IEEE Transactions on Geoscience and Remote Sensing · 2003 · 51 citations · 18 references
ComputingComputer ScienceEarth SciencesComputer VisionFeature EngineeringRemote SensingDigital Image ProcessingFeature ExtractionImage SegmentationLand Cover MappingRemote Sensing Image AnalysisRemote Sensing ImageryLand Cover Feature ExtractionRemote Sensing ClassificationRemote Sensing Feature ExtractionRemote Sensing Image ClassificationRemote Sensing Image FeaturesRemote Sensing SegmentationWavelet FeaturesWavelet Packet Transform
The present paper describes a feature extraction method based on M-band wavelet packet frames for segmenting remotely sensed images. These wavelet features are then evaluated and selected using an efficient neurofuzzy algorithm. Both the feature extraction and neurofuzzy feature evaluation methods are unsupervised, and they do not require the knowledge of the number and distribution of classes corresponding to various land covers in remotely sensed images. The effectiveness of the methodology is demonstrated on two four-band Indian Remote Sensing 1A satellite (IRS-1A) images containing five to six overlapping classes and a three-band SPOT image containing seven overlapping classes.
18