Conference Paper

A Distributed Algorithm for Multispectral Image Segmentation

Univ. Politehnica of Bucharest, Bucharest;
DOI: 10.1109/SYNASC.2007.33 Conference: Symbolic and Numeric Algorithms for Scientific Computing, 2007. SYNASC. International Symposium on
Source: IEEE Xplore

ABSTRACT This paper presents a distributed algorithm for multi-spectral image segmentation. Regions of the image are processed separately and then the results are combined. For this, the algorithm employs two types of clustering algorithms, each specialized in its task and steered toward obtaining a final meaningful segmentation. The workers use an iterative clustering algorithm which is an extension of fuzzy c-means that uses spatial information and a spectral compatibility heuristic. An agglomerative clustering algorithm is used by the master to combine the partial results. The algorithm is used for the segmentation of satellite images coming from the MODIS sensor aboard the Terra and Aqua satellites. The quality of the segmentation results and the speedups obtained by using the grid are discussed.

0 Bookmarks
 · 
59 Views
  • Source
    High-Performance Computing in Remote Sensing. Proceedings of SPIE Volume 8183; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a distributed algorithm for critical area detection in satellite imagery. The detection of critical area is very important in natural disaster detection and control. The algorithm uses the distributed change detection methods for multiple spectral bands in satellite images and combines changes which have appeared during a period of time. The result shows a critical area for analyzed time interval. The algorithm is distributed for support a large amount of data. The distributed approach shows a decrease in processing time with the increase of the number of workers. The presented algorithm represents a component from MedioGRID system, which implemented a real-time satellite image processing system for extracting relevant environmental and meteorological parameters on Grid systems. The critical area detection application will be integrated in Grid environments.
    SYNASC '08: Proceedings of the 2008 10th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing; 01/2008