VENUS: A System for Novelty Detection in Video Streams with Learning

Novelty detection in video is a rapidly developing application domain within computer vision. The motivation behind this paper is a learning based framework for detecting novelty within video. Since, humans have a general understanding about their environment and possess a sense of distinction between what is normal and abnormal about the environment based on our prior experience; any aspect of the scene that does not fit into this definition of normalcy tends to be labeled as a novel event. In this paper, we propose a computational learning based framework for novelty detection and provide the experimental evidence to describe the results obtained by this framework. To begin with the framework extracts low-level features from scenes, based on the focus of attention theory and then combines unsupervised learning techniques such as clustering with habituation theory to emulate the cognitive aspect of learning.

• Type: Conference
• Year: 2004
• Where: FLAIRS
• Authors: Roger S. Gaborski, Vishal S. Vaingankar, Vineet Chaoji, Ankur Teredesai
• Keywords: Artificial Intelligence, Computational Learning, FLAIRS 2004, Learning Based Framework, Unsupervised Learning Techniques