Human 3D motion computation from a varying number of cameras

Authors:
Magnus Burenius;Josephine Sullivan;Stefan Carlsson;Kjartan Halvorsen
Affiliations:
KTH CSC/CVAP, Stockholm, Sweden;KTH CSC/CVAP, Stockholm, Sweden;KTH CSC/CVAP, Stockholm, Sweden;KTH CSC/CVAP, Stockholm, Sweden
Venue:
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Year:
2011

Citing 10
Cited 0

Shape and motion from image streams under orthography: a factorization method

International Journal of Computer Vision
On the convergence of interior-reflective Newton methods for nonlinear minimization subject to bounds

Mathematical Programming: Series A and B
Self-calibration of an affine camera from multiple views

International Journal of Computer Vision
Animating rotation with quaternion curves

SIGGRAPH '85 Proceedings of the 12th annual conference on Computer graphics and interactive techniques
Stochastic Tracking of 3D Human Figures Using 2D Image Motion

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Practical parameterization of rotations using the exponential map

Journal of Graphics Tools
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

International Journal of Computer Vision
View independent human body pose estimation from a single perspective image

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Monocular reconstruction of human motion by qualitative selection

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper focuses on how the accuracy of marker-less human motion capture is affected by the number of camera views used. Specifically, we compare the 3D reconstructions calculated from single and multiple cameras. We perform our experiments on data consisting of video from multiple cameras synchronized with ground truth 3D motion, obtained from a motion capture session with a professional footballer. The error is compared for the 3D reconstructions, of diverse motions, estimated using the manually located image joint positions from one, two or three cameras. We also present a new bundle adjustment procedure using regression splines to impose weak prior assumptions about human motion, temporal smoothness and joint angle limits, on the 3D reconstruction. The results show that even under close to ideal circumstances the monocular 3D reconstructions contain visual artifacts not present in the multiple view case, indicating accurate and efficient marker-less human motion capture requires multiple cameras.