Colloquium Computer Science, Dr. Alessia Saggese (University Salerno, Italy)

Title : ‘ Intelligent Video Surveillance: From Trajectories to Behaviors ’

Abstract:

In the last decades we have assisted to a growing need for security and to a consequent proliferation of cameras spread over the territory. This phenomenon has lead the scientific community in the investigation of those intelligent surveillance solutions, able to bridge the gap between their low-level representation in terms of pixels, and the high-level, natural language description that a human would give about them.

In order to achieve this task, it is required to automatically analyze the video so as to detect persons moving in the scene, extract their trajectories even in case a person is partially or completely occluded by another person moving in the scene. Given the trajectories, it is required to store them so as to allow the human operator to submit complex queries involving geometric and temporal data, as well as semantic one. Furthermore, each object trajectory needs to be properly analyzed in real time in order to interpret the behavior and to understand if it refers to an abnormal one. In this talk we will show how challenging are these tasks and how it has been possible face with them.

The author

Alessia Saggese is an Assistant Professor of the University of Salerno (Italy). She received her sandwich Ph.D. degree in electronic and computer engineering from the University of Salerno and the University of Caen, Basse Normandie (France). Her Ph.D. thesis has been awarded by Italo-French University (UIF) within the Project Vinci Framework and by the GIRPR, the Italian chapter of the IAPR, with a best thesis award. Her research mainly interests computer vision and pattern recognition techniques for video and audio surveillance applications.

Colloquium coordinators are Prof.dr. M. Aiello (e-mail : M.Aiello rug.nl ) and
Prof.dr. M. Biehl (e-mail: M.Biehl rug.nl )

http://www.rug.nl/research/jbi/news/colloquia/computerscience