5 前景
目前的SAR变化检测算法大部分为中低分辨率、象元级、单极化的SAR影像变化检测。最近几年，SAR成像技术日益成熟，图像质量逐渐提高，分辨率不断增强，获取数据的能力和精度越来越高，图像获取越来越便捷。尤其是2007年，德国TerrraSAR-X和意大利Cosmo-SkyMed新型雷达系统的出现，引起了雷达遥感研究和应用的热潮。随着新型雷达系统的出现，SAR变化检测的前景会更加广阔：
1高空间分辨率使得SAR图像能够在较小的空间尺度上探测细节变化，实现对建筑物、道路等地面目标细微特征的探测。
2 多极化方式能够使得雷达图像的解译变得更为容易，实现在变化信息提取的基础上进一步确定变化类型。
3高空间分辨率影像的纹理结构更加清晰，纹理特征成为重要的识别信息，实现特征级变化检测。
因此，随着雷达技术的发展，SAR的变化检测研究将会实现高分辨率、特征级、多极化的变化检测，进而在军事侦查、探测，资源环境监测，土地利用与覆盖变化以及灾害评估与监测等方面起到越来越重要的作用。
参考文献
[1]X.Dai and S.Khorram．The effects of image misregistration on the accuracy of remotely sensed change detection[J]．IEEE Transaction on Geoscience and Remote Sens，1998，36(5)：1566–1577．
[2]Jannie Moulton，Saleem Kassam，Fauzia Ahmad，etc．Target and change detection in synthetic aperture radar sensing of urban structures[J]．Radar Conference, 2008，5：1-6．
[3]Paolo Gamba，Fabil Dell ， Gianni Lisini．Change detection of mulittemporal SAR data in urban area combining feature-based and pixel-based techniques[J]． IEEE Transaction on Geoscience and Remote Sensing，2006，44(10)：2820-2827．
[4] 吴芳，刘荣，田维春，等．遥感变化检测技术及其应用综述[J]．地理空间信息，2007，5(4)：57-60．
[5]Lillesnad，T.M．，R．W．Keief．Remote Sensing and Image Interpretation，2nd Edition． John Wiley&Sons，1979．
[6]Ashbindu Singh．Principal components analysis in remote sensing[J]．IEEE Geoscience and Remote Sensing，1993，18-21(4)：1680-1682．
[7]张路．基于多元统计分析的遥感影像变化检测方法研究[D]．武汉：武汉大学，2004．
[8]Malila，W.A． Change vector analysis：an approach for detecting forest changes with Landsat．Proceeding，LARS Machine Processing of Remotely Sensed Data Sympostium，W．Lafayette，in：Laboratory for the Application of Remote Sensing：326－335．
[9]陈富龙，张红，王超．SAR变化检测技术发展综述[J]．遥感技术与应用，2007， 22（1）：109-115．
[10]Vilasenor L D．Eatland D R，Hinzman L D． Change detection on Alaska's North Slope using repeat-pass ERS-1 SAR images[J]．IEEE Transactions on Geoscience and Remote Sensing，1993，31(1)：227-236．
[11]Eric J， Rignot M．Change Detection techniques for ERS-1 SAR data[J]．IEEE Transactions on Geoscience and Remote Sensing，1993，(31)4：896-906．
SAR图像变化检测综述
[12]Bazi Y，Bruzzone L，Melgani F．Automatic identification of the number and value of decision thresholds in the log-ratio images for change detection in SAR images[J]．IEEE Geoscience and Remote Sensing，2006，3(3)：349-353．
[13]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 Geoscience and Remote Sensing，2005．43(4)：874-887．
[14]Bazi.Y，Bruzzone．L，Melgani．F．Automatic identification of the number and values of decision thresholds in the log-ratio image for change detection in SAR images．IEEE Transactions on Geoscience and Remote Sensing，2006．3(3)：349-353．
[15] Bazi.Y， Bruzzone．L， Melgani．Farid．Image thresholding based on the EM algorithm and the generalized Gaussian distribution．Pattern Recognition．2007，40(2) ：619–634．
[16]Bruzzone.L．A minimum-cost thresholding technique for unsupervised change[J]．Internationa l Journal of Remote Sensing，2000，21(18)：3539–3544．
[17]Bruzzone.L，Prieto．D．F．Automatic analysis of the difference image for unsupervised change detection[J]．IEEE Geoscience and Remote Sensing，2000，38(3)：1171-1182．
[18]Bruzzone.L，Prieto．D．F．An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensingimages[J]．IEEE Transactions on Geoscience and Remote Sensing， 2002， 11(4) ：452-466．
[19] Kasetkasem ．T and Varshney． P． An Image Change Detection Algorithm Based on Markov Random Field Models[J]．IEEE Transactions on Geoscience and Remote Sensing，2002，40(8)： 1815–1823．
[20]Derrode．Ｍ， Mercier G，Ｐieczynski W．Unsupervised change detection in SAR images using a multi-component HMC model．Multi-Temp， July， 16-18 2003， Ispra， Italy．
[21]Bazi．Y， Bruzzone．L，andMelgani．F．Change Detection in Multitemporal SAR Images Based on the EM-GA Algorithm and Markov Random Fields．Proc. of the 3rd Int. Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp 2005), Biloxi, Mississippi, USA, May 2005．
St´ ephane Derrode．Change detection in synthetic aperture radar images [22] Zied Bouyahia， Lamia Benyoussef，
with a sliding hidden Markov chain model．Journal of Applied Remote Sensing，2008．
[23]Ghosh .S， Bruzzone．L， Bovolo．F．etc．all．A Context-Sensitive Technique for Unsupervised Change Detection Based on Hopfield-Type Neural Networks[j]． IEEE Transactions on Geoscience and Remote Sensing， 2007，45(3)：778-789．