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.
|Number of pages||4|
|State||Published - 1 Dec 2004|
|Event||2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings - Tel-Aviv, Israel|
Duration: 6 Sep 2004 → 7 Sep 2004
|Conference||2004 23rd IEEE Convention of Electrical and Electronics Engineers in Israel, Proceedings|
|Period||6/09/04 → 7/09/04|