Title: | Automatic Framework for Spectral–Spatial Classification Based on Supervised Feature Extraction and Morphological Attribute Profiles |
Author: |
|
Date: | 2014 |
Language: | English |
Scope: | 2147-2160 |
University/Institute: | Háskóli Íslands University of Iceland |
School: | Verkfræði- og náttúruvísindasvið School of Engineering and Natural Sciences |
Department: | Rafmagns- og tölvuverkfræðideild Faculty of Electrical and Computer Engineering |
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing; 7:6 |
ISSN: | 1939-1404 |
DOI: | 10.1109/JSTARS.2014.2298876 |
Subject: | Accuracy; Data mining; Feature extraction; Hyperspectral imaging; Iron; Vectors; Gagnavinnsla; Skráning gagna |
URI: | https://hdl.handle.net/20.500.11815/65 |
Citation:P. Ghamisi, J. A. Benediktsson, G. Cavallaro and A. Plaza. 2014 "Automatic Framework for Spectral–Spatial Classification Based on Supervised Feature Extraction and Morphological Attribute Profiles," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 6, pp. 2147-2160.
|
|
Abstract:Supervised classification plays a key role in terms of accurate analysis of hyperspectral images. Many applications can greatly benefit from the wealth of spectral and spatial information provided by these kind of data, including land-use and land-cover mapping. Conventional classifiers treat hyperspectral images as a list of spectral measurements and do not consider spatial dependencies of the adjacent pixels. To overcome these limitations, classifiers need to use both spectral and spatial information. In this paper, a framework for automatic spectral-spatial classification of hyperspectral images is proposed. In order to extract the spatial information, Extended Multi-Attribute Profiles (EMAPs) are taken into account. In addition, in order to reduce the redundancy of features and address the so-called curse of dimensionality, different supervised feature extraction (FE) techniques are considered. The final classification map is provided by using a random forest classifier. The proposed automatic framework is tested on two widely used hyperspectral data sets; Pavia University and Indian Pines. Experimental results confirm that the proposed framework automatically provides accurate classification maps in acceptable CPU processing times.
|
|
Rights:(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
|