Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Traffic event detection from road surveillance videos based on fuzzy logic
AU - Mehboob, Fozia
AU - Abbas, Muhammad
AU - Jiang, Richard
PY - 2016/8/29
Y1 - 2016/8/29
N2 - This work is about the autonomous detection of a road traffic incident by exploiting road surveillance camera videos. Timely and autonomous detection of an incident is paramount for the reduction of traffic congestion so that countermeasures can be taken at the earliest. This paper presents a novel Fuzzy Logic based analysis framework and a video based traffic data extraction scheme to decide upon the right traffic conditions. The existing road traffic analysis approaches as reported in literature do not extract data from the road camera videos; rather they use already available data to validate their schemes. However, in the proposed approach a complete scheme is proposed which takes a raw road camera video and autonomously extracts the relevant data for the subsequent Fuzzy Logic based traffic analysis. To show the efficacy of the proposed scheme, unprocessed surveillance videos of both urban and motorway scenarios are used. The results indicate that the traffic flow and their statistics are adequately determined through the proper selection of membership functions and rule formulation. Owing to the use of fuzzy logic, our proposed framework is seen to be robust enough to reject the noisy data coming from surveillance videos.
AB - This work is about the autonomous detection of a road traffic incident by exploiting road surveillance camera videos. Timely and autonomous detection of an incident is paramount for the reduction of traffic congestion so that countermeasures can be taken at the earliest. This paper presents a novel Fuzzy Logic based analysis framework and a video based traffic data extraction scheme to decide upon the right traffic conditions. The existing road traffic analysis approaches as reported in literature do not extract data from the road camera videos; rather they use already available data to validate their schemes. However, in the proposed approach a complete scheme is proposed which takes a raw road camera video and autonomously extracts the relevant data for the subsequent Fuzzy Logic based traffic analysis. To show the efficacy of the proposed scheme, unprocessed surveillance videos of both urban and motorway scenarios are used. The results indicate that the traffic flow and their statistics are adequately determined through the proper selection of membership functions and rule formulation. Owing to the use of fuzzy logic, our proposed framework is seen to be robust enough to reject the noisy data coming from surveillance videos.
KW - Background Subtraction
KW - Congestion detection
KW - Traffic Incident detection
U2 - 10.1109/SAI.2016.7555981
DO - 10.1109/SAI.2016.7555981
M3 - Conference contribution/Paper
AN - SCOPUS:84988896165
T3 - Proceedings of 2016 SAI Computing Conference, SAI 2016
SP - 188
EP - 194
BT - Proceedings of 2016 SAI Computing Conference, SAI 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 SAI Computing Conference, SAI 2016
Y2 - 13 July 2016 through 15 July 2016
ER -