The Optimal Fusion of Multi-spectral Remote Sensing Images between Bands by Using Decomposable Markov Networks
CAO Jian-nong1,2, LI De-ren3, GUAN Ze-qun2
(1. School of Architecture, Xi'an University of Architecture & Technology, Xi'an,710055, China; 2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, 430079, China; 3.National Laboratory for Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan, 430079)
Abstract£ºThe paper studies concept and method of DMN, analyses its role in spatial data mining, and deeply investigates several score metrics which are used in constructing DMN between multi-bands remote sensing images, and realizes optimal fusion of bands. The researches indicate that the DMN may apropos reveal abstract adjacent relations existing in spatial data, and is basis of in-depth treatment of data. And the DMN oneself has capabilities of showing knowledge. Lastly, point out future direction of its application.
Key words£ºDMN; multi-bands remote sensing; probability distance; spatial data mining