An object-oriented method based on multi-scale segmentation for classification and mapping from Quick bird images

Abstract

The classification and mapping method is vital for many fields of research and has important societal and economic meaning. In this study, we applied QuickBird image to discuss a Multi-scale segmentation method about orchard in Taolin region, Ningxia province in China. Meanwhile, eCognition , as the leading object-oriented software in the world , was used to achieve the goal of classification and mapping. Then, based on the image object's attributes, relationship of each other etc, we formulated a orchard classification system, set a suit of remote sensing interpretation standard, and put forward a Multi-scale segmentation idea to realize sophisticated classification and get satisfied classification result.