VANAHEIM Demonstration to be presented at ECCV2012.
European Conference on Computer Vision 2012

ECCV 2012 solicits for Technical Demonstrations that will provide live evidence of innovative solutions in the field of Computer Vision and its applications, showing leading edge research in action. We are glad to communicate that VANAHEIM demonstration entitled "Unsupervised Activity Analysis and Monitoring algorithms for Effective Surveillance Systems" has been accepted to be presented at ECCV2012.

In this demonstration, we will show the different modules related to the automatic surveillance prototype developed in the context of the project. Several components will be demonstrated on real data from the Torino metro. First, different unsupervised activity modeling algorithms that capture recurrent activities from long recordings will be illustrated. A contrario, they provide unusuallness measures that can be used to select the most interesting streams to be displayed in control rooms. Second, different scene analysis algorithms will be demonstrated, ranging from left-luggage detection to the automatic identification of groups and their tracking. Third, a set of situationnal reporting methods (flow and count monitoring in escalators and at platforms as well as human presence at lift ) that provide a global view of the activity in the metro station and are displayed on maps or along with analyzed video streams. Finally, an offline activity discovery tool based on long term recordings. All algorithms are integrated into a Video Management Solution using an innovative VideoWall module that will be demonstrated as well.

The demonstrator will consist of a professional Video Management Solution, where all the analytics modules developed for the project have been integrated. The user of the system can easily launch any available algorithm, select the audio or video stream to use, and configure the graphical overlay (videowall) where to show the analytics’ results. Given that no live feed can be provided, algorithms will be applied (with online processing) on 26 real data streams pre-recorded from one of the metro stations in Torino.