One of the main goals in the intelligent transportation system (ITS) field is to improve transport safety through the use of Information Technology. Recent advances in Computer Vision allow the urban environment under video surveillance to be modeled by means of the identification of a set of features of the vehicles and pedestrians involved in the scenario. At a higher level, this information can be processed to automatically detect dynamic events in video sequences, which will help the system to understand what is happening and launch an alarm in case of any dangerous behavior or incident may happen. Experimental results demonstrate the effectiveness of the proposed system, allowing a secure mobility of users.
Samenvatting