Abstract
Hyperspectral imaging is a new remote sensing technique that generates hundreds of images, corresponding to different wavelength channels, for the same area on the surface of the Earth. Supervised classification of hyperspectral image data sets is a challenging problem due to the limited availability of training samples (which are very difficult and costly to obtain in practice) and the extremely high dimensionality of the data. In this paper, we explore the use of multi-channel morphological profiles for feature extraction prior to classification of remotely sensed hyperspectral data sets using support vector machines (SVMs). In order to introduce multi-channel morphological transformations, which rely on ordering of pixel vectors in multidimensional space, several vector ordering strategies are investigated. A reduced implementation which builds the multi-channel morphological profile based on the first components resulting from a dimensional reduction transformation applied to the input data is also proposed. Our experimental results, conducted using three representative hyperspectral data sets collected by NASA's Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) sensor and the German Digital Airborne Imaging Spectrometer (DAIS 7915), reveal that multi-channel morphological profiles can improve single-channel morphological profiles in the task of extracting relevant features for classification of hyperspectral data using small training sets.
Highlights
Hyperspectral imaging is an emerging technique that has gained tremendous popularity in many research areas, most notably, in remotely sensed satellite imaging and aerial reconnaissance [1]
We have addressed the problem of supervised classification of hyperspectral image data with limited training samples and further investigated several strategies to build morphological profiles by considering the full spectral information available in the input hyperspectral data and different ways to reduce its dimensionality
Our experimental results, conducted using three highly representative data sets collected by the Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) and DAIS 7915 sensors, reveal that multi-channel morphological profiles built using the entire spectral information available in the data can provide a very good mechanism for feature extraction prior to classification by integrating the spatial and the spectral information available in the data
Summary
Hyperspectral imaging ( known as imaging spectroscopy) is an emerging technique that has gained tremendous popularity in many research areas, most notably, in remotely sensed satellite imaging and aerial reconnaissance [1]. MM operations have been generally applied in the spatial domain of the scene [9], i.e., to each image band of the original scene or to the first few bands resulting from a transformed version of the original hyperspectral scene using techniques such as principal component analysis (PCA) [10] or the minimum noise fraction (MNF) [11] Variations on this idea have comprised extended morphological operations able to work on the spectral domain of the data [12,13], i.e., morphological operations applied to the entire set of bands of the original scene or to a subset of bands, in vector-based fashion. Our last section concludes with some remarks and hints at plausible future research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
