Deep supervised learning for hyperspectral data classification through convolutional neural networks
Spectral observations along the spectrum in many narrow spectral bands through hyperspectral imaging provides valuable information towards material and object recognition, which can be consider as a classification task. Most of the existing studies and research efforts are following the conventional pattern recognition paradigm, which is based on the construction of complex handcrafted features. 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 results and quantitative validation on widely used datasets showcasing the potential of the developed approach for accurate hyperspectral data classification.
PDF
Indian Pines
Pavia University
Kennedy Space Center
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Hyperspectral Image Classification | Indian Pines | 2D-CNN | OA@15perclass | 57.72±1.90 | # 12 | |
| Hyperspectral Image Classification | Kennedy Space Center | 2D-CNN | OA@15perclass | 80.53±1.31 | # 10 | |
| Hyperspectral Image Classification | Pavia University | 2D-CNN | OA@15perclass | 77.53±1.50 | # 9 |
