Remote Vapor Detection and Classification Using Hyperspectral Images

摘要

Adaptive Infrared Imaging Spectroradiometer (AIRIS) is a longwave infrared (LWIR) sensor for remote detection ofchemical agents such as nerve gas. AIRIS can be considered as a hyperspectral imager with 20 bands. In this paper, wepresent a systematic and practical approach to detecting and classifying chemical vapor from a distance. Our approachinvolves the construction of a spectral signature library of different vapors, certain practical preprocessing procedures, andthe use of effective detection and classification algorithms. In particular, our preprocessing involves effective vaporsignature extraction with adaptive background subtraction and normalization, and vapor detection and classification usingSpectral Angle Mapper (SAM) technique, which is a signature-based target detection method for vapor detection. We haveconducted extensive vapor detection analyses on AIRIS data that include TEP and DMMP vapors with differentconcentrations collected at different distances and times of the day. We have observed promising detection results both inlow and high-concentrated vapor releases.