Change detection methodology based on region classification fusion

Conference Paper · August 2007with23 Reads
DOI: 10.1109/ICIF.2007.4408010 · Source: IEEE Xplore
Conference: Information Fusion, 2007 10th International Conference on
In this paper, several classification methods are presented and a fusion structure is included to improve the final classification performance. The definition of "layer" and the method to create it are then introduced. Based on "layer", a multiple level change detection algorithm is proposed, which gives the details of the changes in each region and is demonstrated to be an easy, effective and reliable method. Experimental results are provided using RADARSAT images, which have been registered with the automated registration algorithm of A.U.G. Signals that is currently available under the distributed processing system
  • [Show abstract] [Hide abstract] ABSTRACT: Polarimetric signatures of two primitives shapes (dihedral and edge) are simulated using high-frequency electromagnetic scattering methods. Signatures are predicted for a variety of orientations of the shapes. Polarimetric responses are analyzed using a polarization scattering matrix decomposition developed by Cameron and Leung (1990, 1992). It is shown that symmetric scatterer responses can be represented as points contained in the unit disc of the complex plane. The simulation shows that the polarimetric responses of the primitive shapes are remarkably stable as the shapes are rotated about various axes
    Article · Jun 1996
  • [Show abstract] [Hide abstract] ABSTRACT: Classification trees based on exhaustive search algorithms tend to be biased towards selecting variables that afford more splits. As a result, such trees should be interpreted with caution. This article presents an algorithm called QUEST that has negligible bias. Its split selection strategy shares similarities with the FACT method, but it yields binary splits and the final tree can be selected by a direct stopping rule or by pruning. Real and simulated data are used to compare QUEST with the exhaustive search approach. QUEST is shown to be substantially faster and the size and classification accuracy of its trees are typically comparable to those of exhaustive search. 1
    Full-text · Article · Jul 1999
  • [Show abstract] [Hide abstract] ABSTRACT: This paper presents a new architecture to integrate a library of feature extraction, Data-mining, and fusion techniques to automatically and optimally configure a classification solution for a given labeled set of training patterns. The most expensive and scarce resource in any detection problem (feature selection/classification) tends to be the acquiring of labeled training patterns from which to design the system. The objective of this paper is to present a new Data-mining architecture that will include conventional Data-mining algorithms, feature selection methods and algorithmic fusion techniques to best exploit the set of labeled training patterns so as to improve the design of the overall classification system. The paper describes how feature selection and Data-mining algorithms are combined through a Genetic Algorithm, using single source data, and how multi-source data are combined through several best-suited fusion techniques by employing a Genetic Algorithm for optimal fusion. A simplified version of the overall system is tested on the detection of volcanoes in the Magellan SAR database of Venus.
    Full-text · Article · Oct 2007
Show more