A Distributed Algorithm for Multispectral Image Segmentation
Univ. Politehnica of Bucharest, BucharestDOI: 10.1109/SYNASC.2007.33 Conference: Symbolic and Numeric Algorithms for Scientific Computing, 2007. SYNASC. International Symposium on
Source: IEEE Xplore
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.
Conference Paper: A Distributed Algorithm for Critical Area Detection in Satellite Imagery[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
- [Show abstract] [Hide abstract]
ABSTRACT: Fuzzy clustering is one of the most frequently used methods for identifying homogeneous regions in remote sensing images. In the case of large images, the computational costs of fuzzy clustering can be prohibitive unless high performance computing is used. Therefore, efficient parallel implementations are highly desirable. This paper presents results on the efficiency of a parallelization strategy for the Fuzzy c-Means (FCM) algorithm. In addition, the parallelization strategy has been extended in the case of two FCM variants, which incorporates spatial information (Spatial FCM and Gaussian Kernel-based FCM with spatial bias correction). The high-level requirements that guided the formulation of the proposed parallel implementations are: (i) find appropriate partitioning of large images in order to ensure a balanced load of processors; (ii) use as much as possible the collective computations; (iii) reduce the cost of communications between processors. The parallel implementations were tested through several test cases including multispectral images and images having a large number of pixels. The experiments were conducted on both a computational cluster and a BlueGene/P supercomputer with up to 1024 processors. Generally, good scalability was obtained both with respect to the number of clusters and the number of spectral bands.High-Performance Computing in Remote Sensing. Proceedings of SPIE Volume 8183; 01/2011
- [Show abstract] [Hide abstract]
ABSTRACT: In this article, a segmentation approach for cloud detection in Meteosat Second Generation MSG multispectral images is proposed. The proposed algorithm uses recursive segmentation that dynamically reduces the number of classes. This algorithm consists of two steps. First, an initial segmentation of the image is obtained using local fuzzy clustering. The clustering algorithm is formulated by modifying the similarity measure of the standard fuzzy c-means FCM algorithm. The new similarity function includes the spectral information as well as the homogeneity and spatial clustering information of each considered pixel. In the second step, a hierarchical region-merging process is used to reduce the number of image clusters. At each iteration, the segmentation algorithm proceeds with a new partition until the final result of the segmentation is obtained. The proposed method has been tested using synthetic and MSG images. It yields a compact and coherent segmentation map, with a satisfactory reproduction of the image contours. Moreover, the different types of clouds are well detected and separated with appropriate accuracy.International Journal of Remote Sensing 09/2013; 34(23-23):8360-8372. DOI:10.1080/01431161.2013.838707 · 1.65 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.