Sequential particle swarm optimization for visual tracking
Xiaoqin Zhang, Weiming Hu, Steve Maybank et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2008
Visual tracking usually involves an optimization process for estimating the motion of an object from measured images in a video sequence. In this paper, a new evolutionary approach, PSO (particle swarm optimization), is adopted for visual tracking. Since the tracking process is a dynamic optimization problem which is simultaneously influenced by the object state and the time, we propose a sequential particle swarm optimization framework by incorporating the temporal continuity information into the traditional PSO algorithm. In addition, the parameters in PSO are changed adaptively according to the fitness values of particles and the predicted motion of the tracked object, leading to a favourable performance in tracking applications. Furthermore, we show theoretically that, in a Bayesian inference view, the sequential PSO framework is in essence a multilayer importance sampling based particle filter. Experimental results demonstrate that, compared with the state-of-the-art particle filter and its variation - the unscented particle filter, the proposed tracking algorithm is more robust and effective, especially when the object has an arbitrary motion or undergoes large appearance changes.
Cited by 169 works. doi:10.1109/cvpr.2008.4587512
Authors
References
- Particle swarm optimization
- A New Approach to Linear Filtering and Prediction Problems
- Snakes: Active contour models
- The particle swarm - explosion, stability, and convergence in a multidimensional complex space
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
- CONDENSATION—Conditional Density Propagation for Visual Tracking
- Kernel-based object tracking
- On sequential Monte Carlo sampling methods for Bayesian filtering
- W/sup 4/: real-time surveillance of people and their activities
- The estimation of the gradient of a density function, with applications in pattern recognition