Object oriented land cover classification using ALS and GeoEye imagery over mining area
来源期刊：中国有色金属学报(英文版)2011年第z3期
论文作者：YU Hai-yang CHENG Gang GE Xiao-san LU Xiao-ping
文章页码：733 - 737
Key words：airborne laser scanning; GeoEye; nDSM; object oriented classification; mining areas
Abstract: An object oriented coal mining land cover classification method based on semantically meaningful image segmentation and image combination of GeoEye imagery and airborne laser scanning (ALS) data was presented. First, DEM, DSM and nDSM (normalized Digital Surface Model, nDSM) were extracted from ALS data. The GeoEye imagery and DSM data were combined to create segmented objects based on neighbor regions merge method. Then 10 kinds of objects were extracted. Different kinds of vegetation objects, including crop, grass, shrub and tree, can be extracted by using NDVI and height value of nDSM. Water and coal pile field was extracted by using NDWI and the standard deviation of DSM method. Height differences also can be used to distinguish buildings from road and vacant land, and accurate building contour information can be extracted by using relationship of neighbor objects and morphological method. The test result shows that the total classification accuracy of the presented method is 90.78% and the kappa coefficient is 0.891 4.
YU Hai-yang, CHENG Gang, GE Xiao-san, LU Xiao-ping
(Key Laboratory of Mine Spatial Information Technologies of State Bureau of Surveying and Mapping,
Henan Polytechnic University, Jiaozuo 454000, China)
Abstract:An object oriented coal mining land cover classification method based on semantically meaningful image segmentation and image combination of GeoEye imagery and airborne laser scanning (ALS) data was presented. First, DEM, DSM and nDSM (normalized Digital Surface Model, nDSM) were extracted from ALS data. The GeoEye imagery and DSM data were combined to create segmented objects based on neighbor regions merge method. Then 10 kinds of objects were extracted. Different kinds of vegetation objects, including crop, grass, shrub and tree, can be extracted by using NDVI and height value of nDSM. Water and coal pile field was extracted by using NDWI and the standard deviation of DSM method. Height differences also can be used to distinguish buildings from road and vacant land, and accurate building contour information can be extracted by using relationship of neighbor objects and morphological method. The test result shows that the total classification accuracy of the presented method is 90.78% and the kappa coefficient is 0.891 4.
Key words:airborne laser scanning; GeoEye; nDSM; object oriented classification; mining areas
