Detection of individual tree crowns in high spatial resolution using 2D walking ant histogram

In this paper the forest characterizing is done to find the forest structure using novel shape descriptor. Forest structure types have found based on the high intensity of the sub segments. By adopting a multiscale approach over the edge field major object boundaries are extracted from a scale map. The process of a walking ant with a limited line of sight over the boundary of a particular object, or the texture we traverse through each sub segment and describe a certain line of sight, whether it is a continuous branch or a corner, using individual 2- D histograms. The purpose of this study is detecting individual tree crowns in the forest images. First in order to detect the individual tree crowns, the outline of the tree crown is detected using watershed Algorithm. Next a supervised maximum likelihood classification is performed using the spectral and textual features of each individual tree crown. Thus the present approach could have an operational application in the inventory procedure and forest management plans.