سابِق|تال

Unsupervised super pixel level change detection based on canonical correlation analysis

  • role： First author第一作者
  • Affiliation：

    College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China

  • Email：z17806244661@163.com
  • Introduction：赵元昊，研究方向为城市遥感应用。E-mail： z17806244661@163.com
ZHAO Yuanhao,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China

  • Email：genyunsun@163.com
  • Introduction：孙根云，研究方向为遥感图像处理，智能计算。E-mail： genyunsun@163.com
SUN Genyun*,  
  • Affiliation：

    College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China

ZHANG Aizhu,  
  • Affiliation：

    College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China

JIAO Zhijun,  
  • Affiliation：

    College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China

SUN Chao

ملخص

Change detection, a critical task in remote sensing and geospatial analysis, involves the identification of areas where alterations in land cover types have occurred over time using multi-temporal images. The accurate detection of such changes is essential for various applications, including environmental monitoring, urban development assessment, and natural disaster management. However, existing change detection methods are often susceptible to noise and the influence of specific land features, resulting in significant speckle phenomena and reduced detection accuracy. These limitations hinder the reliable identification of change patterns in land cover, impacting the effectiveness of downstream analyses and decision-making processes.To address these challenges, this paper proposes an unsupervised superpixel-level change detection method that combines canonical correlation analysis and histogram matching. This method aims to improve the accuracy and reliability of change detection by addressing the limitations associated with traditional approaches. The proposed method consists of several steps. First, the remote sensing images were preprocessed and superpixel-segmented. This step is aimed at improving the quality of the image and dividing it into homogeneous regions called superpixels. Superpixel segmentation helps to preserve spatial information and reduces the influence of noise on subsequent analysis. Next, the weight of each superpixel was calculated based on the superpixel scale and the unchanged probability. Superpixel weights are used to highlight the importance of different regions in the change detection process. After obtaining the weights, the method proceeds to extract change features at the superpixel level using multivariate change detection and histogram matching. Multivariate change detection involves analyzing the spectral information of the superpixels to identify changes in land cover types. Histogram matching, on the other hand, aims to align the histograms of the superpixels from different time periods, enabling more accurate comparison and detection of changes. Finally, a change detection result map was developed based on the weighted image, classical methods, and change features.Three hyperspectral test datasets and one multispectral test dataset were used for experimental verification.Experimental validation of the proposed method was conducted on three hyperspectral test datasets and one multispectral test dataset. The results demonstrate the superior performance of the proposed method, with the Overall Accuracy (OA) and Kappa index surpassing those of existing methods across all four test datasets. Specifically, the OA values consistently exceed 90% on all datasets, indicating the high accuracy and robustness of the proposed method. Moreover, comparative analysis reveals significant improvements in the OA when compared to other existing methods. The proposed method achieves an OA increase of 4.41%, 3.44%, 1.74%, and 0.19% on the four datasets, highlighting its efficacy in enhancing change detection accuracy and reliability. In conclusion, the proposed unsupervised superpixel-level change detection method, which integrates canonical correlation analysis and histogram matching, demonstrates remarkable performance in detecting changes in land cover types from multi-temporal remote sensing images.

مفهوم

remote sensing;super pixel;change detection;canonical correlation analysis;histogram specification

References

  1. 1.
    Bovolo F. 2009. A multilevel parcel-based approach to change detection in very high resolution multitemporal images. IEEE Geoscience and Remote Sensing Letters, 6(1): 33-37 [DOI: ＲS.2008.2007429]
  2. 2.
    Bruzzone L and Carlin L. 2006. A multilevel context-based system for classification of very high spatial resolution images. IEEE Transactions on Geoscience and Remote Sensing, 44(9): 2587-2600
  3. 3.
    Bruzzone L and Prieto D F. 2000. Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote Sensing, 38(3): 1171-1182
  4. 4.
    Cai F S, Xiang Z J, Cai H and Shan D M. 2020. CVA multi-scale remote sensing image change detection combined with feature selection. Bulletin of Surveying and Mapping, 8: 101-104, 130
  5. 5.
    Canty M J, Nielsen A A and Schmidt M. 2004. Automatic radiometric normalization of multitemporal satellite imagery. Remote Sensing of Environment, 91(3/4): 441-451
  6. 6.
    Carvalho Júnior O A, Guimarães R F, Gillespie A R, Silva N C and Gomes R A T. 2011. A new approach to change vector analysis using distance and similarity measures. Remote Sensing, 3(11): 2473-2493
  7. 7.
    Du B, Ru L X, Wu C and Zhang L P. 2019. Unsupervised deep slow feature analysis for change detection in multi-temporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 57(12): 9976-9992
  8. 8.
    Han Y, Javed A, Jung S and Liu S C. 2020. Object-based change detection of very high resolution images by fusing pixel-based change detection results using weighted Dempster–Shafer theory. Remote Sensing, 12(6): 983
  9. 9.
    Hu H T and Ban Y F. 2014. Unsupervised change detection in multitemporal SAR images over large urban areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(8): 3248-3261
  10. 10.
    Li H, Ma J J, Gong M G, Jiang Q Z and Jiao L C. 2015. Change detection in synthetic aperture radar images based on evolutionary multiobjective optimization with ensemble learning. Memetic Computing, 7(4): 275-289
  11. 11.
    Li L, Wang L, Sun X P and Ying G W. 2017. Remote sensing change detection method based on object-oriented change vector analysis. Remote Sensing Information, 32(6): 71-77
  12. 12.
    Liao M S, Zhu P and Gong J Y. 2000. Multivariate change detection based on canonical transformation. Journal of Remote Sensing (in Chinese), 4(3): 197-201
  13. 13.
    Liu B Q, Zhao Z, Sheng Y T and Zhang Z F. 2018. High Resolution SAR image change detection based on texture fusion and generalized Gaussian model. Engineering of Surveying and Mapping, 27(6): 19-25
  14. 14.
    Liu J H. 2015. Improved Mixed Double Domain Image Denoising and SAR Image Change Detection Based on Difference Image Combing and Edge Classification. Xi’an: Xidian University: 37-50
  15. 15.
    Lu D, Mausel P, Brondízio E and Moran E. 2004. Change detection techniques. International Journal of Remote Sensing, 25(12): 2365-2401
  16. 16.
    Lu M, Mei Y, Zhao Y and Leng L. 2015. Change detection based on multi-scale geometric feature vector. Geomatics and Information Science of Wuhan University, 40(5): 623-627
  17. 17.
    Marchesi S, Bovolo F and Bruzzone L. 2010. A context-sensitive technique robust to registration noise for change detection in VHR multispectral images. IEEE Transactions on Image Processing, 19(7): 1877-1889
  18. 18.
    Marpu P, Gamba P and Benediktsson J A. 2011a. Hyperspectral change detection using IR-MAD and feature reduction. Proceedings of 2011 IEEE International Geoscience and Remote Sensing Symposium. Vancouver: IEEE: 98-101
  19. 19.
    Marpu P R, Gamba P and Canty M J. 2011b. Improving change detection results of IR-MAD by eliminating strong changes. IEEE Geoscience and Remote Sensing Letters, 8(4): 799-803
  20. 20.
    Nielsen A A. 2007. The regularized iteratively reweighted MAD method for change detection in multi- and hyperspectral data. IEEE Transactions on Image Processing, 16(2): 463-478
  21. 21.
    Nielsen A A and Vestergaard J S. 2013. A kernel version of multivariate alteration detection. IEEE International Geoscience and Remote Sensing Symposium, 3451-3454
  22. 22.
    Ouyang S N. 2019. Cross detection method of high resolution remote sensing images based on IR-MAD. Beijing Surveying and Mapping, 33(9): 1029-1033
  23. 23.
    Sun X X, Zhang J X, Yan Q and Gao J X. 2011. A Summary on current techniques and prospects of remote sensing change detection. Remote Sensing Information, (1): 119-123
  24. 24.
    Wang B, Choi S K, Han Y K, Lee S K and Choi J W. 2015. Application of IR-MAD using synthetically fused images for change detection in hyperspectral data. Remote Sensing Letters, 6(8): 578-586
  25. 25.
    Wang Q, Li Q and Li X L. 2021. A fast neighborhood grouping method for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 59(6): 5028-5039
  26. 26.
    Wang X L, Yang J P, Jiang T, Gang H L and Sun Y C. 2020. Change detection from remote sensing images based on IR-MAD algorithm. Geomatics World, 27(3): 56-62
  27. 27.
    Wu C, Du B and Zhang L P. 2014. Slow feature analysis for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2858-2874
  28. 28.
    Xu Y D, Yu L, Zhao F R, Cai X L, Zhao J Y, Lu H and Gong P. 2018. Tracking annual cropland changes from 1984 to 2016 using time-series Landsat images with a change-detection and post-classification approach: experiments from three sites in Africa. Remote Sensing of Environment, 218: 13-31
  29. 29.
    Zeng Z F. 2013. Change Detection Research for Remote Sensing Image Land Use Based on the Change Vector Analysis Method. Chongqing: Chongqing Jiaotong University: 10-12
  30. 30.
    Zhang M Z, Zhang H, Wang C, Liu M and Xie L. 2016. Combining super-pixel segmentation and multiple difference maps for SAR change detection. Remote Sensing Technology and Application, 31(3): 481-487
  31. 31.
    Zhao M and Zhao Y D. 2018. Object-oriented and multi-feature hierarchical change detection based on CVA for high-resolution remote sensing imagery. Journal of Remote Sensing, 22(1): 119-131
  32. 32.
    Zhao Z M, Meng Y, Yuan A Z, Huang Q Q, Kong Y L, Yuan Y, Liu X Y, Lin L and Zhang M M. 2016. Review of remotely sensed time series data for change detection. Journal of Remote Sensing (in Chinese), 20(5): 1110-1125
  33. 33.
    Zhuang H F. 2018. Research on Several Methods in Change Detection of Multispectral/SAR Images. Xuzhou: China University of Mining and Technology: 13-28

قراءة النص الكامل

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website