Multimodal activity recognition in video documents

Intelligent Video Surveillance (IVS) systems are becoming more and more popular in security applications. The analysis and recognition of abnormal behavior in a video sequence has gradually drawn the attention in this field. The focus of this project is the contextual information, and how to model a context so that a system can automatically detect it in video documents. The context classification will be later useful for other tasks, such as the detection of abnormal events. The goal of this project is to design and develop a system for context modelling and classification of surveillance videos of crowd scenes.
Student: Dominic Lukas Wyler
Year: 2012



Website of the project

Project Information