Detection of missing aircrafts by spectral signature identification using hyperspectral images

Abstract

Hyperspectral imaging technology plays an important role in remote sensing applications. HSI is a procedure to collect and handle information across the electromagnetic spectrum. The objective of HSI is to achieve a spectrum for every pixel in the image, offering high spectral resolution. This gives an easy way of detection and understanding of components in the image. Target detection is the important issue in HSI processing. It is important to take into account of both spectral and spatial information such as spectral signature, texture feature to improve the performances. Two main approaches to Hyperspectral target detection are: anomaly detection techniques which detect the components which are different from the background and spectral signature techniques which identify the target by spectrum estimation. In this paper, new method which uses both spectral and spatial information, by using RX anomaly detection with some elements of the level set methods for shape analysis and power spectrum estimation is performed.