An invariant and compact representation for unrestricted pose estimation

Authors:
Robert Söderberg;Klas Nordberg;Gösta Granlund
Affiliations:
Computer Vision Laboratory, Department of Electrical Engineering, Linköping University, Linköping;Computer Vision Laboratory, Department of Electrical Engineering, Linköping University, Linköping;Computer Vision Laboratory, Department of Electrical Engineering, Linköping University, Linköping
Venue:
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
Year:
2005

Citing 3
Cited 1

Local Grayvalue Invariants for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Unrestricted recognition of 3D objects for robotics using multilevel triplet invariants

AI Magazine

Comparison of local image descriptors for full 6 degree-of-freedom pose estimation

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a novel compact representation of local features called the tensor doublet. The representation generates a four dimensional feature vector which is significantly less complex than other approaches, such as Lowe's 128 dimensional feature vector. Despite its low dimensionality, we demonstrate here that the tensor doublet can be used for pose estimation, where the system is trained for an object and evaluated on images with cluttered background and occlusion.