Probabilistic Collaborative Representation Based Ensemble Learning for Classification of Wetland Hyperspectral Imagery

Protection of wetlands is important for ecosystem in recent years, and the classification of wetland ground cover is the foundation of investigation and protection work. Probabilistic collaborative representation classifier (ProCRC) is one of the best performing classifiers, which has been applied in the hyperspectral image (HSI) classification. However, its performance is greatly limited for wetland data where spectrums are highly similar. Moreover, the complex distribution of ground objects in wetlands has not been wisely utilized in the classification. In this article, the intrinsic mechanism of ProCRC is found and its kernel version is proposed to solve the problems of wetland classification. Then, a new ensemble learning strategy that considers neighborhood information is proposed, which largely alleviates the problem of sample collection in wetlands. Under the guidance of this strategy, two specific ensemble learning algorithms, i.e., local neighborhood-based ensemble (LNE) and local neighborhood and samples augmentation-based ensemble (LNSAE), are proposed. The superiority of the proposed methods is validated using three typical HSI datasets of China coastal wetland with few samples.