Towards 3D Object Model Acquisition and Recognition using 3D Affine Invariants

Sven Vinther, Roberto Cipolla
1993 Procedings of the British Machine Vision Conference 1993  
We evaluate the power of 3D affine invariants in an object recognition scheme. These invariants are actively calculated by the real-time tracking of 2D image features (corners) over an image sequence. This is done optimally by using a Kalman filter. Object information is located in a hash table where it is stored and retrieved using the invariants as stable indices. Recognition takes place when significant evidence for a particular shape has been found from the table. Preliminary results with
more » ... al data are presented, and some of the noise problems arising due to the weak perspective approximation and corner localisation errors are discussed.
doi:10.5244/c.7.37 dblp:conf/bmvc/VintherC93 fatcat:qaqcgytraraxhgqvywgpgaixne