We show how to recover the position and orientation of a pair of known
coplanar conics from a single perspective image. We describe and comp
are a number of methods for determining this relationship. One uses a
simple four point back projection model, and the other utilizes transf
ormation invariants. These results can be extended in a number of ways
. Firstly, they can be applied to arbitrary plane curves using an inva
riant fitting technique. Secondly, the recovery methods are applicable
to higher order algebraic curves. We show examples of pose determinat
ion for both synthetic data and real images of conic and non-conic obj
ects. For example, we recognize and determine pose for a gasket contai
ning non-conic curves. We assess the methods for stability and for acc
uracy against an accepted standard-Tsai's calibration method1. We conc
lude that using such methods enables accurate pose determination for a
rbitrary plane curves.