitemporal SAR images change detection based on joint sparse representation of pair dictionaries[C]//Proceedings of 2012 IEEE International Geoscience and Remote Sensing Symposium. Munich, Germany: IEEE,2012: 6165-6168.
[24] ZHOU D, WESTON J, GRETTON A, et al. Ranking on data manifolds[C]//Proceedings of the 16th International Conference on Neural Information Processing Systems. Whistler, British Columbia, Canada; MIT Press,2003: 169-76.
[25] ZHOU Dengyong, BOUSQUET O, LAL T N, et al. Learning with local and global consistency[C]//Proceedings of the 16th International Conference on Neural Information Processing Systems. New York, USA: ACM press, 2003: 321-328.
[26] YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA: IEEE, 2013: 3166-3173.
[27] 王林. 基于超像素和显著性检测的SAR图像变化检测研究[D].西安:西安电子科技大学,2018. WANG Lin. SAR image change detection based on super-pixel and saliency detection[D]. Xi’an:Xidian University, 2018.
[28] 王延召, 彭国华, 延伟东. 基于流形排序和联合连通性先验的显著性目标检测[J]. 模式识别与人工智能, 2019, 32(1): 82-93. WANG Yanzhao, PENG Guohua, YAN Weidong. Salient object detection based on manifold ranking and co-connectivity[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(1): 82-93.
[29] WANG Zhongli, TIAN Guohui. Integrating manifold ranking with boundary expansion and corners clustering for saliency detection of home scene[J]. Neurocomputing, 2020, 379: 182-196.
[30] LÜ Ning, CHEN Chen, QIU Tie, et al. Deep learning and superpixel feature extraction based on contractive autoencoder for change detection in SAR images[J]. IEEE Transactions on Industrial Informatics, 2018, 14(12): 5530-5538.
[31] ZHANG Yue, SUN Xian, SUN Hao, et al. High resolution SAR image classification with deeper convolutional neural network[C]//Proceedings of 2018 IGARSS-IEEE International Geoscience and Remote Sensing Symposium. Valencia, Spain:IEEE,2018: 2374-2377.
[32] 王钟书, 公茂果, 张明阳, 等. 基于复数深度网络的SAR图像变化检测[C]//第五届高分辨率对地观测学术年会. 西安:中国科学院空天信息创新研究院, 2018: 610-622. WANG Zhongshu, GONG Maoguo, ZHANG Mingyang, et al. SAR image change detection based on complex depth network[C]//Proceedings of the 5th China High Resolution Earth Observation Conference. Xi’an, China: Aerospace Information Innovation Research Institute, Chinese Academy of Sciences,2018: 610-622.
[33] SEYDI S T, HASANLOU M, AMANI M. A new end-to-end multi-dimensional CNN framework for land cover/land use change detection in multi-source remote sensing datasets[J]. Remote Sensing, 2020, 12(12): 2010.
[34] DONG Huihui, MA Wenping, WU Yue, et al. Self-supervised representation learning for remote sensing image change detection based on temporal prediction[J]. Remote Sensing, 2020, 12(11): 1868.
[35] WANG Rongfang, DING Fan, CHEN Jiawei, et al. A lightweight convolutional neural network for bitemporal image change detection[C]//Proceedings of 2020 IGARSS IEEE International Geoscience and Remote Sensing Symposium.Waikoloa, HI,USA:IEEE,2020:2551-2554.
[36] CHEN Jiawei, WANG Rongfang, DING Fan, et al. A convolutional neural network with parallel multi-scale spatial pooling to detect temporal changes in SAR images[J]. Remote Sensing,2020, 12 (10): 1619.
[37] 徐真, 王宇, 李宁, 等. 一种基于CNN的SAR图像变化检测方法[J]. 雷达学报, 2017, 6(5): 483-491. XU Zhen, WANG Yu, LI Ning, et al. A novel approach to change detection in SAR images with CNN classification[J]. Journal of Radars, 2017, 6(5): 483-491.
[38] SHI Wenzhong, ZHANG Min, ZHANG Rui, et al. Change detection based on artificial intelligence: state-of-the-art and challenges[J]. Remote Sensing, 2020, 12(10): 1688.
[39] 黄海燕, 王瑛. 一种改进的SAR图像LEE滤波算法[J]. 遥感信息, 2010, 25(5): 26-29. HUANG Haiyan, WANG Ying. An improved LEE algorithm of SAR image filtering[J]. Remote Sensing Information, 2010, 25(5): 26-29.
[40] OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[41] ZHENG Yaoguo, ZHANG Xiangrong, HOU Biao, et al. Using combined difference image and k-means clustering for SAR image change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(3): 691-695.