TY - GEN
T1 - Freeway Traffic Incident Detection from Cameras
T2 - 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018
AU - Chakraborty, Pranamesh
AU - Sharma, Anuj
AU - Hegde, Chinmay
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/7
Y1 - 2018/12/7
N2 - Early detection of incidents is a key step to reduce incident related congestion. State Department of Transportation (DoTs) usually install a large number of Close Circuit Television (CCTV) cameras in freeways for traffic surveillance. In this study, we used semi-supervised techniques to detect traffic incident trajectories from the cameras. Vehicle trajectories are identified from the cameras using state-of-the-art deep learning based You Look Only Once (YOLOv3) classifier and Simple Online Realtime Tracking (SORT) is used for vehicle tracking. Our proposed approach for trajectory classification is based on semi-supervised parameter estimation using maximum-likelihood (ML) estimation. The ML based Contrastive Pessimistic Likelihood Estimation (CPLE) attempts to identify incident trajectories from the normal trajectories. We compared the performance of CPLE algorithm to traditional semi-supervised techniques Self Learning and Label Spreading, and also to the classification based on the corresponding supervised algorithm. Results show that approximately 14% improvement in trajectory classification can be achieved using the proposed approach.
AB - Early detection of incidents is a key step to reduce incident related congestion. State Department of Transportation (DoTs) usually install a large number of Close Circuit Television (CCTV) cameras in freeways for traffic surveillance. In this study, we used semi-supervised techniques to detect traffic incident trajectories from the cameras. Vehicle trajectories are identified from the cameras using state-of-the-art deep learning based You Look Only Once (YOLOv3) classifier and Simple Online Realtime Tracking (SORT) is used for vehicle tracking. Our proposed approach for trajectory classification is based on semi-supervised parameter estimation using maximum-likelihood (ML) estimation. The ML based Contrastive Pessimistic Likelihood Estimation (CPLE) attempts to identify incident trajectories from the normal trajectories. We compared the performance of CPLE algorithm to traditional semi-supervised techniques Self Learning and Label Spreading, and also to the classification based on the corresponding supervised algorithm. Results show that approximately 14% improvement in trajectory classification can be achieved using the proposed approach.
KW - maximum likelihood estimation
KW - semi-supervised learning
KW - surveillance
KW - traffic incident detection
UR - http://www.scopus.com/inward/record.url?scp=85060442420&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060442420&partnerID=8YFLogxK
U2 - 10.1109/ITSC.2018.8569426
DO - 10.1109/ITSC.2018.8569426
M3 - Conference contribution
AN - SCOPUS:85060442420
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 1840
EP - 1845
BT - 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 November 2018 through 7 November 2018
ER -