In recent years there have been changes in the way cars are designed. Car manufactures put a lot of effort on safety and systems that provide information to the driver with the long-term objective of achieve a complete self-driving car. Nowadays the most effective approach relies on data fusion of information, coming from a plethora of different sensors like RADARs and videocameras. While some of these sensors are already available on commercial cars, others will be introduced step-by-step. Therefore, data fusion algorithms should address the possibility to manage duplicated information and using this redundant information to validate the received data. In this work we describe two near-real time algorithms which exploit the video stream acquired by on-board camera. One allows for the identification of traffic light status and the second one addresses vehicles tracking and plate recognition.

Video processing for V2V communications: A case study with traffic lights and plate recognition / Russo, G.; Baccaglini, Enrico; Boulard, LUCA MATTEO; Brevi, D.; Scopigno, Riccardo. - (2015), pp. 144-148. ((Intervento presentato al convegno 1st IEEE International Forum on Research and Technologies for Society and Industry, RTSI 2015 tenutosi a Torino, Italy nel 2015 [10.1109/RTSI.2015.7325064].

Video processing for V2V communications: A case study with traffic lights and plate recognition

BACCAGLINI, ENRICO;BOULARD, LUCA MATTEO;SCOPIGNO, RICCARDO
2015

Abstract

In recent years there have been changes in the way cars are designed. Car manufactures put a lot of effort on safety and systems that provide information to the driver with the long-term objective of achieve a complete self-driving car. Nowadays the most effective approach relies on data fusion of information, coming from a plethora of different sensors like RADARs and videocameras. While some of these sensors are already available on commercial cars, others will be introduced step-by-step. Therefore, data fusion algorithms should address the possibility to manage duplicated information and using this redundant information to validate the received data. In this work we describe two near-real time algorithms which exploit the video stream acquired by on-board camera. One allows for the identification of traffic light status and the second one addresses vehicles tracking and plate recognition.
9781467381666
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2644959
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo