Title :
A morphological approach to automatic mine detection problems
Author :
Banerji, Ashish ; Goutsias, John
Author_Institution :
Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
fDate :
10/1/1998 12:00:00 AM
Abstract :
We consider the problem of detecting mines and minelike targets imaged by multispectral sensors. We propose an algorithm, based on mathematical morphology (MM), that yields accurate detection results in moderately cluttered environments. For targets in heavily cluttered environments, a preprocessing step is employed, based on the maximum noise fraction (MNF) transform, in order to reduce the effect of clutter and enhance the presence of targets. The algorithm is simple, performs well, and requires only approximate knowledge of target size
Keywords :
clutter; covariance matrices; image reconstruction; image registration; image sequences; mathematical morphology; object detection; sensor fusion; accurate detection results; automatic mine detection problems; covariance matrices; data fusion; heavily cluttered environments; mathematical morphology; maximum noise fraction transform; minelike targets; moderately cluttered environments; morphological approach; morphological image reconstruction; multispectral optical sensors; preprocessing step; Image sensors; Landmine detection; Layout; Marine technology; Military computing; Object detection; Optical filters; Optical imaging; Optical sensors; Sea measurements;
Journal_Title :
Aerospace and Electronic Systems, IEEE Transactions on
