30 October 2009 Design of tracking system based on mean-shift and Kalman filter
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953D (2009); doi: 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.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hao Zhang, Jingxin Hong, Wu Lin, 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); doi: 10.1117/12.832551; https://doi.org/10.1117/12.832551
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Filtering (signal processing)

Detection and tracking algorithms

Cameras

Control systems

RGB color model

Computing systems

Electronic filtering

Back to Top