Sea ice classificaiton from hyperspectral images based on
self-paced boost learning
Submitted to IGARSS 2018
Dong Wang, Feng Gao, Junyu Dong, Shengke Wang
Last modified: 2018/1/15
Hyperspectral imagery has evident advantages for sea ice
classification due to enormous spectral bands. In this paper,
we proposed a novel sea ice classification framework from hyperspectral image based on self-paced boost learning (SPBL).
First, the criterion of linear prediction error is used for unsupervised band selection. Then, local binary pattern (LBP) features are extracted from the selected bands. Finally, SPBL is
employed as the classifier to provide probability outputs using
the extracted features. The proposed framework can capture
the intrinsic inter-class discriminative models while ensuring
the reliability of the samples involved in learning. The experimental results in real-world dataset demonstrate that the proposed framework is superior to several closely related methods
[ MATLAB code ]
The demo has not been well organized. Please contact me if you meet any problems.
Links to most related works
- M. Gong, M. Zhang, Y. Yuan, ※Unsupervised band selection based on evolutionary multobjective optimization for hyperspectral images,§ IEEE Trans. Geosci. Remote Sens., vol. 54, no. 1, pp. 544每557, 2016.
- W. Li and Q. Du, ※Gabor-filtering based nearest regularized subspace for hyperspectral image classification,§ IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 7, no. 4, pp. 1012每1022, 2014.
- W. Li et al., ※Local binary patterns and extreme learning machine for hyperspectral imagery classification,§ IEEE Trans. Geosci. Remote Sens., vol. 53, no. 7, pp. 3681每3693, 2015.
- Q. Zhao et al. ※Self-paced learning for matrix factorization,§ AAAI Conference on Aritificial Intelligence, pp. 3196每3202, 2015.
- T. Pi et al., ※Self-paced boost learning for classification,§ International Joint Conference on Artificial Intelligence, pp. 1932每1938, 2016
>>   return to Feng Gao's homepage
Last modified: 2018/1/15.