Sparse autoencoder based feature learning for unmanned aerial vehicle landforms image classification

A new algorithm of unmanned aerial vehicle landforms image classification based on sparse autoencoder(SAE) is proposed in view of the drawbacks of single layer sparse autoencoder for feature learning that it is easy to lose the deep abstract feature and the feature lacks the robustness. In this paper, first, by constructing the deep sparse autoencoder, the image layer by layer learning and automatically extract each layer features. Then, in order to improve the feature representations, the each layer feature weights and the reorganized feature set are obtained according to the feature set weighting method. Finally, combining the strong global search ability of genetic algorithm (GA) and the excellent performance of support vector machine (SVM), the image classification is completed efficiently and accurately. The experimental results show that the proposed algorithm can automatically learn the deep feature of the image, and the reorganized feature has high discriminations image representations, which effectively improves the image classification accuracy.