Road scene analysis for determination of road traffic density

Abstract

Road traffic density has always been a concern in large cities around the world, and many approaches were developed to assist in solving congestions related to slow traffic flow. This work proposes a congestion rate estimation approach that relies on real-time video scenes of road traffic, and was implemented and evaluated on eight different hotspots covering 33 different urban roads. The approach relies on road scene morphology for estimation of vehicles average speed along with measuring the overall video scenes randomness acting as a frame texture analysis indicator. Experimental results shows the feasibility of the proposed approach in reliably estimating traffic density and in providing an early warning to drivers on road conditions, thereby mitigating the negative effect of slow traffic flow on their daily lives.

Keywords

road congestion / image texture / local binary pattern / scene morphology

References

[1] Villagra J, Milanes V, Perez J, Godoy J. Smooth path and speed planning for an automated public transport vehicle. Robotics and Autonomous Systems, 2012, 60: 252-26

[2] Towards a new culture for urban mobility. Green paper of European Commission, 2007, 1-6

[3] Hartgen D, Fields M G, Moore A. Gridlock and growth: the effect of trafflc congestion on regional economic performance. Reason Foundation, 2009, 1-8

[4] Schrank D, Lomax T, Eisele B. 2011 Urban Mobility Report and Appendices. Texas Transportation Institute, 2011

[5] Lomax T, Turner S, Shunk G, Levinson H S, Pratt R H, Bay P N, Douglas G B. Quantifying congestion. Transportation Research Board, 1997

[6] Pattara-Atikom M, Pongpaibool P, Thajchayapong S. Estimating road trafflc congestion using vehicle velocity. In: Proceedings of the 6th International Conference on ITS Telecommunications Proceedings. 2006, 1001-1004

[7] Oh J, Min J, Kim M, Cho H. Development of an automatic trafflc conflict detection system based an image tracking technology. Transportation Research Record, 2009, 45-54

[8] Cheng H Y, Hsu S H. Intelligent highway trafflc surveillance with self-diagnosis abilities. IEEE Transactions on Intelligent Transportation Systems, 2011, 12: 1462-1472

[9] Houben Q, Diaz J C T, Warzee N, Debeir O, Czyz J, Insticc. Multifeature stereo vision system for road trafflc analysis. In: Proceedings of the 4th International Conference on Computer Vision Theory and Applications. 2009, 554-559

[10] Bishop B, Casabona J. Automatic congestion detection and visualization using networked GPS unit data. In: Proceedings of the 47th Annual Southeast Regional Conference. 2009, 79

[11] Ozkurt C, Camci F. Automatic trafflc density estimation and vehicle classification for trafflc surveillance systems using neural networks. Mathematical & Computational Applications, 2009, 14: 187-196

[12] Jain V, Sharma A, Subramanian L. Road trafflc congestion in the developing world. In: Proceedings of the 2nd ACM Symposium on Computing for Development. 2012, 11

[13] Chen Y L, Wu B F, Huang H Y, Fan C J. A real-time vision system for nighttime vehicle detection and trafflc surveillance. IEEE Transactions on Industrial Electronics, 2011, 58: 2030-2044

[14] Yu Z, Chen Y P. A real-time motion detection algorithm for trafflc monitoring systems based on consecutive temporal difference. In: Proceedings of the 7th Asian Control Conference. 2009, 1594-1599

[15] Marfia G, Roccetti M. Vehicular congestion detection and short-term forecasting: a new model with results. IEEE Transactions on Vehicular Technology, 2011, 60: 2936-2948

[16] Brahme Y B, Kulkarni P S. An implementation of moving object detection, tracking and counting objects for trafflc surveillance system. In: Proceedings of the 2011 International Conference on Computational Intelligence and Communication Networks. 2011, 143-148

[17] Buch N, Velastin S A, Orwell J. A review of computer vision techniques for the analysis of urban trafflc. IEEE Transactions on Intelligent Transportation Systems, 2011, 12: 920-939

[18] Al-Kadi O S. Combined statistical and model based texture features for improved image classification. In: Proceedings of the 4th International Conference on Advances in Medical, Signal and Information Processing. 2008, 1-4

[19] Al-Kadi O S. Supervised texture segmentation: a comparative study. In: Proceedings of the 2011 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies. 2012, 1-5

[20] Gonzales R C, Woods R E. Digital Image Processing. Prentice Hall, 2002, 299-300

[21] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24: 971-987

[22] Guo Y, Zhao G, Pietik M. Discriminative features for texture description. Pattern Recognition, 2012, 45: 3834-3843

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg