Lagorio, Andrea and Grosso, Enrico and Tistarelli, Massimo (2008) Automatic detection of adverse weather conditions in traffic scenes. In: 5th IEEE International Conference on Advanced Video and Signal based Surveillance, 1-3 September 2008, Santa Fe, New Mexico. Los Alamitos, IEEE Computer Society. p. 273-279. ISBN 978-0-7695-3341-4. Conference or Workshop Item.
Visual surveillance in outdoor environments requiresthe monitoring of both objects and events. The analysis isgenerally driven by the target application which, in turn,determines the set of relevant events and objects to beanalyzed. In this paper we concentrate on the analysis ofoutdoor scenes, in particular for vehicle traffic control. Inthis scenario, the analysis of weather conditions isconsidered to signal particular and potentially dangeroussituations like the presence of snow, fog, or heavy rain.The developed system uses a statistical framework basedon the mixture of Gaussians to identify changes both in thespatial and temporal frequencies which characterizespecific meteorological events. Several experimentsperformed on standard databases and real scenesdemonstrate the applicability of the proposed approach.
I documenti depositati in UnissResearch sono protetti dalle leggi che regolano il diritto d'autore
Repository Staff Only: item control page