OUTLIER - Online and Unattended Learning for Implicit Event Recognition

  • Hirzer, Martin (Co-Investigator (CoI))
  • Schulter, Samuel (Co-Investigator (CoI))
  • Bischof, Horst (Principal Investigator (PI))
  • Safariazaralamdari, Amirreza (Co-Investigator (CoI))
  • Zeisl, Bernhard (Co-Investigator (CoI))

Project: Research project

Project Details


The ever increasing number of cameras in surveillance system requires automatic video analysis in order to spot critical situations and to alert the monitoring personnel in a timely manner. While most current approaches in this area aim for detecting a large number of specific events on a large set of complex application scenarios, the goal of this project is to go far beyond state of the art by developing novel online learning methods to detect unusual situations in a camera specific scenario.
We will exploit the huge amount of data available for a specific camera to reliably learn usual and unusual situations.

In particular the OUTLIER project will carry out basic research in the following areas:

- Novel methods for semi-supervised learning in huge amounts of unlabeled data

- Improved exemplar based learning methods for huge amounts of data

Special attention will be paid to avoid drifting and to optimize the sensitivity of learning methods.
These generic learning algorithms will be applied for the detection of unusual situations in public places and traffic scenarios. Typical examples are fog and smoke, wrong way driving, lost goods and accidents. Unlike other approaches we do not want to model these situations explicitly and individually, but we will resort to learning to discriminate the usual situation from the unusual one.
The research partners have dedicated roles in the work programme to achieve the basic and applied research goals. The industrial partner has excellent knowledge of the market, will provide user requirements and will test and evaluate the developments.
Effective start/end date1/07/0931/07/11


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.