Target Detection in Hyperspectral Imagery Using Atmospheric-Spectral Modeling and Deep Learning

Target detection (TD) in spectral imagery is an evolving analytical perspective with broader application potential. The perceived distinctness of the spectral signatures of the materials of interest is exploited for detecting targets in hyperspectral imagery. Space-time varying atmospheric perturbances on the radiation reaching a remote sensor are major limitations for designing a successful TD framework. Incorporating atmospheric components into a TD framework is vital for practical applicability. Considered a general approach for flexibility, scalability, and optimal prediction, deep learning (DL) methods are increasingly used in various remote sensing applications. However, their potential for TD is relatively unexplored. Especially, the ability to provide training data sufficient for DL models and maintaining the functional relevance of the sparsely distributed targets in hyperspectral imagery are crucial for TD frameworks. This letter presents a novel method for the training of DL architecture, called deep spectral target detector (DSTD). The proposed method includes a semisupervised multiscenario forward radiative transfer modeling (RTM) for the simulation of spectral signatures of various targets as training data suitable for the functional requirements of a typical DL architecture. We implemented the DSTD on a TD application-specific benchmark AVIRIS-NG airborne hyperspectral imagery acquired over a study site near Ooty, India. Compared to the state-of-the-art statistical target detectors, the detection performance of the DSTD is superior to equivalent. Furthermore, RTM-based training yields a robust model, impervious to the atmospheric mismatches between target collection and TD environments, indicating the potential for a similar approach to develop efficient DL-based methods for TD in the future.