Demo for the proposed SSAL-SDP method, i.e., superpixel-based semisupervised active learning (SSAL) method with the density peak (DP) augmentation, for the hyperspectral image classification.

This set of files contains the Matlab code for the superpixel based semisupervised active learning (SSAL) with the density peak (DP) augmentation proposed in the following paper:

[1] C. Liu, J. Li and L. He, Superpixel-Based Semisupervised Active Learning for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.12, no.1, pp. 357-370, Jan. 2019.

The SLIC superpixel segmentation for hyperspectral images is implemented according to:

[2] Xiang Xu, Jun Li, Changshan Wu, Antonio Plaza,Regional clustering-based spatial preprocessing for hyperspectralunmixing. Remote Sensing of Environment,Vol.204, Pages 333-346, January 2018.

The compared method, i.e., SSAL-N is implemented following:

[3] I. Dopido, J. Li, P. R. Marpu, A. Plaza, J. M. Bioucas Dias and J. A. Benediktsson, Semisupervised Self-Learning for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, vol.51, no.7, pp.4032-4044, July 2013.

The Multinomial logistic regression (MLR) implimentation is by:

[4] J. Li, J. Bioucas-Dias and A. Plaza. Hyperspectral Image Segmentation Using a New Bayesian Approach with Active Learning, IEEE Transactions on Geoscience and Remote Sensing, vol. 49, no. 10, pp.3947-3960, October 2011.

The LBP is implemented by:

[5] J. Li, J. M. Bioucas-Dias and A. Plaza, Spectral¡§CSpatial Classification of Hyperspectral Data Using Loopy Belief Propagation and Active Learning, IEEE Transactions on Geoscience and Remote Sensing, vol. 51, no. 2, pp. 844-856, Feb. 2013.

If you use this demo, please cite these references --- [1][2][3][4][5] ---

For their BibTeX formats, please see --- Reference_ssal.bib ---

Any suggestions and comments are appreciated, and please send them to the authors: Chenying Liu ([email protected]) Jun Li ([email protected]) Lin He ([email protected])