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

Authors:
Shihab Hamid;Bernhard Hengst
Affiliations:
School of Computer Science and Engineering, UNSW, Sydney, Australia and NICTA, Sydney, Australia;School of Computer Science and Engineering, UNSW, Sydney, Australia and ARC Centre of Excellence for Autonomous Systems, and NICTA, Sydney, Australia
Venue:
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Year:
2009

Citing 7
Cited 0

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Monocular model-based 3D tracking of rigid objects

Foundations and Trends® in Computer Graphics and Vision
Model generation for video-based object recognition

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Fast and cheap object recognition by linear combination of views

Proceedings of the 6th ACM international conference on Image and video retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.