An algorithm for detection of vehicles that stop in restricted areas, e.g. excluded by traffic rules, is proposed. Classic approaches based on object tracking are inefficient in high traffic scenes because of tracking errors caused by frequent object merging and splitting. The proposed algorithm uses the background subtraction results for detection of moving objects, then pixels belonging to moving objects are tested for stability. Large connected components of pixels that are stable within a sufficiently long period are extracted and compared with the detected moving objects. Therefore, detection of stationary objects which were previously moving is possible and if the object has stopped in a designated area, the event is declared. The algorithm was evaluated using a real traffic monitoring camera and performance of the algorithm is discussed. The algorithm may be used for automatic detection of potentially dangerous traffic events in video acquired from surveillance cameras.
Autorzy
Informacje dodatkowe
- Kategoria
- Aktywność konferencyjna
- Typ
- materiały konferencyjne indeksowane w Web of Science
- Język
- angielski
- Rok wydania
- 2014
