Search

The ignorance of the spatial structure of subpixel is one of the factors that influence the accuracy of hyperspectral subpixel mapping. In order to effectively solve this problem, a subpixel mapping algorithm is proposed that based on linear feature detection in mixed pixels. Firstly, the mixed pixels of typical linear feature classes are determined by spectral unmixing. Then, based on the maximum linear index method of the complete straight-line set, the linear features of remaining mixed pixels are determined. The template matching method is used in conjunction with the pixel attraction to determine the classes of linear subpixels. Finally, the subpixel categories of the remaining mixed pixels are iteratively determined based on the linear optimization method. The experimental results of real data and simulation data show that the proposed method can effectively improve the precision of subpixel mapping.

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to design an unsupervised feature learning network for hyperspectral classification. Experiments have proved that our two proposed autoencoder networks have good feature learning capabilities by themselves, and the contrastive learning network we designed can better combine the features of the two to learn more representative features. As a result, our method surpasses other comparison methods in the hyperspectral classification experiments, including some supervised methods. Moreover, our method maintains a fast feature extraction speed than baseline methods. In addition, our method reduces the requirements for huge computing resources, separates feature extraction and contrastive learning, and allows more researchers to conduct research and experiments on unsupervised contrastive learning.