This paper presents a real-time Hough-based algorithm for straight line seg
ment extraction in complex multisensor images, which aims to avoid loss of
spatial information as well as to eliminate spurious peaks and reduce discr
etization errors. A parameter space representation able to take into accoun
t spatial information during the voting phase is proposed. This representat
ion allows the detection phase to be performed by focusing the algorithm on
particular locations of the parameter space. The search space is consequen
tly reduced, and a deeper decision strategy can be adopted, which takes int
o account the local distribution of segments along both a line and differen
t lines, for comparable directions and positions. Experimental results on a
large set of complex multisensor images (e.g. underwater images, low-light
outdoor images, SAR images, etc.) are presented. The main advantages of th
e proposed method over both feature and image-space methods are evaluated i
n terms of computational efficiency, detection accuracy and noise robustnes
s. (C) 2000 Academic Press.