Shared Features for Scalable Appearance-Based Object Recognition

Authors:
Erik Murphy-Chutorian;Jochen Triesch
Affiliations:
University of California, San Diego;University of California, San Diego
Venue:
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 11

Robust model-based scene interpretation by multilayered context information

Computer Vision and Image Understanding
Scalable representation for 3D object recognition using feature sharing and view clustering

Pattern Recognition
Toward humanoid manipulation in human-centred environments

Robotics and Autonomous Systems
Towards using multiple cues for robust object recognition

Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
An Integrated Method for Multiple Object Detection and Localization

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Recognition of objects of a living room of class through a pyramidal method

ICCOMP'08 Proceedings of the 12th WSEAS international conference on Computers
Short communication: Simultaneous place and object recognition using collaborative context information

Image and Vision Computing
Combining Harris interest points and the SIFT descriptor for fast scale-invariant object recognition

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Cue-based equivalence classes and incremental discrimination for multi-cue recognition of "Interactionable" objects

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Toward a unified probabilistic framework for object recognition and segmentation

ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Scalable representation and learning for 3d object recognition using shared feature-based view clustering

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a framework for learning object representations for fast recognition of a large number of different objects. Rather than learning and storing feature representationsseparately for each object, we create a finite set of representative features and share these features within and between different object models. In contrast to traditional recognition methods that scale linearly with the number of objects, the shared features can be exploited by bottom-up search algorithms which require a constant number of feature comparisons for any number of objects. We demonstrate the feasibility of this approach on a novel database of 50 everyday objects in cluttered real-world scenes. Using Gabor wavelet-response features extracted only at corner points, our system achieves good recognition results despite substantial occlusion and background clutter.