Robust 3D Marker Localization Using Multi-spectrum Sequences

Authors:
Pengcheng Li;Jun Cheng;Ruifeng Yuan;Wenchuang Zhao
Affiliations:
Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences/The Chinese University of Hong Kong, Shenzhen, China 518055;Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences/The Chinese University of Hong Kong, Shenzhen, China 518055;Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences/The Chinese University of Hong Kong, Shenzhen, China 518055;Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences/The Chinese University of Hong Kong, Shenzhen, China 518055
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Year:
2009

Citing 4
Cited 2

Computer vision for computer games

FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
A motion capture system using passive markers

VRCAI '04 Proceedings of the 2004 ACM SIGGRAPH international conference on Virtual Reality continuum and its applications in industry
Interactive control of physically-valid aerial motion: application to VR training system for gymnasts

Proceedings of the 2007 ACM symposium on Virtual reality software and technology
Real-time and marker-free 3D motion capture for home entertainment oriented applications

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I

Gray scale potential theory of sparse image

ICIC'11 Proceedings of the 7th international conference on Advanced Intelligent Computing
Constraint-based Correspondence Matching for Stereo-based Interactive Robotic Massage Machine

Journal of Intelligent and Robotic Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Robust 3D marker localization in different conditions is an open, challenging problem to stereovision systems. For years, many algorithms -- using monocular or multiple views; based on visible or infrared sequences -- have been proposed to solve this problem. But they all have limitations. In this paper, we propose a novel algorithm for robust 3D marker localization in different conditions, using synchronous visible and infrared (IR) spectrum sequences captured by binocular camera. The main difficulty of the proposed algorithm is how to accurately match the corresponding marked objects in multi-spectrum views. We propose to solve the matching problem by considering geometry constraints, context based features of special designed markers, 3D physical spacial constraints, and etc. Experimental results demonstrated the feasibility of the proposed algorithm.