In this paper, we propose a method for the detection of spatial points and
lines from a sequence of images. Our method does not require any predetermi
nation of point correspondences among images. With camera motion, a sequenc
e of images defines data in a spatiotemporal domain. In this domain, a traj
ectory of point correspondences among images defines a curve segment. For t
he detection of the curve segment in the spatiotemporal domain, we develop
a classification process for points in the spatiotemporal domain where the
camera motion is known. For the classification process, we adopt the voting
procedure which is the main concept underlying the Hough transform. (C) 20
01 Elsevier Science B.V. All rights reserved.