End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing - Normandie Université Access content directly
Journal Articles Remote Sensing Year : 2022

End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

Mohamad Dhaini
Paul Honeine
Antonin van Exem
  • Function : Author


Hyperspectral Unmixing is the process of decomposing a mixed pixel into its pure materials (endmembers) and estimating their corresponding proportions (abundances). Although linear unmixing models are more common due to their simplicity and flexibility, they suffer from many limitations in real world scenes where interactions between pure materials exist, which paved the way for nonlinear methods to emerge. However, existing methods for nonlinear unmixing require prior knowledge or an assumption about the type of nonlinearity, which can affect the results. This paper introduces a nonlinear method with a novel deep convolutional autoencoder for blind unmixing. The proposed framework consists of a deep encoder of successive small size convolutional filters along with max pooling layers, and a decoder composed of successive 2D and 1D convolutional filters. The output of the decoder is formed of a linear part and an additive non-linear one. The network is trained using the mean squared error loss function. Several experiments were conducted to evaluate the performance of the proposed method using synthetic and real airborne data. Results show a better performance in terms of abundance and endmembers estimation compared to several existing methods.

Dates and versions

hal-03749095 , version 1 (10-08-2022)



Mohamad Dhaini, Maxime Berar, Paul Honeine, Antonin van Exem. End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing. Remote Sensing, 2022, 14 (14), pp.3341. ⟨10.3390/rs14143341⟩. ⟨hal-03749095⟩
30 View
0 Download



Gmail Facebook Twitter LinkedIn More