Automatic Spectral–Spatial Classification Framework Based on Attribute Profiles and Supervised Feature Extraction
- 17 December 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 52 (9), 5771-5782
- https://doi.org/10.1109/tgrs.2013.2292544
Abstract
A robust framework for the classification of hyperspectral images which takes into account both spectral and spatial information is proposed. The extended multivariate attribute profile (EMAP) is used for extracting spatial information. Moreover, for solving the so-called curse of dimensionality, supervised feature extraction is carried out on both the original hyperspectral data and the output of the EMAP. After performing the dimensionality reduction, two output vectors of the original data and attributes are concatenated into one stacked vector. The final classification map is achieved by using a random-forest classifier. The main difficulties of using an EMAP is to initialize the attribute parameters. Therefore, a fully automatic scheme of the proposed method is introduced to overcome the shortcomings of using EMAP. The proposed method is tested on two widely known data sets. Experimental results confirm that the proposed method provides an accurate classification map in an acceptable CPU processing time.Keywords
Funding Information
- Icelandic Research Fund for Graduate Students
This publication has 31 references indexed in Scilit:
- Spectral–Spatial Classification of Hyperspectral Images Based on Hidden Markov Random FieldsIEEE Transactions on Geoscience and Remote Sensing, 2013
- Combining Support Vector Machines and Markov Random Fields in an Integrated Framework for Contextual Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2012
- Automatic Generation of Standard Deviation Attribute Profiles for Spectral–Spatial Classification of Remote Sensing DataIEEE Geoscience and Remote Sensing Letters, 2012
- Classification of Hyperspectral Images by Using Extended Morphological Attribute Profiles and Independent Component AnalysisIEEE Geoscience and Remote Sensing Letters, 2010
- Extended profiles with morphological attribute filters for the analysis of hyperspectral dataInternational Journal of Remote Sensing, 2010
- Combination of region-based and pixel-based hyperspectral image classification using erosion technique and MRF modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Theoretical Foundations of Spatially-Variant Mathematical Morphology Part II: Gray-Level ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Thematic Map ComparisonPhotogrammetric Engineering & Remote Sensing, 2004
- Random ForestsMachine Learning, 2001
- Antiextensive connected operators for image and sequence processingIEEE Transactions on Image Processing, 1998