Spectral Unmixing of Hyperspectral Images in the Presence of Small Targets
Journal Title: Remote Sensing - Year 2018, Vol 7, Issue 1
Abstract
Generally, the content of the hyperspectral image pixel is a mixture of the reflectance spectra of the different components in the imaged scene. In this paper, we consider a linear mixing model where the pixels are linear combinations of those reflectance spectra, called endmembers, and linear coefficients corresponding to their abundances. An important issue in hyperspectral imagery consists in unmixing those pixels to retrieve the endmembers and their corresponding abundances. We consider the unmixing issue in the presence of small targets, that is, their endmembers are only contained in few pixels of the image. We introduce a thresholding method relying on Non-negative Matrix Factorization to detect pixels containing rare endmembers. We propose two resampling methods based on bootstrap for spectral unmixing of hyperspectral images to retrieve both the dominant and rare endmembers. Our experimental results on both simulated and real world data demonstrate the efficiency of the proposed method to estimate correctly all the endmembers present in hyperspectral images, in particular the rare endmembers.
Authors and Affiliations
Sylvain Ravel, Caroline Fossati, Salah Bourennane
Keywords
Related Articles
- EP ID EP680273
- DOI -
- Views 200
- Downloads 0
An optimized reconstruction algorithm for point spread Function Based on Slant Step Edge
The existing slant step edge methods, greatly influenced by the edge? s sub-pixel positioning precision, the Edge spread Function (ESF) Samples5 quality and fitting models of the ES F curve, do not perform-stability and...
Exploration and exploration of geological and mineral resources
In view of the application of prospecting and prospecting methods, a simple discussion is made. At the present stage, the stock of mineral, has been reduced continuously, which makes s continue to increase the strength o...
The development characteristics of remote sensing classification technology in the Study of vegetation classification
Summary Remote Sensing technology evolving , The applies to vegetation classification studies with the following features : one , Remote sensing data from low-resolution to high resolution ; second , data from the single...
The application of photogrammetry and remote Sensing in Engineering surveying
The with the development of the the global economy faster and faster, also affects the industrial science and technology To reform the innovation, and by speeding up its development speed, now modern engineering measurem...
Development and application of settlement Index of Forest pests and Diseases for Large Areas through Using modis-ndvi Data
settlement to forest pests and diseases to Large areas is one of Most pressing challenges For the " Development of Forest insurance. This Study , taking , forestareas of of East Inner Mongolia, developed A settlement ind...