%0 Conference Proceedings
%T Shared feature representations of LiDAR and optical images: Trading sparsity for semantic discrimination
%A M. Campos-Taberner
%A Adriana Romero
%A Carlo Gatta
%A Gustavo Camps-Valls
%B IEEE International Geoscience and Remote Sensing Symposium IGARSS2015
%D 2015
%F M. Campos-Taberner2015
%O LAMP; 600.079;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2724), last updated on Thu, 12 May 2016 15:46:05 +0200
%X This paper studies the level of complementary information conveyed by extremely high resolution LiDAR and optical images. We pursue this goal following an indirect approach via unsupervised spatial-spectral feature extraction. We used a recently presented unsupervised convolutional neural network trained to enforce both population and lifetime spar-sity in the feature representation. We derived independent and joint feature representations, and analyzed the sparsity scores and the discriminative power. Interestingly, the obtained results revealed that the RGB+LiDAR representation is no longer sparse, and the derived basis functions merge color and elevation yielding a set of more expressive colored edge filters. The joint feature representation is also more discriminative when used for clustering and topological data visualization.
%U http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7303999
%U http://dx.doi.org/10.1109/IGARSS.2015.7326744
%P 4169-4172