Real-Time Tracking of Multiple Articulated Structures in Multiple Views

Authors:
Tom Drummond;Roberto Cipolla
Affiliations:
-;-
Venue:
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Year:
2000

Citing 11
Cited 4

Efficient binary space partitions for hidden-surface removal and solid modeling

Discrete & Computational Geometry - Selected papers from the fifth annual ACM symposium on computational geometry, Saarbrücken, Germany, June 5-11, 1989
Fitting Parameterized Three-Dimensional Models to Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust model-based motion tracking through the integration of search and estimation

International Journal of Computer Vision
Tracking with Kalman snakes

Active vision
Tracking with rigid models

Active vision
Geometry from visual motion

Active vision
Pose refinement of active models using forces in 3D

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Nonrigid motion analysis: articulated and elastic motion

Computer Vision and Image Understanding
CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
Spatial Dependence in the Observation of Visual Contours

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
3D Articulated Models and Multi-View Tracking with Silhouettes

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2

Model-Based Silhouette Extraction for Accurate People Tracking

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Region-Based Pose Tracking

IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
A Geometric Approach to Joint 2D Region-Based Segmentation and 3D Pose Estimation Using a 3D Shape Prior

SIAM Journal on Imaging Sciences
An accelerated human motion tracking system based on voxel reconstruction under complex environments

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a highly flexible approach to real-time frame-rate tracking in complex camera and structures configurations, including the use of multiple cameras and the tracking of multiple or articulated targets. A powerful and general method is presented for expressing and solving the constraints which exist in these configurations in a principled manner. This method exploits the geometric structure present in the Lie group and Lie algebra formalism to express the constraints that derive from structures such as hinges or a common ground plane. This method makes use of the adjoint representation to simplify the constraints which are then applied by means of Lagrange multipliers.