基于改进证据理论的多时相微波遥感图像融合及在城区地表变化检测中的应用

曹广真; 侯鹏; 金亚秋; 毛显强

doi:10.3724/SP.J.1146.2006.02035

基于改进证据理论的多时相微波遥感图像融合及在城区地表变化检测中的应用

doi: 10.3724/SP.J.1146.2006.02035

基金项目:

国家973计划(2005CB724204)资助课题

计量
- 文章访问数: 3436
- HTML全文浏览量: 97
- PDF下载量: 1016
- 被引次数: 0
出版历程
- 收稿日期: 2006-12-25
- 修回日期: 2007-09-20
- 刊出日期: 2008-08-19

Data Fusion of Multi-Temporal SAR Remote Sensing with Improved D-S Algorithm and Application to Change Detection of Urban Terrain

摘要

摘要: 该文发展证据理论融合算法，采用不同时相的微波遥感图像检测复杂城市区域地表的变化信息。首先通过综合考虑证据本身的确信度和证据对辨别框架中子集的平均支持度进行证据间的加权合成，改进证据理论对证据的合成，提高其可靠性；然后提取不同时相图像间的散射幅度的对比度和概率密度分布函数在皮尔逊图中的欧式距离，两种特征参数代表了像元级和区域级不同空间尺度下微波遥感图像中关于地表变化的信息；最后将改进的证据理论用于两特征之间的融合处理，得到地表的变化信息。为了实验和验证该文的方法，选择上海市陆家嘴地区不同时相的微波遥感图像，进行地表的变化检测，得到较好的结果。
- 数据融合; 城市区域; 改进的证据理论; 变化检测
Abstract: Dempster-Shafer (D-S) algorithm is improved to fuse different features of multi-temporal SAR images to detect change detection of urban areas. Firstly, Dempster-Shafer is developed by not only considering the certainty of the evidence, but also considering the average support of the evidence to different subsets in the assignment framework so that it can give more reliable combination result. Secondly, amplitude ratio feature and Euclid distance of the probability density distribution function in Pearson graph from different temporal SAR images are extracted to present change feathers in different scales. Finally, the improved Dempster-Shafer algorithm is applied to fuse the two different features to detect change information of SAR images. An example of the Shanghai Lujiazui area using the ERS-2 SAR image well demonstrates the accuracy of the improved fusion algorithm.

HTML全文

参考文献(1)

Villasensor J D, Fatland D R, and Hinzman L D. Changedetection on Alaska's North Slope using repeat-pass ERS-1SAR images [J].IEEE Trans. on Geoscience and RemoteSensing.1993, 31(1):227-236[2]Bruzzone L and Prieto D F. Automatic analysis of thedifference image for unsupervised change cetection [J].IEEETrans. on Geoscience and Remote Sensing.2000, 38(3):1171-1182[3]Jin Ya-qiu and Chen Fei. Automatic detection of changedirection of multi-temporal ERS-2 SAR images usingtwo-threshold EM and MRF algorithms [J].Imaging ScienceJournal.2004, 52( 4):234-247[4]Bazi Y, Bruzzone L, and Melgani F. An unsupervisedapproach based on the generalized Gaussian model toautomatic change detection in multitemporal SAR images [J].IEEE Trans. on Geoscience and Remote Sensing.2005, 43(4):874-878[5]Bujor F, Trouve E, and Valet L, et al.. Application of logcumulantsto the detection of spatiotemporal discontinuitiesin multitemporal SAR images [J].IEEE Trans. on Geoscienceand Remote Sensing.2004, 42(10):2073-2084[6]Klein L A. Sensor and Data Fusion Concepts and Application(second edition) [M]. Bellingham: SPIE Optical EngineeringPress, 1999: 48.[7]Yager R. On the dempster shafer framework and newcombination rules [J].Information Sciences.1987, 41(2):93-137[8]孙全, 叶臭清, 顾伟康.一种新的基于证据理论的合成公式[J].电子学报, 2000, 28(8): 117-119.Sun Quan, Ye Xiu-qing, and Gu Wei-kang. A newcombination rule of evidence theory [J]. Acta ElectronicaSinica, 2000, 28(8): 117-119.[9]Yager R R. Uncertainty representation using fuzzy measures[J].IEEE Trans. on Systems, Man and Cybernetics.2002,32(1):13-20[10]Rignot E J M and van Zyl J J. Change detection techniquesfor ERS-1 SAR data [J].IEEE Trans. on Geoscience andRemote Sensing.1993, 31(4):896-906[11]Tison C, Nicolas J M, and Tupin F, et al.. A new statisticalmodel for Markovian classification of urban areas inhigh-resolution SAR images [J].IEEE Trans. on Geoscienceand Remote Sensing.2004, 42(10):2046-2057[12]Nicolas J M, and Tupin F. Gamma mixture modeled withsecond kind statistics: application to SAR image processing[A]. In Proceedings of IEEE International Geoscience andRemote Sensing Symposium [C], Toronto, 2002, 4: 2489-2491.

施引文献

资源附件(0)

访问统计