Dual-discriminator conditional generative adversarial network optimized with hybrid manta ray foraging optimization and volcano eruption algorithm for hyperspectral anomaly detection

Abstract

A significant task on remote sensing field is anomaly detection in hyperspectral images (HSI). Many scientists have created several relevant techniques developing deep network-based ways for hyperspectral anomaly detection (HAD) in the recent years. Dual-discriminator conditional generative adversarial network (DcGAN) optimized with hybrid Manta ray foraging optimization algorithm and Volcano eruption algorithm (Hyb-MRF-VEA) is proposed for anomaly identification in Hyperspectral images (DcGAN-HAD) in this manuscript. The three steps of the proposed methodology are data preparation, reconstruction, and detection. Background purification is a stage in the data preparation process that trains the deep network unsupervised. In the reconstruction step, DcGAN method is executed in spatial, spectral, combined spectral-spatial domains. The novelty of DcGAN method is to produce the hyper spectral images (HSIs) that are closer to real ones. Among original and image pixels the reconstruction error map (REM) is computed. The pixel weights are obtained with respect to REM at the detection step. Finally, to obtain the final detection map, the original with reconstructed image is subject to spatial and spectral joint anomaly detector. For scaling the optimal parameters and make sure exact detection, DcGAN approach not exposes any optimization techniques adoption. Therefore, in this work, a Hyb-MRF-VEA with optimize DcGAN weight parameters. The proposed DcGAN-HAD system is done in PyTorch and its efficacy is calculated with certain performances metrics, like, area under ROC curve (AUC) metric, precision, computation time, accuracy. For hyper spectral remote sensing scenes dataset of PAVIA CENTER ANDUNIVERSITY, the proposed DcGAN-HAD method attains 22.15%, 58.97% and 34.29% higher accuracy compared with the existing methods.