Multimodal Audio-Visual Recognition of Traffic Events
Kuba Łopatka, Józef Kotus, Maciej Szczodrak, Piotr Marcinkowski, Adam Korzeniewski, Andrzej Czyżewski · 2011
A demonstrator of traffic events detector based on the multimodal analysis of audio and video signals is described. The subsystem is a part of smart surveillance applications. It uses surveillance cameras and microphones as the data source. The algorithms employed to the analysis of data - sound event recognition and video analytics, are explained. Results of the multimodal analysis of recordings of dangerous and passive traffic situations are presented and discussed.