Translator Disclaimer
6 December 2005 Robust tracking based on orientation code matching under irregular conditions
Author Affiliations +
Proceedings Volume 6051, Optomechatronic Machine Vision; 60510S (2005) https://doi.org/10.1117/12.645515
Event: Optomechatronic Technologies 2005, 2005, Sapporo, Japan
Abstract
Feature extraction and tracking are widely applied in the industrial world of today. It is still an important topic in Machine Vision. In this paper, we present a new feature extraction and tracking method which is robust against illumination change such as shading and highlighting, scaling and rotation of objects. The method is composed mainly of two algorithms: Entropy Filter and Orientation Code Matching (OCM). The Entropy Filter points up areas of images being messy distribution of orientation codes. The orientation code is determined by detecting the orientation of maximum intensity change around neighboring 8 pixels. It is defined as simply integral values. We can extract good features to track from the images by using the Entropy Filter. And then, the OCM, a template matching method using the orientation code, is applied to track the features each frame. We can track the features robustly against the illumination change by using the OCM. Moreover, updating these features (templates) each frame allows complicated motions of tracked objects such as scaling, rotation and so on. In this paper, we report the details of our algorithms and the evaluations of comparison with other well-known feature extraction and tracking methods. As an application example, planer landmarks and face tracking is tried. The results of them are also reported in context.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yukiyasu Domae, Shun'ichi Kaneko, and Takayuki Tanaka "Robust tracking based on orientation code matching under irregular conditions", Proc. SPIE 6051, Optomechatronic Machine Vision, 60510S (6 December 2005); https://doi.org/10.1117/12.645515
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top