Automatically Tuning Background Subtraction Parameters using Particle Swarm Optimization

Computer Vision Techniques for Background Modeling in Urban Traffic Monitoring

“…Other measures for fitness quantification, in the context of background subtraction techniques, have been proposed in the literature (Rosin & Ioannidis, 2003;White & Shah, 2007;Ilyas et al, 2009). The following are some examples:…”

“…The optimal tuning of the parameter set in this algorithm is considered not to be a trivial issue. In White & Shah (2007), an automatic tuning strategy based on particle swarm optimization is proposed. Another set of algorithms lay in the category of non-parametric algorithms.…”

Subsequent Processing of Background Modeling for Traffic Surveillance System

“…Another measure for fitness quantification in the context of background subtraction is F-measure (Fm) [20]- [22] which combines precision and recall to provide more representative than PR and RC themselves.…”

Background Modeling via Incremental Maximum Margin Criterion

“…Indeed, it doesnt need to label data. Recently, White et al [1] proved that the Gaussian Mixture Model (GMM) [19] gives better results when some coefficients are determined in a supervised way. Following this idea, we propose to use a supervised subspace learning for background modeling.…”

“…Their main advantage is that it doesn't need to label data during the training and running phase. Recently, White et al [1] have shown that a supervised approach can improved significantly the robustness in background modeling. Following this idea, we propose to model the background via a supervised subspace learning called Incremental Maximum Margin Criterion (IMMC).…”