An infrared small target detection method based on nonnegative matrix factorization and compressed sensing

摘要

According to the low rank property of the background and the sparse features of the target in infrared image, a novel infrared small target detection method based on the nonnegative matrix factorization (NMF) and compressed sensing technology was presented in this paper. This method trained background model through NMF, and then sampled the infrared image sequences directly using the block compressed sensing technology. Through the alternating direction method of multipliers (ADMM), the infrared small target was extracted and the background was recovered from the image. At the same time, the background was updated by the update algorithm, to adapt to the changes in the background. The simulation results show that the proposed method can detect the infrared target precisely and efficiently.