P. Gros et al., USING LOCAL PLANAR GEOMETRIC INVARIANTS TO MATCH AND MODEL IMAGES OF LINE SEGMENTS, Computer vision and image understanding, 69(2), 1998, pp. 135-155
Image matching consists of finding features in different images that r
epresent the same feature of the observed scene. It is a basic process
in vision whenever several images are used. This paper describes a ma
tching algorithm for lines segments in two images, The key idea of the
algorithm is to assume that the apparent motion between the two image
s can be approximated by a planar geometric transformation (a similari
ty or an affine transformation) and to compute such an approximation,
Under such an assumption, local planar invariants related the kind of
transformation used as approximation, should have the same value in bo
th images. Such invariants are computed for simple segment configurati
ons in both images and matched according to their values. A global con
straint is added to ensure a global coherency between all the possible
matches: all the local matches must define approximately the same geo
metric transformation between the two images. These first matches are
verified and completed using a better and more global approximation of
the apparent motion by a planar homography and an estimate of the epi
polar geometry, If more than two images are considered, they are initi
ally matched pairwise; then global matches are deduced in a second ste
p. Finally, from a set of images representing different aspects of an
object, it is possible to compare them and to compute a model of each
aspect using the matching algorithm. This work uses in a new way many
elements already known in vision; some of the local planar invariants
used here were presented as quasi-invariants by Binford and studied by
Ben-Arie in his work on the peaking effect. The algorithm itself uses
other ideas coming from the geometric hashing and the Hough algorithm
s. Its main limitations come from the invariants used. They are really
stable when they are computed for a planar object or for many man-mad
e objects which contain many coplanar facets and elements. On the othe
r hand, the algorithm will probably fail when used with images of very
general polyhedrons. Its main advantages are that it still works even
if the images are noisy and the polyhedral approximation of the conto
urs is not exact, if the apparent motion between the images is not inf
initesimal, if they are several different motions in the scene, and if
the camera is uncalibrated and its motion unknown. The basic matching
algorithm is presented in Section 2, the verification and completion
stages in Section 3, the matching of several images is studied in Sect
ion 4 and the algorithm to model the different aspects of an object is
presented in Section 5. Results obtained with the different algorithm
s are shown in the corresponding sections. (C) 1998 Academic Press.