%0 Journal Article
%T A Neural Network Based Hybrid Mixture Model to Extract Information from Non-linear Mixed Pixels
%A Uttam Kumar
%A Kumar S. Raja
%A Chiranjit Mukhopadhyay
%A T.V. Ramachandra
%J Information
%D 2012
%I MDPI AG
%R 10.3390/info3030420
%X Signals acquired by sensors in the real world are non-linear combinations, requiring non-linear mixture models to describe the resultant mixture spectra for the endmember¡¯s (pure pixel¡¯s) distribution. This communication discusses inferring class fraction through a novel hybrid mixture model (HMM). HMM is a three-step process, where the endmembers are first derived from the images themselves using the N-FINDR algorithm. These endmembers are used by the linear mixture model (LMM) in the second step that provides an abundance estimation in a linear fashion. Finally, the abundance values along with the training samples representing the actual ground proportions are fed into neural network based multi-layer perceptron (MLP) architecture as input to train the neurons. The neural output further refines the abundance estimates to account for the non-linear nature of the mixing classes of interest. HMM is first implemented and validated on simulated hyper spectral data of 200 bands and subsequently on real time MODIS data with a spatial resolution of 250 m. The results on computer simulated data show that the method gives acceptable results for unmixing pixels with an overall RMSE of 0.0089 ¡À 0.0022 with LMM and 0.0030 ¡À 0.0001 with the HMM when compared to actual class proportions. The unmixed MODIS images showed overall RMSE with HMM as 0.0191 ¡À 0.022 as compared to the LMM output considered alone that had an overall RMSE of 0.2005 ¡À 0.41, indicating that individual class abundances obtained from HMM are very close to the real observations.
%K mixture model
%K sub-pixel classification
%K non-linear unmixing
%K MODIS
%U http://www.mdpi.com/2078-2489/3/3/420