Fire Detection in Compressed Video

Day - Time: 03 September 2018, h.15:00
Place: Area della Ricerca CNR di Pisa - Room: C-29
  • Behcet Ugur Toreyin (Informatics Institute at Istanbul Technical University, Turkey)

Davide Moroni


Early detection of fires is an important aspect of public safety. In the past decades, devices and systems are developed for volumetric sensing of fires using non-conventional techniques, like computer vision based methods and pyro-electric infrared sensors. These systems pose an alternative for the commonly used point detectors which are suffering from transport delay in large and open areas.

Ubiquity of computing promises an increase in the number of deployments of such systems. Existing video based methods are developed for the analysis of uncompressed spatio-temporal sequences. In order to respond the growing demand of such systems, techniques specifically aimed at analyzing compressed domain video streams should be developed for early fire detection purposes. In this talk, an attempt to further improve the current state-of-the-art methods for video fire detection will be presented. The method aims at detecting signs of flame and/or smoke existence in the compressed video domain.

In the second half the talk, an overview of projects carried out by the "Signal Processing for Computational Intelligence Group - SPACING" of Informatics Institute at Istanbul Technical University, Turkey, will be presented.