Element-Oriented Land-Use Classification of Mining Area by High Spatial Resolution Remote Sensing Image
For the purpose of rational exploitation of mineral resources and effective monitor of ecological environment in mining areas, we did experiments about land-use classification of the high spatial resolution airborne image from a mining area in Heng County of Guangxi province using element-oriented method. By optimizing the evolution of multi-scale fractal network segment process, two levels of image elements were extracted efficiently. Based on the multi-scale image elements, the land-use classification knowledge base of the study area was established through analyzing spectral, spatial and class-relation features in this area. The classification precision improved from 53% to 90% by decision supporting fuzzy logic reasoning of the knowledge base. The experiments show that the element-oriented method can obtain high precision land-use classification for taking full advantage of various features of the mining area from the high spatial resolution image.
high spatial resolutionelement-orientedland-use classification of mining areafractal net evolution approachknowledge base
NETL
NSTL
万方数据
维普
