An architecture for a self configurable video supervision

Authors:

Abstract
In this paper, we propose a self configurable cognitive architecture for supervising video data in manufacturing environments. The architecture supports weakly supervised learning algorithms and self-adaptation strategies for analysis of visually observable procedures. The research proposed directly affects ease of deployment and minimises effort of operation of monitoring systems and is unique in the sense that it links object learning using low-level object descriptors and procedure learning with adaptation mechanisms and active camera network coordination. The architecture advocates a synergistic approach that combines largely unsupervised learning and model evolution in a bootstrapping process, while the application scenario is very complex taken from an automobile industry. Copyright 2008 ACM

This publication has 17 references indexed in Scilit: