|
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:
|
|
|
Full Contents:
|
click to dowload 
|
|
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. |
|
|
|
|
|
|
