Whilst the domains of electronics and micro-electronics saw much progress in the last three decades, the acquisition of video sequences became a task of increasing triviality. However, these advancements, which have given rise to rapid improvements in sensor quality and therefore image resolution, as well as increases in computer processing power and memory, have made it possible, perhaps essential, to analyze movement in addition to detecting it.
New algorithms have appeared whose purpose is to detect and follow movement in a video sequence. These “tracking algorithms” have many practical applications, notably in human–machine interaction, surveillance, medical and biomedical imagery and even interactive games. Object tracking in video, and the challenges that arise from this, have become an increasingly stronger area of focus in research every year.
In recent years, Monte-Carlo methods, also known as particle filters, have become the algorithm of choice for visual tracking. This book presents the various contributions in relation to managing large state and observation representation spaces, one of the major challenges of particle filtering. The author suggests several approaches to allow for better focusing within the state space and to thereby accelerate the process of tracking by particle filtering.
1. Visual Tracking by Particle Filtering.
2. Data Representation Models.
3. Tracking Models That Focus on the State Space.
4. Models of Tracking by Decomposition of the State Space.
5. Research Perspectives in Tracking and Managing Large Spaces.
Séverine Dubuisson is Assistant Professor in the Institute for Intelligent Systems and Robotics, at Pierre and Marie Curie University in Paris, France. Her research interests include tracking in video sequences, management of large state spaces and observation, analysis of the dynamics in video sequences and analysis and modeling of social interactions.
Table of Contents
PDF File 34 Kb