Implementation of a Segmentation Method for Agricultural Fields in Aerial Sequences of Images Based on CSAR Model

In this paper, a segmentation method for agricultural fields in aerial sequences of images based on the Circular Symmetri Auto-Regressive (CSAR) model is presented. The image sequences assumed to be acquired by a video camera (RGB-CCD system) from an aeroplane, which moves linearly over the scene. The objects in the scenes being considered in this paper, are agricultural fields. The classes of agricultural fields to be distinguished are determined by the type of crop, e.g. potatoes sugar beet, wheat, etc. In order to recognize and classify these fields from aerial sequence of images, a reliable segmentatio is required. Here texture features are used for segmentation. The implementation of segmentation for agricultural fields in aerial sequences of images is based on CSAR model in texture analysis. By comparing the estimated parameters of CSAR model from different area in an image, the characteristics and the class of a texture may be determined. The paper describes the segmentation method and its evaluation through experiments. Based on segmentation results, classification for surface texture of vegetation from aerial sequences of images is realized.