Abstract
With the rapid advancement of sensing technologies, it has been feasible to collect various types of traffic data such as traffic volume and travel times. Vision-based approach is one of the major scheme actively used for the automated traffic data collection, and continues to gain traction to a broader utilization. It collects video streams from cameras installed near roads, and processes the video streams frame by frame using image processing algorithms. The widely used algorithms include vehicle detection and vehicle tracking which recognize every vehicle in the camera view and track it in the consecutive frames. Vehicle counts and speed can be estimated from the detection and tracking results. Continuous efforts have been made for the performance improvement of the algorithms and for their effective applications. However, little research has been found on the application to the various view settings of highway CCTV cameras as well as the reliability of the speed estimation. This paper proposes a vision-based system that integrates vehicle detection, vehicle tracking, and field of view calibration algorithms to obtain vehicle counting data and to estimate individual vehicle speed. The proposed system is customized for the video streams collected from highway CCTVs which have various settings in terms of focus and view angles. The system detects and tracks every vehicle in the view unless it is occluded by other vehicles. It is also capable of handling occlusions that occurs frequently depending on the view angles. The system has been tested on the several different views including congested scenes. Vehicle counts and speed estimation results are compared to the manual counting and GPS data, respectively. The comparison signifies that the system has a high potential to extract reliable information about highway traffic conditions from highway CCTVs.
Similar content being viewed by others
References
Bas E, Tekalp M, Salman FS (2007) Automatic vehicle counting from video for traffic flow analysis. 2007 I.E. Intell Vehicles Symp 1-3:1085–1090
Bouttefroy PLM, Bouzerdoum A, Phung SL, Beghdadi A (2008) Vehicle tracking by non-drifting mean-shift using projective Kalman Filter. Proc 11th Int IEEE Conf Intell Transportat Syst: 61–66
Chaiyawatana N, Uyyanonvara B, Kondo T, Dubey P, Hatori Y (2011) Robust object detection on video surveillance. Proc 8th Int Joint Conf Comput Sci Softw Eng: 149–153
Ervin R, MacAdam C, Walker J, Bogard S, Hagan M, Vayda A, Anderson E (2000) System for assessment of the vehicle motion environment (SAVME). University of Michigan Transportation Research Institute, Ann Arbor
Feris R, Petterson J, Siddiquie B, Brown L, Pankanti S (2011) Large-scale vehicle detection in challenging urban surveillance environments. IEEE Workshop Appl Comput Vision (WACV) 2011:527–533
FLIR Monitoring traffic at the Rion-Antirion Bridge, Day and Night. <http://www.flir.co.uk/traffic/display/?id=63198 > (Accessed at January 7, 2017)
Gokule R, Kulkarni A (2014) Video based vehicle speed estimation and stationary vehicle detection. Int J Adv Foundation Res Comput (IJAFRC) 1(11):93–99
Harsha SS, Anne KR (2016) A highly robust vehicle detection, tracking and speed measurement model for intelligent transport systems. Int J Appl Eng Res 11(5):3733–3742
Hsieh JW, Yu SH, Chen YS, Hu WF (2006) Automatic traffic surveillance system for vehicle tracking and classification. IEEE T Intell Transp 7(2):175–187
Huang L (2010) Real-time multi-vehicle detection and sub-feature based tracking for traffic surveillance systems. 2010 2nd Int Asia Conf Inform Contrl, Automation Robot (CAR) 2:324–328
Kanheer NK (2008) Vision-based detection, tracking and classification of vehicles using stable features with automatic camera calibration. Clemson University
Kanhere NK, Birchfield ST, Sarasua WA, Whitney TC (2007) Real-time detection and tracking of vehicle base fronts for measuring traffic counts and speeds on highways. Transport Res Rec 1993:155–164
Kanhere NK, Birchfield ST (2008) Real-time incremental segmentation and tracking of vehicles at low camera angles using stable features. IEEE T Intell Transp 9(1):148–160
Kanhere NK, Birchfield ST (2010) A taxonomy and analysis of camera calibration methods for traffic monitoring applications. IEEE T Intell Transp 11(2):441–452
Kim Z, Cao M (2010) Evaluation of feature-based vehicle trajectory extraction algorithm. 13th Int IEEE Ann Conf Intell Transport Syst, Proc, Madeira Island, Portugal: 99–104
Kim Z, Gomes G, Hranac R, Skabardonis A (2005) A machine vision system for generating vehicle trajectories over extended freeway segments. Proc 12th World Congress Intell Transport Syst
Kim Z, Malik J (2003) Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking. Ninth IEEE Int Conf ComputVision, Vols I and Ii, Proceedings, 524-531
Lienhart R, Maydt J (2002) An extended set of haar-like features for rapid object detection. Proc 2002 Int Conf Imag Process 1:900–903
Liu T, Zheng NN, Zhao L, Cheng H (2005) Learning based symmetric features selection for vehicle detection. IEEE Intell Vehicles Symp Proc 2005:124–129
Malinovskiy Y, Wu YJ, Wang YH (2009) Video-based vehicle detection and tracking using spatiotemporal maps. Transport Res Rec (2121), 81–89
Mcfarlane NJB, Schofield CP (1995) Segmentation and tracking of piglets in images. Mach Vis Appl 8(3):187–193
Melo J, Naftel A, Bernardino A, Santos-Victor J (2006) Detection and classification of highway lanes using vehicle motion trajectories. IEEE T Intell Transp 7(2):188–200
Miovision (2016) Miovision Traffic Data. <https://miovision.com/traffic-data/ > (Accessed at January 7, 2017)
Mu K, Hui F, Zhao X (2016) Multiple vehicle detection and tracking in highway traffic surveillance video based on SIFT feature matching. J Inf Process Syst 12(2):183–195
NGSIM (2006) Next generation simulation <http://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm> (Accessed at June 4, 2012)
Robert K (2009) Video-based traffic monitoring at day and night Vehicle Features Detection and Tracking. 2009 12th Int IEEE Conf Intell Transport Syst (Itsc 2009), 285–290
Rodriguez T, Garcia N (2010) An adaptive, real-time, traffic monitoring system. Mach Vision Appl 21(4):555–576
Ross D, Lim J, Lin R-S, Yang M-H (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77(1):125–141
Scharcanski J, de Oliveira AB, Cavalcanti PG, Yari Y (2011) A particle-filtering approach for vehicular tracking adaptive to occlusions. IEEE T Veh Technol 60(2):381–389
Skimson E (2016) The evolution of data-driven traffic operations. <https://miovision.com/blog/evolution-data-driven-traffic-operations> (Accessed at January 7, 2017)
Tamersoy B, Aggarwal JK (2009) Robust Vehicle detection for tracking in highway surveillance videos using unsupervised learning. Avss: 2009 6th IEEE Int Conf Adv Video Signal Based Surv: 529–534
TrafficVision “Video Analytics Detection for KC SCOUT.” TrafficVision™ Case Study < http://www.trafficvision.com/kc-scout-case-study> (Accessed at January 7, 2017)
Tsai LW, Chean YC, Ho CP, Gu HZ, Lee SY (2011) Multi-lane detection and road traffic congestion classification for intelligent transportation system. Energy Procedia 13:3174–3182
Tsuchiya M, Fujiyoshi H (2006) Evaluating feature importance for object classification in visual surveillance. Int C Patt Recog: 978–981
Uzkent B, Hoffman MJ, Vodacek A (2016) Real-time vehicle tracking in aerial video using hyperspectral features. IEEE Conf Comput Vision Pattern Recogn Workshops 2016:1443–1451
Vargas M, Milla JM, Toral SL, Barrero F (2010) An enhanced background estimation algorithm for vehicle detection in urban traffic scenes. IEEE T Veh Technol 59(8):3694–3709
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. Proc IEEE Comput Soc Conf Comput Vision Pattern Recogn 1:511–518
Xiong C-Z, Pang Y-G, Li Z-X, Liu Y-L, Li Y-H (2009) Vehicle tracking from videos based on mean shift algorithm. Proc ICCTP 2009: Crit Issues Transport Syst Plan, Dev, Manag: 486–493
Yabo A, Arroyo S, Safar F, Oliva D (2016) Vehicle classification and speed estimation using computer vision techniques. Proc AADECA 2016 – Semana del Control Automatico, Buenos Aires, Argentina
Zhang L, Li SZ, Yuan XT, Xiang SM (2007) Real-time object classification in video surveillance based on appearance learning. Proc Cvpr IEEE: 3766–3773
Zhang ZX, Li M, Huang KQ, Tan TN (2008) Boosting local feature descriptors for automatic objects classification in traffic scene surveillance. 19th Int Conf Pattern Recogn 1–6:3918–3921
Acknowledgements
This work was supported by NRF-2014R1A1A2054793 and Transportation & Logistics Research Program ID-97344.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Park, MW., In Kim, J., Lee, YJ. et al. Vision-based surveillance system for monitoring traffic conditions. Multimed Tools Appl 76, 25343–25367 (2017). https://doi.org/10.1007/s11042-017-4521-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4521-4