A k-means clustering algorithm initialization for unsupervised statistical satellite image segmentation

The increasing availability of satellite images acquired periodically by satellite on different area, makes it extremely interesting in many applications. In deed, the recent construction of multi and hyper spectral images will provide detailed data with information in both the spatial and spectral domain. This data shows great promise for remote sensing applications ranging from environmental and agricultural to national security interests. The exploitation of these images requires the use of different approach, and notably these founded on the unsupervised statistical segmentation principle. Indeed these methods that exploit the statistical images attributes offer some convincing and encouraging results, under the condition to have an optimal initialization step. Indeed, in order to assure a better convergence of the different images attributes, the unsupervised segmentation approaches, require a fundamental initialization step. We will present in this paper a k-means clustering algorithm and describe its importance in the initialization of the unsupervised satellite image segmentation.