Robust multi-hypothesis 3D object pose tracking

Authors:
Georgios Chliveros;Maria Pateraki;Panos Trahanias
Affiliations:
Foundation for Research and Technology Hellas, Institute of Computer Science, Heraklion, Crete, Greece;Foundation for Research and Technology Hellas, Institute of Computer Science, Heraklion, Crete, Greece;Foundation for Research and Technology Hellas, Institute of Computer Science, Heraklion, Crete, Greece,Dept. of Computer Science, University of Crete, Heraklion, Greece
Venue:
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Year:
2013

Citing 11
Cited 0

Model-based object tracking in monocular image sequences of road traffic scenes

International Journal of Computer Vision
Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Real-Time Visual Tracking of Complex Structures

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stable Real-Time 3D Tracking Using Online and Offline Information

IEEE Transactions on Pattern Analysis and Machine Intelligence
Monocular model-based 3D tracking of rigid objects

Foundations and Trends® in Computer Graphics and Vision
Real-Time Camera Tracking Using Known 3D Models and a Particle Filter

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Object tracking: A survey

ACM Computing Surveys (CSUR)
Propagation of Pixel Hypotheses for Multiple Objects Tracking

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Sparse non-linear least squares optimization for geometric vision

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Robust 3D visual tracking using particle filtering on the special Euclidean group: A combined approach of keypoint and edge features

International Journal of Robotics Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper tackles the problem of 3D object pose tracking from monocular cameras. Data association is performed via a variant of the Iterative Closest Point algorithm, thus making it robust to noise and other artifacts. We re-initialise the hypothesis space based on the resulting re-projection error between hypothesised models and observed image objects. This is performed through a non-linear minimisation step after correspondences are found. The use of multi-hypotheses and correspondences refinement, lead to a robust framework. Experimental results with benchmark image sequences indicate the effectiveness of our framework.