A Hybrid Algorithm for Satellite Image Classification

Abstract

Remote sensing is the most relevant science that permits us to acquire information about the surface of the land, without having actual contact with the area being observed. Amongst the multiple uses of remote sensing, one of the most important has been its use in solving the problem of land cover mapping. Multi spectral classification of remotely sensed data has been widely used to generate thematic Land-Use/Land-Cover maps. Two of the extensively used algorithms for image classification are Self Organizing Feature Maps (SOFM) and Ant Colony Optimization. Although both are bio-inspired optimization techniques, however combining them is a challenging task, especially in the field of remote sensing. In this paper, we have used a Self Organizing Ant Algorithm for Classification of remotely sensed data. Also, we have suggested a new reinforcement factor for the pheromone updation. A test of algorithm is conducted by classifying a high resolution, multi-spectral satellite image of Alwar Region. Results obtained are encouraging.