Queuing theory guided intelligent traffic scheduling through video analysis using Dirichlet process mixture model

• Published in: Expert systems with applications 2019-03, Vol.118, p.169-181
• Main Authors: Kelathodi Kumaran, Santhosh, Prosad Dogra, Debi, Pratim Roy, Partha
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Computer vision; Dirichlet problem; Dirichlet process; Expert systems; Feature extraction; Highways; Machine learning; Management systems; Parameters; Predictions; Probabilistic models; Queues; Queuing theory; Regression analysis; Roads; Signal duration prediction; Signalling systems; Traffic control; Traffic intersection management; Traffic management; Traffic models; Traffic signals; Unsupervised learning; Video; Visual surveillance
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.09.057

•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. Intelligent traffic signaling is an important part of city road traffic management systems. In many countries, it is done through supervised/semi-supervised ways. With the advances in computer vision and machine learning, it is now possible to develop expert systems guided intelligent traffic signaling systems that are unsupervised in nature. In order to schedule traffic signals, it is essential to learn the traffic characterization parameters such as the number of vehicles, their arrival and departure rates, etc. In this work, we use unsupervised machine learning with the help of a modified Dirichlet Process Mixture Model (DPMM) to measure the aforementioned traffic parameters. This has been done using a new feature, named temporal clusters or tracklets extracted using DPMM. Detailed analysis on tracklet behavior during signal on/off period has been carried out to derive a queuing theory-based method for signal duration prediction. The queuing behavior at a junction is analyzed using tracklets for understanding their applicability. Queue clearance time at the junction has been used for predicting the signal duration with the help of Gaussian regression of historical data. Two publicly available video datasets, namely QMUL and MIT have been used for verification of the hypothesis. The mean absolute error (MAE) of the proposed method using tracklets has been reduced by a factor of 2.4 and 6.3 when compared with the tracks generated using Kernel Correlation Filters (KCF) and Kanade–Lucas–Tomasi (KLT), respectively. Through experiments, we are also able to establish that KCF and KLT tracks do not consider spatial occupancy of the vehicles on roads, leading to error in the estimation. The results reveal that the proposed queuing theory-based approach predicts the signal duration for the next cycle more accurately as compared to the ground truths. The method can be used for building intelligent traffic control systems for roadway junctions in cities and highways.