Detection of large targets in noisy hyper-spectral images

Basing ourselves on a novel segmentation algorithm for hyper-spectral images (HSI), we have considered how to detect large targets (multi-pixel anomalous objects) in image cubes with a spectral component. In particular, we have developed several filters to compensate for speckle noise which may be present in the initial cube (and specifically in the target). We show that for speckle noise, a modification of our morphological technique allows us to detect targets without an enhanced false alarm result.