"Deep Supervised Learning For Hyperspectral Data Classification Through Convolutional Neural Networks"
Konstantinos Makantasis , Konstantinos Karantzalos , Anastasios Doulamis , Nikolaos Doulamis, International Geoscience and Remote Sensing Symposium 2015 (IGARSS 2015), 26th July 2015, Milan, Italy
Hyperspectral imaging is defined as the simultaneous acquisition of an image in many narrow spectral bands, providing this way valuable information towards material recognition, which can be viewed as a classification task. Towards this direction most of the existing work is following the conventional pattern recognition paradigm, which is based on complex handcrafted features construction. However, it is rarely known which features are important for the problem at hand. In contrast to these approaches, we propose a deep learning based classification method that hierarchically constructs high-level features in an automated way. Our method exploits a Convolutional Neural Network to encode pixels’ spectral and spatial information and a Multi-Layer Perceptron to conduct the classification task. Experimental evaluation of the proposed method on widely used datasets showcasing its potential for accurate hyperspectral data classification.
Read More: .pdf