Robust Technique for Segmentation and Counting of Trees from Remotely Sensed Data

Advanced data mining technologies along with the large quantities of Remotely Sensed Imagery, provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data are typically used in order to detect the distribution of vegetation, soil classes, built-up areas, roads and water bodies such as rivers, lakes etc. The availability of new high spatial resolution satellite sensors permits people having large amounts of detailed digital imaging of rural environment. In this paper an approach towards the automatic segmentation of the satellite image into distinct regions and further to extract tree count from the vegetative area is presented. Counting trees in specific geographical areas is a very complicated process. Now a days manual counting is done by the forest department, both in agricultural as well as forest regions. Image segmentation is a very important technique in image processing. However, it is a very difficult task and there is no single unified approach for all types of images In this paper, image processing techniques have been employed for automatic segmentation of the satellite image and extraction of the trees from the segmented image.