Digital Library

cab1

 
Title:      MARKER-LESS COMPUTER VISION TRACKING FOR AUGMENTED REALITY
Author(s):      W. T. Fong, S. K. Ong, A. Y. C. Nee
ISBN:      978-972-8939-22-9
Editors:      Yingcai Xiao, Tomaz Amon and Piet Kommers
Year:      2010
Edition:      Single
Keywords:      Computer vision tracking, illumination model, augmented reality, non-linear optimization
Type:      Full Paper
First Page:      85
Last Page:      92
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      A real time marker-less computer vision tracker designed for Augmented Reality is presented. It obtains accurate camera positions and orientations relative to well-patterned planar surfaces in real time, without the use of artificial markers. It relies on Efficient Second-order Minimization (ESM) of the pixel intensity errors over a large image region to perform frame-to-frame tracking. A sub-grid gradient-based reference image selection process and an illumination model are proposed to improve the robustness and efficiency of ESM tracking. The proposed illumination model allows ESM tracking to robustly handle shadows, glares, general ambient light changes and partial occlusion, while increasing the accuracy and processing speed. Evaluation using video sequences of tracking of real objects is presented. A feature-tracking component is added to automatically initialize and recover ESM tracking.
   

Social Media Links

Search

Login