Improvement of Spatial Accuracy in Natural Resources Mapping Using Multisensor Remote Sensing and Multisource Spatial Data

摘要

In this paper, we present a subpixel proportional land-cover information transformation (SPLIT) model to extract proportions of land cover types from Landsat Thematic Mapper (TM) data by incorporating subpixel information obtained from high spatial resolution digital multispectral videography (DMSV) data. Modularized artificial neural network (MANN) was developed to integrate multisensor remote sensing and the transection data guided by global position system (GPS). The SPLIT model is to improve the mapping accuracy of natural communities for the efforts of Chicago Wilderness in biodiversity conservation.