Affiliation:
1. School of Computer Science, China University of Geosciences, Wuhan 430078, China
2. Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan 430078, China
Abstract
Hyperspectral image (HSI) classification is a vital task in hyperspectral image processing and applications. Convolutional neural networks (CNN) are becoming an effective approach for categorizing hyperspectral remote sensing images as deep learning technology advances. However, traditional CNN usually uses a fixed kernel size, which limits the model’s capacity to acquire new features and affects the classification accuracy. Based on this, we developed a spectral segmentation-based multi-scale spatial feature extraction residual network (MFERN) for hyperspectral image classification. MFERN divides the input data into many non-overlapping sub-bands by spectral bands, extracts features in parallel using the multi-scale spatial feature extraction module MSFE, and adds global branches on top of this to obtain global information of the full spectral band of the image. Finally, the extracted features are fused and sent into the classifier. Our MSFE module has multiple branches with increasing ranges of the receptive field (RF), enabling multi-scale spatial information extraction at both fine- and coarse-grained levels. On the Indian Pines (IP), Salinas (SA), and Pavia University (PU) HSI datasets, we conducted extensive experiments. The experimental results show that our model has the best performance and robustness, and our proposed MFERN significantly outperforms other models in terms of classification accuracy, even with a small amount of training data.
Subject
General Earth and Planetary Sciences
Reference48 articles.
1. Hyperspectral image data analysis;Landgrebe;IEEE Signal Process. Mag.,2002
2. Hyperspectral image classification based on deep deconvolution network with skip architecture;Ma;IEEE Trans. Geosci. Remote Sens.,2018
3. Evaluation of deep learning CNN model for land use land cover classification and crop identification using hyperspectral remote sensing images;Bhosle;J. Indian Soc. Remote Sens.,2019
4. Yan, Z., Zhang, H., Piramuthu, R., Jagadeesh, V., DeCoste, D., Di, W., and Yu, Y. (2015, January 7–13). HD-CNN: Hierarchical deep convolutional neural networks for large scale visual recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.
5. Tongue coat information extraction of the Traditional Chinese Medicine with hyperspectral image;Liu;Guang Pu Xue Yu Guang Pu Fen Xi,2017