A Parallel Algorithm for Hyperspectral Target Detection Based on Weighted Alternating Direction Method of Multiplier

Target detection for hyperspectral images (HSIs) is one of the significant techniques in remote sensing data processing. Targets generally comprise various object categories with complex features and varying sizes. often used application scenarios which accurately efficiently acquiring results can be challenging. The development advanced target approaches becoming increasingly necessary both military civilian fields. This article proposes an alternating direction method multiplier (ADMM) based parallel approach detection. Different from existing methods performing solely on images, our performs fusion multispectral to leverage spectral spatial information prior. For each task or partition, processing computation load multiple computing nodes substantially reduce time. In addition, we introduce a novel weighted ADMM, takes influence different variables convergence into account, further enhance computational efficiency model. Experiments real-world HSI datasets demonstrate that proposed not only produces more accurate than direct methods, but also achieves acceleration ratio compared serial flow.