Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 19, Issue 7, Pages 1890-1907Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2010.2045034
Keywords
Conditional random field (CRF); contextual information; hyperpectral image classification; multinomial logistic regression (MLR); piecewise training
Funding
- Natural Science Foundation of China [60902088]
- NUDT
- Innovation Fund of Hunan Province
- NDTF Project of the ATR Laboratory [9140C8004011005]
Ask authors/readers for more resources
Hyperspectral images exhibit strong dependencies across spatial and spectral neighbors, which have been proved to be very useful for hyperspectral image classification. State-of-the-art hyperspectral image classification algorithms use the dependencies in a heuristic way or in probabilistic frameworks but impose unreasonable assumptions on observed data. In this paper, we formulate a conditional random field (CRF) to replace such heuristics and unreasonable assumptions for the classification of hyperspectral images. Moreover, because of avoiding explicit modeling of the observed data, the proposed method can incorporate the classification of hyperspectral images with different statistics characteristics into a unified probabilistic framework. Since the usual classification task for hyperspectral images needs the proposed CRF to be trained on local samples, available global training methods cannot be directly used. Under piecewise training framework, this paper develops an efficient local method to train the CRF. It is efficiently implemented through separated trainings of simple classifiers defined by corresponding potentials. However, the independent classifier trainings may lead to over-counting problems during inference. So we further propose a strategy to combine the independently trained models to obtain final CRF model. Experiments on real-world hyperspectral data show that our algorithm is competitive with the most recent results in hyperspectral image classification.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available