Hyperspectral Image Classification Based on Belief Propagation with Multi-features and Small Sample Learning
- 7 Downloads
In order to solve the “massive information but low accuracy” problem of hyperspectral image (HSI) classification, a novel HSI classification method MFSSL-BPMRF based on belief propagation (BP) Markov random field (MRF) using multi-features and small sample learning (MFSSL) is proposed in this paper. Firstly, an extended morphological multi-attributes profiles algorithm is used to extract spatial information of HSI, and a spatial–spectral multi-features fusion model is established to improve classification results. Then, BPMRF is used for image segmentation and classification because of its superiority in the spatial–spectral combination classification. MRF can describe the spatial distribution features of ground objects based on neighborhood model, and the spectral information of pixels can be integrated into the calculation of conditional probability. BP is used to learn the marginal probability distributions from the multi-features fusion information. Finally, the small sample training set is selected to enhance the computational efficiency. In the experiments of several hyperspectral images, the proposed method provides higher classification accuracy than other methods, and it is efficient for the classification with limited labeled training samples.
KeywordsHyperspectral image Classification Features fusion Belief propagation
This work is supported by National Natural Science Foundation of China (Grant No. 61461003).
- Hu, J., Tan, K., & Wu, L. (2015). An improved hyperspectral image classification algorithm based on multinomial logistic regression. Remote Sensing Technology & Application, 30(1), 135–139.Google Scholar
- Li, J., Bioucas-Dias, J. M., & Plaza, A. (2010). Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Transactions on Geoscience and Remote Sensing, 48(11), 4085–4098.Google Scholar
- Rui, B., Junshi, X., Zhaohui, X., et al. (2016). Ensemble classification for hyperspectral imagery based on morphological attribute profiles. Remote Sensing Technology and Application, 31(4), 731–738.Google Scholar
- Zhou, Q., Zhang, C., & Zhang, Y. (2015). Relationship between the number of labeled samples and classification accuracy based on sparse representation. Proceedings of Science, 1, 97–103.Google Scholar