A tracking technology of feature point's fuzzy clustering algorithm based on image stabilization

Dan-dan Qu; Yue-jin Zhao; Bin Wang; Mei Hui

doi:10.1117/12.807611

2 February 2009 A tracking technology of feature point's fuzzy clustering algorithm based on image stabilization

Dan-dan Qu, Yue-jin Zhao, Bin Wang, Mei Hui

Proceedings Volume 7157, 2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications; 715718 (2009) https://doi.org/10.1117/12.807611
Event: International Conference of Optical Instrument and Technology, 2008, Beijing, China

Abstract

Object tracking technology combined with image stabilization is called tracking technology based on image stabilization. Moving objects affect stabilization compensation in tracking algorithm based on image stabilization. The middle value method, former background method and dynamic clustering method are not useful for rotate or non-rigid objects. Fuzzy Clustering of feature points is proposed to solve these problems. First background and objectives membership value of the pixel are calculated, and then pixels are classified to background and target categories accurately by defining membership threshold of the background and targets. Experimental results show that fuzzy clustering algorithm resolves the moving target interference problem in image sequence and realizes steady tracking of object. It is proved to be more robust and less sensitive to the numbers of initial clustering.

Citation Download Citation

Dan-dan Qu, Yue-jin Zhao, Bin Wang, and Mei Hui "A tracking technology of feature point's fuzzy clustering algorithm based on image stabilization", Proc. SPIE 7157, 2008 International Conference on Optical Instruments and Technology: Advanced Sensor Technologies and Applications, 715718 (2 February 2009); https://doi.org/10.1117/12.807611

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available