Efficient parallel algorithm for pixel classification in remote sensing imagery
- 461 Downloads
An important approach for image classification is the clustering of pixels in the spectral domain. Fast detection of different land cover regions or clusters of arbitrarily varying shapes and sizes in satellite images presents a challenging task. In this article, an efficient scalable parallel clustering technique of multi-spectral remote sensing imagery using a recently developed point symmetry-based distance norm is proposed. The proposed distributed computing time efficient point symmetry based K-Means technique is able to correctly identify presence of overlapping clusters of any arbitrary shape and size, whether they are intra-symmetrical or inter-symmetrical in nature. A Kd-tree based approximate nearest neighbor searching technique is used as a speedup strategy for computing the point symmetry based distance. Superiority of this new parallel implementation with the novel two-phase speedup strategy over existing parallel K-Means clustering algorithm, is demonstrated both quantitatively and in computing time, on two SPOT and Indian Remote Sensing satellite images, as even K-Means algorithm fails to detect the symmetry in clusters. Different land cover regions, classified by the algorithms for both images, are also compared with the available ground truth information. The statistical analysis is also performed to establish its significance to classify both satellite images and numeric remote sensing data sets, described in terms of feature vectors.
KeywordsPixel classification Distributed algorithm Remote sensing imagery Symmetry detection Point-symmetry based distance measure
Experiments presented in this paper were carried out using the PLAFRIM experimental testbed, being developed under the INRIA PlaFRIM development action with support from LABRI and IMB and other entities: Conseil Régional d’Aquitaine, FeDER, Université de Bordeaux and CNRS (see https://plafrim.bordeaux.inria.fr/).
- 5.Bentley JL (1990) K-d trees for semidynamic point sets (1990). In: Proceedings of the 6th annual Symposium on Computational Geometry (SCG 90), ACM-SIGACT ACM-SIGGRAPHGoogle Scholar
- 6.Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New YorkGoogle Scholar
- 10.Gonzalez RC, Woods RE (1992) Digital image processing. Addison-Wesley, MassachusettsGoogle Scholar
- 11.Hollander M, Wolfe D (1999) Nonparametric statistical methods, 2nd edn. WileyGoogle Scholar
- 13.Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall, Englewood CliffsGoogle Scholar
- 20.Mount DM, Arya S (2005) ANN: A library for approximate nearest neignbor searching. http://wwwcsumdedu/~mount/ANN
- 22.Pacheco P (1997) Parallel programming with MPI. Morgan KaufmannGoogle Scholar
- 23.Pierce L, Samples G, Dobson M, Ulaby F (1998) An automated usupervised/supervised methodology. In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS’98), vol 4. IEEE, New York, pp 1781–1783Google Scholar
- 25.Sarkar A, Maulik U (2009) Parallel point symmetry based clustering for gene microarray data. International Conference on Advances in Pattern Recognition, pp 351–354. doi: ieeecomputersociety.org/10.1109/ICAPR.2009.40
- 27.Song Y, Chen WY, Bai H, Lin CJ, Chang E (2008) Parallel spectral clustering. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp 374–389Google Scholar