Abstraction and generalization of 3D structure for recognition in large intra-class variation

Authors:
Gowri Somanath;Chandra Kambhamettu
Affiliations:
Video/Image Modeling and Synthesis Lab, Department of Computer and Information Sciences, University of Delaware, Newark, DE;Video/Image Modeling and Synthesis Lab, Department of Computer and Information Sciences, University of Delaware, Newark, DE
Venue:
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Year:
2010

Citing 10
Cited 0

The society of mind

The society of mind
Generating and generalizing models of visual objects

Artificial Intelligence
Similarity, typicality, and categorization

Similarity and analogical reasoning
Achieving Generalized Object Recognition through Reasoning about Association of Function to Structure

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Function-based generic recognition for multiple object categories

CVGIP: Image Understanding
Random Forests

Machine Learning
3D Model Retrieval with Spherical Harmonics and Moments

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
FOCUS: a generalized method for object discovery for robots that observe and interact with humans

Proceedings of the 1st ACM SIGCHI/SIGART conference on Human-robot interaction
Learning function-based object classification from 3D imagery

Computer Vision and Image Understanding
Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Humans have abstract models for object classes which helps recognize previously unseen instances, despite large intra-class variations. Also objects are grouped into classes based on their purpose. Studies in cognitive science show that humans maintain abstractions and certain specific features from the instances they observe. In this paper, we address the challenging task of creating a system which can learn such canonical models in a uniform manner for different classes. Using just a few examples the system creates a canonical model (COMPAS) per class, which is used to recognize classes with large intra-class variation (chairs, benches, sofas all belong to sitting class). We propose a robust representation and automatic scheme for abstraction and generalization. We quantitatively demonstrate improved recognition and classification accuracy over state-of-art 3D shape matching/classification method and discuss advantages over rule based systems.