We present an approach for recovering surface shape from the occluding
contour using an active (i.e., moving) observer. It is based on a rel
ation between the geometries of a surface in a scene and its occluding
contour: If the viewing direction of the observer is along a principa
l direction for a surface point whose projection is on the contour, su
rface shape (i.e., curvature) at the surface point can be recovered fr
om the contour. Unlike previous approaches for recovering shape from t
he occluding contour, we use an observer that purposefully changes vie
wpoint in order to achieve a well-defined geometric relationship with
respect to a 3-D shape prior to its recognition. We show that there is
a simple and efficient viewing strategy that allows the observer to a
lign the viewing direction with one of the two principal directions fo
r a point on the surface. This strategy depends on only curvature meas
urements on the occluding contour and therefore demonstrates that reco
vering quantitative shape information from the contour does not requir
e knowledge of the velocities or accelerations of the observer. Experi
mental results demonstrate that our method can be easily implemented a
nd can provide reliable shape information from the occluding contour.