Robust Visual Tracking via MCMC-based Particle Filter

Abstract : We present in this paper a new visual tracking framework based on the MCMC-based particle algorithm. Firstly, in order to obtain a more informative likelihood, we propose to combine the color- based observation model with a detection confidence density ob- tained from the Histograms of Oriented Gradients (HOG) descriptor. The MCMC-based particle algorithm is then employed to estimate the posterior distribution of the target state to solve the tracking prob- lem. The global system has been tested on different real datasets. Experimental results demonstrate the robustness of the proposed sys- tem in several difficult scenarios.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal-imt.archives-ouvertes.fr/hal-00685929
Contributor : François Septier <>
Submitted on : Friday, April 6, 2012 - 1:23:42 PM
Last modification on : Thursday, October 17, 2019 - 12:35:47 PM
Long-term archiving on : Saturday, July 7, 2012 - 2:35:16 AM

File

ICASSP12_VF.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00685929, version 1

Citation

D.N. Truong Cong, François Septier, Christelle Garnier, L. Khoudour, Yves Delignon. Robust Visual Tracking via MCMC-based Particle Filter. IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2012, Kyoto, Japan. ⟨hal-00685929⟩

Share

Metrics

Record views

371

Files downloads

528