Title :
An improved visual tracking algorithm based on particle filter
Author :
Mo Li ; Zheyi Fan ; Zhiwen Liu
Author_Institution :
Sch. of Inf. & Electron., Beijing Inst. of Technol., Beijing, China
Abstract :
Aiming at the shortcomings of color histogram-based observation model in traditional particle filter, a DCT-based observation model is presented. To reduce the particle degeneration effectively, a proposal distribution based on PSO method is put forward which can make full use of the current measurement. Experimental results show that the proposed algorithm can achieve more accurate and robust tracking results.
Keywords :
discrete cosine transforms; image colour analysis; object tracking; particle filtering (numerical methods); particle swarm optimisation; statistical distributions; DCT-based observation; PSO method; color histogram-based observation model; discrete cosine transform; particle degeneration; particle filter; particle swarm optimization; proposal distribution; visual tracking algorithm; Discrete cosine transforms; Feature extraction; Image color analysis; Particle filters; Proposals; Target tracking; DCT transform; PSO; observation model; particle filter; proposal distribution; visual target tracking;
Conference_Titel :
TENCON 2013 - 2013 IEEE Region 10 Conference (31194)
Conference_Location :
Xi´an
Print_ISBN :
978-1-4799-2825-5
DOI :
10.1109/TENCON.2013.6718890
