Change detection of remote sensing images based on the fusion of co-saliency difference images
-
摘要: 针对高空间分辨率遥感影像地物复杂、传统变化检测方法漏检率高的问题,提出了一种联合显著性和多方法差异影像融合的多时相遥感影像变化检测方法。选取3组双时相高空间分辨率遥感影像作为实验数据,首先分别采用变化矢量分析(change vector analysis,CVA)和光谱斜率差异(spectral gradient difference,SGD)两种方法对两个时相遥感影像进行对应的差异影像构造; 然后通过基于聚类的联合显著性方法分别获取两幅差异影像的联合显著性图; 最后,将两幅联合显著性图进行融合得到联合显著性差异图,并采用大津法(OTSU)对联合显著性差异图进行阈值分割和闭运算得到最终变化图。实验表明,该方法的总体精度(overall accuracy,OA)、Kappa系数和F-measure精度优于传统方法,可靠性强,具有很高的准确性。Abstract: Owing to the complex surface features in the high spatial resolution (HR) remote sensing images, traditional change detection methods suffer the shortcoming of a high omission rate. Given this, this paper proposed a change detection method based on multi-temporal remote sensing images based on the fusion of co-saliency difference images. In this study, three groups of dual-temporal HR remote sensing images were selected to carry out the experiment according to the following steps. First, develop difference images based on the dual-temporal HR remote sensing images using the methods of change vector analysis (CVA) and spectral gradient difference (SGD). Then obtain a co-saliency map of two difference images using the cluster-based co-saliency detection. Finally, obtain the co-saliency difference map by fusing two co-saliency maps, and then conduct threshold segmentation and closing operation of the co-saliency difference map using the OTSU method. In this way, the final change map was obtained. As indicated by the experiment results, this method is superior to traditional methods in terms of overall accuracy (OA), Kappa coefficient, and F-measure accuracy and thus is highly reliable and accurate.
-
-
[1] 黄亮, 左小清, 於雪琴. 遥感影像变化检测方法探讨[J]. 测绘科学, 2013, 38(4):203-206.
[2] Huang L, Zuo X Q, Yu X Q. Review on change detection methods of remote sensing images[J]. Science of Surveyingand Mapping, 2013, 38(4):203-206.
[3] Radke R J, Andra S, Al K O, et al. Image change detection algorithms:A systematic survey[J]. IEEE Transactions on Image Processing, 2005, 14(3):294-307.
[4] 眭海刚, 冯文卿, 李文卓, 等. 多时相遥感影像变化检测方法综述[J]. 武汉大学学报(信息科学版), 2018, 43(12):1885-1898.
[5] Sui H G, Feng W Q, Li W Z, et al. Review of change detection methods for multi-temporal remote sensing imagery[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12):1885-1898.
[6] 张良培, 武辰. 多时相遥感影像变化检测的现状与展望[J]. 测绘学报, 2017, 46(10):1447-1459.
[7] Zhang L P, Wu C. Advance and future development of change detection for multi-temporal remote sensing imagery[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1447-1459.
[8] 黄亮, 於雪琴, 姚丙秀, 等. 线性迭代聚类和主成分分析的遥感影像变化检测[J]. 测绘科学, 2019, 44(11):189-194.
[9] Huang L, Yu X Q, Yao B X, et al. Change detection for remote sensing images based on SLIC and PCA[J]. Science of Surveying and Mapping, 2019, 44(11):189-194.
[10] Huang L, Fang Y M, Zuo X Q, et al. Automatic change detection method of multitemporal remote sensing images based on 2D-OTSU algorithm improved by firefly algorithm[J]. Journal of Sensors, 2015(3):327123.
[11] Wu Z, Hu Z, Fan Q. Superpixel-based unsupervised change detection using multi-dimensional change vector analysis and SVM-based classification[J]. ISPRS Annals of the Photogrammetry, 2012, I-7(1):257-262.
[12] 赵敏, 赵银娣. 面向对象的多特征分级CVA遥感影像变化检测[J]. 遥感学报, 2018, 22(1):119-131.
[13] Zhao M, Zhao Y D. Object-oriented and multi-feature hierarchical change detection based on CVA for high-resolution remote sensing imagery[J]. Journal of Remote Sensing, 2018, 22(1):119-131.
[14] 冯文卿, 张永军. 利用多尺度融合进行面向对象的遥感影像变化检测[J]. 测绘学报, 2015, 44(10):1142-1151.
[15] Feng W Q, Zhang Y J. Object-oriented change detection for remote sensing images based on multiscale fusion[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(10):1142-1151.
[16] Chen J, Lu M, Chen X, et al. A spectral gradient difference based approach for land cover change detection[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2013(85):1-12.
[17] 肖明虹, 冯文卿, 眭海刚. 超像素分割和多方法融合的遥感影像变化检测方法[J]. 测绘通报, 2018(10):93-97,121.
[18] Xiao M H, Feng W Q, Sui H G. Remote sensing image change detection algorithm based on super-pixel segmentation and multiple difference maps[J]. Bulletin of Surveying and Mapping, 2018(10):93-97,121.
[19] He S F, Rynson W H L, Liu W X, et al. SuperCNN:A superpixelwise convolutional neural network for salient object detection[J]. International Journal of Computer Vision, 2015, 115(3):330-344.
[20] Fu H Z, Cao X C, Tu Z W. Cluster-based co-saliency detection[J]. IEEE Transactions on Image Processing, 2013, 22(10):3766-3778.
[21] Huang L, Peng Q Z, Yu X Q. Change detection in multitemporal high spatial resolution remote-sensing images based on saliency detection and spatial intuitionistic fuzzy C-means clustering[J]. Journal of Spectroscopy, 2020:1-9.
[22] Zhao J, Liu J J, Fan D P, et al. EGNet:Edge guidance network for salient object detection[C]// CVF International Conference on Computer Vision (ICCV).IEEE, 2020:8778-8787.
[23] 刘媛媛, 孙嘉慧, 王跃勇, 等. Otsu和形态学相结合的人参叶斑图像分割系统[J/OL]. 长春:吉林农业大学学报(2020-07-23)[2020-09-24]. https://doi.org/10.13327/j.jjlau.2020.5794.
[24] Liu Y Y, Sun J H, Wang Y Y, et al. Ginseng leaf spot image segmentation system based on Otsu and morphology algorithm[J/OL]. Changchun:Journal of Jilin Agricultural University(2020-07-23)[2020-09-24]. https://doi.org/10.13327/j.jjlau.2020.5794.
[25] Liu D, Yu J. Otsu method and K-means[C]// Ninth International Conference on Hybrid Intelligent Systems.IEEE Computer Society, 2009:344-349.
[26] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to change detection in multitemporal SAR images[J]. IEEE Transactions on Geoscience & Remote Sensing, 2005, 43(12):2963-2972.
[27] Gong M, Zhang P, Su L, et al. Coupled dictionary learning for change detection from multisource data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12):7077-7091.
[28] Wu C, Du B, Cui X, et al. A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion[J]. Remote Sensing of Environment, 2017, 199:241-255.
[29] Duan Y P, Liu F, Jiao L C, et al. SAR Image segmentation based on convolutional-wavelet neural network and markov random field[J]. Pattern Recognition, 2017, 64:255-267.
[30] 刘瑞, 贾振红, 覃锡忠, 等. 基于模糊局部信息C均值的SAR图像变化检测[J]. 激光杂志, 2015, 36(11):28-31.
[31] Liu R, Jia Z H, Qin X Z, et al. A new SAR image change detection based on FLICM algorithm[J]. Laser Journal, 2015, 36(11):28-31.
[32] Celik T. Unsupervised change detection in satellite images using principal component analysis and K-means clustering[J]. IEEE Geoscience & Remote Sensing Letters, 2009, 6(4):772-776.
-
计量
- 文章访问数: 559
- PDF下载数: 131
- 施引文献: 0
下载: