Design of tracking system based on mean-shift and Kalman filter

Hao Zhang; Jingxin Hong; Wu Lin; Lin Li

doi:10.1117/12.832551

30 October 2009 Design of tracking system based on mean-shift and Kalman filter

Hao Zhang, Jingxin Hong, Wu Lin, Lin Li

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953D (2009) https://doi.org/10.1117/12.832551
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

This paper presents a set of real-time tracking system based on mean-shift and Kalman filter. The proposed system is composed of two major modules. The host computer adopts tracking algorithm combining mean-shift with Kalman filter to achieve the implementation of object tracking. The improvement of the proposed algorithm is that when the moving vessels are largely occluded, the Kalman filter is updated by velocity vector which is estimated according to target locations in the prior frames, and then the filter is exploited to implement tracking alone. The algorithm achieves good tracking effect. The lower computer is a set of motion control system, consisting of high-performance camera and numerical control PTZ (Pan/Tilt/Zoom). It could manipulate PTZ to track motive object simultaneously according to the results from PC real-time tracking. Experimental results show that the system can implement marine moving object tracking with good real-time performance and robustness.

Citation Download Citation

Hao Zhang, Jingxin Hong, Wu Lin, and Lin Li "Design of tracking system based on mean-shift and Kalman filter", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953D (30 October 2009); https://doi.org/10.1117/12.832551

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