Multi-spectral remote sensing land-cover classification based on deep learning methods

It is of great significance and practical application value to extract land-cover type accurately. However, the input data usually used in classification such as reflectance data or vegetation index are very simple and quantitative remote sensing products are rarely used. In this paper, a multi-spectral land-cover classification method based on deep learning is proposed. Using the excellent detail capture ability of contourlet transform to obtain the potential information to supplement the spectral feature space, combined with deep learning for feature selection and feature extraction, a spectral-texture classification model is constructed. The multi-spectral sensing remote data and field measurement data in Dadukou District of Chongqing, northern Negev, and Changping region of Beijing were used for evaluation. Experiment results show the proposed method can outperform principal component analysis, linear discriminant analysis and neural network, and effectively improve the classification accuracy of multi-spectral images; this method provides a new perspective for land-use classification.

Automated summary

A multi-spectral land-cover classification method based on deep learning is proposed in this paper, using contourlet transform and deep learning to construct a spectral-texture classification model. Experimental results show the method can improve classification accuracy and provide a new perspective for land-use classification.