Queuing theory guided intelligent traffic scheduling through video analysis using Dirichlet process mixture model
作者：
Highlights：
• Dirichlet Process Mixture Model guided unsupervised learning of temporal clusters.
• Representation of moving objects in the form of temporal clusters.
• Queuing theory guided unidirectional traffic flow modeling using temporal clusters.
• Automatic prediction of traffic signal duration in a unidirectional flow.
• Comparison with state-of-the-art tracking based features.
摘要
•Dirichlet Process Mixture Model guided unsupervised learning of temporal clusters.•Representation of moving objects in the form of temporal clusters.•Queuing theory guided unidirectional traffic flow modeling using temporal clusters.•Automatic prediction of traffic signal duration in a unidirectional flow.•Comparison with state-of-the-art tracking based features.
论文关键词：Traffic intersection management,Signal duration prediction,Dirichlet process,Queuing theory,Unsupervised learning,Visual surveillance
论文评审过程：Received 9 March 2018, Revised 13 July 2018, Accepted 30 September 2018, Available online 3 October 2018, Version of Record 12 October 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.09.057
