The extraction of remote sensing signatures from a particular geographical region allows the generation of electronic signature maps, which are the basis to create a high- resolution collection atlas processed in continuous discrete time. This can be achieved using a new multispectral image classification approach based on pixel statistics for the class description. This is referred to as the Weighted Pixel Statistics Method. This paper explores the effectiveness of this novel approach developed for supervised segmentation and classification of remote sensing signatures, with a comparison with the traditional Weighted Order Statistics Method. The extraction of remote sensing signatures from real-world high- resolution environmental remote sensing imagery is reported to probe the efficiency of the developed technique.
展开▼
