輻射同態化與變遷分析是遙感探測中重要的多時期資料處理與分析。它們一般仰賴從衛星影像中挑選變化物及擬恆定特徵物（PIF）。PIF為資料獲取過程中反射率不變或接近不變的地表物。相反地，變化物像素在不同日期獲取的兩個影像中有不同的反射率。先前研究可以成功地從雙時期影像中提取令人滿意的PIF成果。但是針對兩個時期以上的多時期影像，他們依然以成對的方式執行而沒有考慮到會造成PIF選擇不一致的問題。相同地，部分先前變遷偵測的研究中採用多變數轉化偵測法（MAD）的統計方法取得變化的像素。但這依然未解決當處理多時期光學衛星影像時造成的偵測不一致的問題。因此本研究介紹了新穎的多時間和多變數轉化偵測法（MMAD）方法緩解上述問題。該方法基於加權廣義典型相關性分析，同時解算多變數和多時期資料的典型係數，實現一致的變遷偵測與穩定的輻射同態化。此外，MMAD的新加權機制考量像素相似度、影像品質與時間一致性，減少針對大面積的地表變遷的敏感性，進而魯棒地分辨變遷與未變遷地區。本研究還提出了另一種基於差值影像的變遷偵測法，解決基於MAD的相關方法中變遷高估的問題。該方法中，各波段的輻射同態化差值影像被結合成卡方分佈的變遷機率圖，並透過本研究提出的自動最佳閥值選擇法分辨變遷與未變遷地區。實驗測試了SPOT-5和Landsat-8的多時期衛星影像。在SPOT-5衛星影像的輻射同態化實驗顯示，MMAD加權方式使PIF的品質（以R^2作指標）在4個波段分別提升25.69%，17.15%，4.03%和4.44%。此外，在同時考量多時期時間序列的情況下，輻射同態化結果能保持著一致性並且避免誤差傳播的問題。在Landsat-8的變遷偵測實驗中，與基於MAD的相關方法相比，MMAD最多將整體準確性，精度和kappa係數分別提高了2.03%，23.85%和17.91%。此外，基於差值影像的變化檢測方法顯示能夠克服MAD相關方法的高估問題。與基於MAD的相關方法相比，變遷偵測的總體準確性、精度和kappa係數最多分別提高了4.83%，101.35%和58.41%。

Radiometric normalization and change detection are important multitemporal data processing and analysis tasks in remote sensing. These tasks generally rely on the selection of change objects and pseudo-invariant features (PIFs) from satellite images. PIFs are ground objects whose reflectance are invariant or near invariant during data acquisition. By contrast, change objects are pixels with different reflectance in two images acquired from different dates. Previous studies have successfully extracted PIFs from bitemporal images with satisfactory results. However, they do not fully consider the problem of inconsistent PIFs selection caused by performing pairwise PIF selection for more than two images. Similarly, some studies on change detection have subtracted change pixels from bitemporal images by using a statistical approach called multivariate alteration detection (MAD). However, the inconsistency encountered when dealing with more than two optical satellite images has not been addressed. To address these problems, this study introduces a novel method called multitemporal and multivariate alteration detection (MMAD), which is based on weighted generalized canonical correlation analysis and solves the canonical coefficients for multivariable and multitemporal data, thereby ensuring a consistent change detection and stabilizing the radiometric normalization results. A new weighting scheme based on pixel similarity, image quality, and temporal coherence is also introduced to reduce the sensitivity of MMAD to large land-cover changes and to robustly distinguish changed areas from non-changed ones. Another difference-based change detection method is also proposed to address the over-estimation problem in related MAD-based methods. In this method, a chi-square-distributed change probability map is generated by combining different images with radiometric normalization results. Afterward, an optimal threshold determination method is proposed for change probability maps. SPOT-5 and Landsat-8 multitemporal images are tested in experiments, and the results of radiometric normalization show that the proposed weighting schemes in MMAD improve the quality of the selected PIFs in terms of R^2 by 25.69%, 17.15%, 4.03%, and 4.44% in band 1 to 4, respectively, of SPOT-5 images. The resulting normalized images are also consistent with the time sequence images by avoiding error propagation while considering temporal coherence. In the change detection experiments, MMAD achieves 2.03%, 23.85%, and 17.91% higher overall accuracy, precision, and kappa coefficient, respectively, compared with related MAD-based methods. Moreover, the proposed difference-based change detection method is also effectively addresses the over-estimation problem of MAD-related methods. Overall, the difference-based change detection method outperforms other MAD-based methods by 4.83%, 101.35%, and 58.41% the most in terms of overall accuracy, precision, and kappa coefficient, respectively.

Bai, Y., Tang, P., & Hu, C. (2018). kCCA Transformation-Based Radiometric Normalization of Multi-Temporal Satellite Images. Remote Sensing, 10, 432.
Bao, N., Lechner, A. M., Fletcher, A., Mellor, A., Mulligan, D., & Bai, Z. (2012). Comparison of relative radiometric normalization methods using pseudo-invariant features for change detection studies in rural and urban landscapes. Journal of Applied Remote Sensing, 6(1), 063578-1.
Bouziani, M., Goïta, K., & He, D.-C. (2010). Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 143-153.
Bovolo, F., Bruzzone, L., & Marconcini, M. (2008). A novel approach to unsupervised change detection based on a semisupervised svm and a similarity measure. IEEE Transactions on Geoscience and Remote Sensing, 46(7), 2070-2082.
Bruzzone, L., & 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.
Byrne, G. F., Crapper, P. F., & Mayo, K. K. (1980). Monitoring land-cover change by principal component analysis of multitemporal landsat data. Remote Sensing of Environment, 10, 175-184.
Byun, Y., & Han, D. (2018). Relative radiometric normalization of bitemporal very high-resolution satellite images for flood change detection. Journal of Applied Remote Sensing, 12(2), 1-19.
Canty, M. J., & Nielsen, A. A. (2008). Automatic radiometric normalization of multitemporal satellite imagery with the iteratively re-weighted MAD transformation. Remote Sensing of Environment, 112(3), 1025-1036.
Canty, M. J., Nielsen, A. A., & Schmidt, M. (2004). Automatic radiometric normalization of multitemporal satellite imagery. Remote Sensing of Environment, 91(3), 441-451.
Chen, J., Gong, P., He, C., Pu, R., & Shi, P. (2003). Land-use/land- cover change detection using improved change-vector analysis. Photogrammetric Engineering and Remote Sensing, 69, 369-379.
Chen, Y., Sun, K., Li, D., Bai, T., & Li, W. (2018). Improved relative radiometric normalization method of remote sensing images for change detection. Journal of Applied Remote Sensing, 12(4), 1-16.
Collins, J. B., & Woodcock, C. E. (1994). Change detection using the gramm- schmidt transformation applied to mapping forest mortality. Remote Sensing of Environment, 50(3), 267-279.
Coppin, P. R., & Bauer, M. E. (1994). Processing of multitemporal landsat tm imagery to optimize extraction of forest cover change features. IEEE Transactions on Geoscience and Remote Sensing, 32(4), 918-927.
Coppin, P. R., & Bauer, M. E. (1996). Digital change detection in forest ecosystems with remote sensing imagery. Remote Sensing Reviews, 13, 207-234.
de Bem, P. P., de Carvalho Junior, O. A., Guimarães, R. F., & Gomes, R. A. T. (2020). Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks. Remote Sensing, 12(6), 901.
Descals, A., Szantoi, Z., Beck, P. S. A., Brink, A., & Strobl, P. (2017). Automated detection of selective logging using smallsat imagery. IEEE Geoscience and Remote Sensing Letters, 14(12), 2180-2184.
Desclée, B., Bogaert, P., & Defourny, P. (2006). Forest change detection by statistical object-based method. Remote Sensing of Environment, 102(1), 1-11.
Du, Y., Teillet, P. M., & Cihlar, J. (2002). Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection. Remote Sensing of Environment, 82(1), 123 - 134.
Fung, T., & LeDrew, E. (1988). The Determination of Optimal Threshold Levels for Change Detection Using Various Accuracy Indices. Photogrammetric Engineering and Remote Sensing, 54(10), 1449- 1454.
Ghanbari, H., Homayouni, S., Ghamisi, P., & Safari, A. (2018). Radiometric Normalization of Multitemporal and Multisensor Remote Sensing Images Based on a Gaussian Mixture Model and Error Ellipse. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(11), 4526-4533.
Habib, T., Inglada, J., Mercier, G., & Chanussot, J. (2009). Support vector reduction in svm algorithm for abrupt change detection in remote sensing. IEEE Geoscience and Remote Sensing Letters, 6(3), 606- 610.
Hall, F. G., Strebel, D. E., Nickeson, J. E., & Goetz, S. J. (1991). Radiometric rectification: Toward a common radiometric response among multidate, multisensor images. Remote Sensing of Environment, 35(1), 11-27.
Han, J., Kamber, M., & Pei, J. (2011). Data mining: Concepts and techniques, third edition (3rd ed.). Amsterdam.
Hou, B., Liu, Q., Wang, H., & Wang, Y. (2020). From W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques. IEEE Transactions on Geoscience and Remote Sensing, 58(3), 1790-1802.
Howarth, P. J., & Wickware, G. M. (1981). Procedures for change detection using Landsat digital data. International Journal of Remote Sensing, 2, 277-291.
Huang, C., Song, K., Kim, S., Townshend, J. R., Davis, P., Masek, J. G., & Goward, S. N. (2008). Use of a dark object concept and support vector machines to automate forest cover change analysis. Remote Sensing of Environment, 112(3), 970-985.
Hussain, M., Chen, D., Cheng, A., Wei, H., & Stanley, D. (2013). Change detection from remotely sensed images: From pixel-based to object- based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 80, 91-106.
Im, J., & Jensen, J. R. (2005). A change detection model based on neighborhood correlation image analysis and decision tree classification. Remote Sensing of Environment, 99(3), 326-340.
Kauth, R. J., & Thomas, G. S. (1976). The tasselled cap-A graphic description of the spectral-temporal development of agricultural crops as seen by Landsat. In Procs. symposium on machine processing of remotely sensed data (p. 41-51). Purdue University, West Lafayette, Indiana.
Li, D. (2010). Remotely sensed images and gis data fusion for automatic change detection. International Journal of Image and Data Fusion, 1(1), 99-108.
Lillesand, T. M., Kiefer, R. W., & Chipman, J. W. (2011). Remote Sensing and Image Interpretation, 6th Edition. Wiley India Pvt. Limited.
Lin, B. Y., Wang, Z. J., Syariz, M. A., Denaro, L. G., & Lin, C. H. (2019). Pseudoinvariant Feature Selection Using Multitemporal MAD for Optical Satellite Images. IEEE Geoscience and Remote Sensing Letters, 16(9), 1353-1357.
Lippitt, C., Rogan, J., Li, Z., Eastman, R., & Jones, T. (2008, 10). Mapping selective logging in mixed deciduous forest: A comparison of machine learning algorithms. Photogrammetric Engineering and Remote Sensing, 74, 1201-1211.
Lu, D., Mausel, P., Brondízio, E., & Moran, E. (2004). Change detection techniques. International Journal of Remote Sensing, 25(12), 2365- 2401.
Ludeke, A. K., Maggio, R. C., & Reid, L. M. (1990). An analysis of anthropogenic deforestation using logistic regression and GIS. Journal of Environmental Management, 31, 247–259.
Lunetta, R. S. (1999). Applications, project formulation, and analytical approach. In R. S. Lunetta & C. D. Elvidge (Eds.), Remote sensing change detection: Environmental monitoring methods and applications. (p. 1-19). Taylor & Francis.
Luo, H., Liu, C., Wu, C., & Guo, X. (2018). Urban Change Detection Based on Dempster–Shafer Theory for Multitemporal Very High- Resolution Imagery. Remote Sensing, 10(7), 980.
Marpu, P. R., Gamba, P., & Canty, M. J. (2011). Improving change detection results of IR-MAD by eliminating strong changes. IEEE Geoscience and Remote Sensing Letters, 8(4), 799-803.
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.
Nielsen, A. A., Conradsen, K., & Simpson, J. J. (1998). Multivariate al- teration detection (MAD) and MAF postprocessing in multispectral, bitemporal image data: New approaches to change detection studies. Remote Sensing of Environment, 64(1), 1-19.
Nordberg, M. L., & Evertson, J. (2005). Vegetation index differencing and linear regression for change detection in a Swedish mountain range using Landsat TM®and ETM+®imagery. Land Degradation and Development, 16, 139-149.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62-66.
Petit, C. C., & Lambin, E. F. (2001). Integration of multi-source remote sensing data for land cover change detection. International Journal of Geographical Information Science, 15(8), 785-803.
Powers, M. W. D. (2007). Evaluation: From Precision, Recall and F-Factor to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies, 2(1), 37-63.
Qi, J., Chehbouni, A., Huete, A., Kerr, Y., & Sorooshian, S. (1994). A modified soil adjusted vegetation index. Remote Sensing of Environment, 48(2), 119-126.
Quarmby, N. A., & Cushnie, J. L. (1989). Monitoring urban land cover changes at the urban fringe from spot hrv imagery in south-east England. International Journal of Remote Sensing, 10(6), 953-963.
Ridd, M. K., & Liu, J. (1998). A Comparison of Four Algorithms for Change Detection in an Urban Environment. Remote Sensing of Environment, 63(2), 95-100.
Rignot, E. J. M., & vanZyl, J. J. (1993). Change detection techniques for ERS-1 SAR data. IEEE Transactions on Geoscience and Remote Sensing, 31, 896–906.
Sadeghi, V., Ahmadi, F. F., & Ebadi, H. (2017). A new automatic regression-based approach for relative radiometric normalization of multitemporal satellite imagery. Computational and Applied Mathematics, 36, 825-842.
Santra, A., Mitra, S. S., Mitra, D., & Sarkar, A. (2019). Relative radiometric normalisation-performance testing of selected techniques and impact analysis on vegetation and water bodies. Geocarto International, 34(1), 98-113.
Schott, J. R., Salvaggio, C., & Volchok, W. J. (1988). Radiometric scene normalization using pseudoinvariant features. Remote Sensing of Environment, 26(1), 1-16.
Schroeder, T. A., Cohen, W. B., Song, C., Canty, M. J., & Yang, Z. (2006). Radiometric correction of multi-temporal Landsat data for characterization of early successional forest patterns in western Oregon. Remote Sensing of Environment, 103, 16-26.
Seoa, D. K., Kim, Y. H., Eo, Y. D., & Park, W. Y. P. H. C. (2017). Generation of Radiometric, Phenological Normalized Image Based on Random Forest Regression for Change Detection. Remote Sensing, 9(11), 1163.
Singh, A. (1989). Review article digital change detection techniques using remotely-sensed data. International Journal of Remote Sensing, 10(6), 989-1003.
Smith, G. M. (2008). The development of integrated object-based analysis of eo data within uk national land cover products. In T. Blaschke, S. Lang, & G. J. Hay (Eds.), Object-based image analysis: Spatial concepts for knowledge-driven remote sensing applications (p. 513- 528). Springer Berlin Heidelberg.
Solano-Correa, Y. T., Bovolo, F., & Bruzzone, L. (2019). Generation of Homogeneous VHR Time Series by Nonparametric Regression of Multisensor Bitemporal Images. IEEE Transactions on Geoscience and Remote Sensing, 57(10), 7579-7593.
Solano-Correa, Y. T., Bovolo, F., & Bruzzone, L. (2018). An Approach for Unsupervised Change Detection in Multitemporal VHR Images Acquired by Different Multispectral Sensors. Remote Sensing, 10(4), 533.
Song, A., & Choi, J. (2020). Fully Convolutional Networks with Multiscale 3D Filters and Transfer Learning for Change Detection in High Spatial Resolution Satellite Images. Remote Sensing, 12(5), 799.
Song, C., Woodcock, C. E., Seto, K. C., Lenney, M. P., & Macomber, S. A. (2001). Classification and change detection using landsat tm data: When and how to correct atmospheric effects? Remote Sensing of Environment, 75(2), 230-244.
Tenenhaus, A., Philippe, C., & Frouin, V. (2015). Kernel generalized canonical correlation analysis. Computational Statistics & Data Analysis, 90, 114-131.
Vapnik, V. N. (2000). The Nature of Statistical Learning Theory, Second Ed. Springer.
Wiskott, L., & Sejnowski, T. J. (2002). Slow feature analysis: unsupervised learning of invariances. Neural computation, 14(4), 715-770.
Yuan, D., & Elvidge, C. D. (1996). Comparison of relative radiometric normalization techniques. ISPRS Journal of Photogrammetry and Remote Sensing, 51(3), 117-126.
Zhong, C., Xu, Q., & Li, B. (2016). Relative radiometric normalization for multitemporal remote sensing images by hierarchical regression. IEEE Geoscience and Remote Sensing Letters, 13(2), 217-221.