A METHOD OF CONTEXTUAL DATA FUSION ON MULTISENSOR IMAGE CLASSIFICATION
In this paper, a new classification method based on contextual data fusion is proposed. The method is suited for land-use classification of remotely sensed images of the same scene captured at different dates from multiple sources. It incorporates a priori information about the likelihood of changes between the acquisitions of the different images to be fused. The contextual analysis of a multisensor image of a given site represents a way to improve the accuracy with respect to the non-contextual single-time classification.Experimental results on a multisensor data set consisting of two multisensor images are presented and the performances of the proposed method are compared with those of both a classifier based on Markov random fields and a statistical contextual classifier.
Multisensor image fusion Contextual data fusion Combination of classifers
HAI-HUI WANG YAN-SHENG LU AI-PING CAI
College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 43 College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 43 School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, 430073, China
国际会议
2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)
大连
英文
3745-3750
2006-08-13（万方平台首次上网日期，不代表论文的发表时间）