Author/Authors :
Alireza Asvadi Department of ECE - Babol (Noshirvani) University of Technology, Babol, Iran , Hami Mahdavinataj Department of ECE - Babol (Noshirvani) University of Technology, Babol, Iran , Mohammadreza Karami Department of ECE - Babol (Noshirvani) University of Technology, Babol, Iran , Yasser Baleghi Department of ECE - Babol (Noshirvani) University of Technology, Babol, Iran
كليدواژه :
incremental learning , 3D joint RGB histogram , color object tracking , Visual tracking
چكيده لاتين :
This paper presents an object tracking algorithm based on discriminative
3D joint RGB histograms of the object and surrounding background. Meanshift
algorithm on object confident map is used for localization. An incremental
color learning scheme with a forgetting factor is utilized to account for appearance
variation of the object. Experiments demonstrate the effectiveness of the
proposed tracking algorithm where the object undergoes variation in illumination
and color. Implemented in MATLAB, the proposed tracker runs at 25.7
frames per second.
