tailieunhanh - WETLAND AND WATER RESOURCE MODELING AND ASSESSMENT: A Watershed Perspective - Chapter 2

Một chuyên gia phân loại hình ảnh dựa trên hệ thống Xác định loại liên quan đến đất ngập nước Che đất 2,1 GIỚI THIỆU Hiểu biết về thay đổi vùng đất ngập nước liên quan đến phát triển đô thị bằng cách sử dụng các kỹ thuật viễn thám là rất quan trọng để lập kế hoạch quản lý hệ sinh thái và phát triển khu vực bền vững. Các phương pháp phân loại cho mỗi điểm ảnh có được sử dụng rộng rãi trong khai thác thông tin chuyên đề (Wang et al 2004). Thuộc tính quang phổ của các. | 2 An Expert System-Based Image Classification for Identifying Wetland-Related Land Cover Types Xiaobin Cai and Xiaoling Chen INTRODUCTION Understanding wetland changes in relation to urban development using remote sensing techniques is critical to planning ecosystem management and sustainable regional development. The per-pixel classification methods have been used extensively in thematic information extraction Wang et al. 2004 . The spectral property of surface objects was utilized in remote sensing classification in these techniques. However the spectral property information usually is not sufficient to generate accurate classification results. Therefore other types of information such as DEM digital elevation model and road data have been used to improve classification accuracy. The intrinsic spatial distribution and relationships that exist in geographical objects enable the adoption of spatial information such as the texture of an object which was widely used in the process of classification at the pixel level. On the other hand to better represent spatial relationships spatial information at the object level was more useful in identifying the distribution patterns of different classes. This idea directly resulted in the invention of object-oriented classification software. Ecognition a software package was recently enhanced by integrating the object-oriented classification techniques with its classification procedures. However Ecognition s classification procedure is too complicated Burnett et al. 2003 especially when selecting segmentation parameters. This paper introduces a simple object-oriented method to improve classification accuracy. STUDY AREA AND DATA The study area is located in northern Jiangxi Province China with a geographic range of E115 24 to 117 43 and N27 57 to 29 47 . The area covers Poyang Lake and its surrounding wetlands which is one of 21 wetlands in China that have been designated as having international importance under the .