Learning and Recognition of 3D Visual Objects in Real-Time

Quickly learning and recognising familiar objects seems almost automatic for humans, yet it remains a challenge for machines. This paper describes an integrated object recognition system including several novel algorithmic contributions using a SIFT feature appearance-based approach to rapidly learn incremental 3D representations of objects as aspect-graphs. A fast recognition scheme applying geometric and temporal constraints localizes and identifies the pose of 3D objects in a. video sequence. The system is robust to significant variation in scale, orientation, illumination, partial deformation, occlusion, focal blur and clutter and recognises objects at near real-time video rates.