Road traffic congestion in the developing world

Road traffic jams continue to remain a major problem in most cities around the world, especially in developing regions resulting in massive delays, increased fuel wastage and monetary losses. Due to the poorly planned road networks, a common outcome in many developing regions is the presence of small critical areas which are common hot-spots for congestion; poor traffic management around these hotspots potentially results in elongated traffic jams. In this paper, we first present a simple automated image processing mechanism for detecting the congestion levels in road traffic by processing CCTV camera image feeds. Our algorithm is specifically designed for noisy traffic feeds with poor image quality. Based on live CCTV camera feeds from multiple traffic signals in Kenya and Brazil, we show evidence of this congestion collapse behavior lasting long time-periods across multiple locations. To partially alleviate this problem, we present a local de-congestion protocol that coordinates traffic signal behavior within a small area and can locally prevent congestion collapse sustaining time variant traffic bursts. Based on a simulation based analysis on simple network topologies, we show that our local de-congestion protocol can enhance road capacity and prevent congestion collapse in localized settings.

[1]  Hai Yang,et al.  Traffic assignment and signal control in saturated road networks , 1995 .

[2]  H Lieu,et al.  TRAFFIC-FLOW THEORY , 1999 .

[3]  Tsu Chin,et al.  California Partners for Advanced Transit and Highways (PATH) , 2004 .

[4]  Akinori Asahara,et al.  Macroscopic Structural Summarization of Road Networks for Mobile Traffic Information Services , 2006, 7th International Conference on Mobile Data Management (MDM'06).

[5]  Jae-Gil Lee,et al.  Traffic Density-Based Discovery of Hot Routes in Road Networks , 2007, SSTD.

[6]  Wayne A Sarasua,et al.  Real-Time Detection and Tracking of Vehicle Base Fronts for Measuring Traffic Counts and Speeds on Highways , 2007 .

[7]  Mario Gerla,et al.  LOUVRE: Landmark Overlays for Urban Vehicular Routing Environments , 2008, 2008 IEEE 68th Vehicular Technology Conference.

[8]  S. Dennis Using Pricing to Reduce Traffic Congestion , 2009 .

[9]  Mario Gerla,et al.  Histogram-based density discovery in establishing road connectivity , 2009, 2009 IEEE Vehicular Networking Conference (VNC).

[10]  Fabio Ricciato,et al.  Exploiting Cellular Networks for Road Traffic Estimation: A Survey and a Research Roadmap , 2009, VTC Spring 2009 - IEEE 69th Vehicular Technology Conference.

[11]  Celil Ozkurt,et al.  Automatic Traffic Density Estimation and Vehicle Classification for Traffic Surveillance Systems Using Neural Networks , 2009 .

[12]  Aditya Dhananjay,et al.  Traffic Density Estimation for Noisy Camera Sources , 2012 .