An infinite Gaussian mixture model with its application in hyperspectral unmixing

Spectral unmixing is a critical issue in multi-spectral data processing, which has the ability to identify the constituent components of a pixel. Most of the hyperspectral unmixing current methods are based on Linear Mixture Model (LMM) and have been widely used in many scenarios. However, both the noise contained in the LMM and the requirement of essential prior knowledge strongly limit their practical applications. In order to address these issues, this paper proposes an iterative approach named CBIGMM. It utilizes infinite Gaussian mixture model to describe the hyperspectral data, which is robust to the noise due to the intrinsic randomness of the Gaussian components; and extracts the endmembers and their corresponding abundance in a fully unsupervised way without prior knowledge. A set of experiment is conducted on both synthetic and real data set from pesticide-contaminated vegetables. The results and analyses show CBIGMM outperforms other methods in addressing hyperspectral unmixing problem.