Visual Tracking by Particle Filtering
Séverine Dubuisson · 2015
This introductory chapter gives a brief overview of the progress made over the last 20 years in visual tracking by particle filtering. It presents the theoretical elements necessary for understanding particle filtering. Thus, it introduces recursive Bayesian filtering, before giving the outline of particle filtering. The chapter explains how particle filtering is used in visual tracking in video sequences and also presents certain limits of particle filtering. It also presents the elements fundamental to the introduction and the definition of sequential Monte-Carlo methods, as well as their use in the context of tracking in video sequences. Toward the end, it specifies the scientific position and the methodological axes that allow a part of these problems to be solved. Finally, the chapter gives the state of the main large families of approaches that are concerned with managing large-sized state and/or observation spaces in particle filtering.