30 October 2009 Multifeature fusion tracking in a particle filter framework
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74954T (2009) https://doi.org/10.1117/12.833995
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Particle filtering has been proven very successful for non-gaussian and non-linear estimation problems. In this study we used the particle filtering technique with multiple features to track the moving object effectively in video image. The object tracking system relies on the deterministic search of window, whose color content matches a reference histogram model. A simple histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by PCA transform technique. Our observation system of particle filter uses the combination of color and PCA features with a likelihood measurement. Experiment results show that the algorithm can effectively handle the effect of illumination, and is stable and robust.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lizhi Pei, Lizhi Pei, Peng Zhang, Peng Zhang, Runsheng Wang, Runsheng Wang, } "Multifeature fusion tracking in a particle filter framework", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74954T (30 October 2009); doi: 10.1117/12.833995; https://doi.org/10.1117/12.833995

Back to Top