Abstract
The paper presents a real-time vision system to compute traffic parameters by analyzing monocular image sequences coming from pole-mounted video cameras at urban crossroads. The system uses a combination of segmentation and motion information to localize and track moving objects on the road plane, utilizing a robust background updating, and a feature-based tracking method. It is able to describe the path of each detected vehicle, to estimate its speed and to classify it into seven categories. The classification task relies on a model-based matching technique refined by a feature-based one for distinguishing between classes having similar models, like bicycles and motorcycles. The system is flexible with respect to the intersection geometry and the camera position. Experimental results demonstrate robust, real-time vehicle detection, tracking and classification over several hours of videos taken under different illumination conditions. The system is presently under trial in Trento, a 100,000-people town in northern Italy.
Similar content being viewed by others
References
Cucchiara R, Grana C, Piccardi M, Prati A (2000) Statistic and knowledge-based moving object detection in traffic scenes. In: 3rd IEEE conference on intelligent transportation systems. Dearborn, IN, USA, pp 27–32
Ferryman JM, Maybank SJ, Worrall AD (2000) Visual surveillance for moving vehicles. Int J Comput Vis 37(2):187–197
Haag M, Nagel HH (2000) Incremental recognition of traffic situations from video image sequences. Image Vis Comput 18(2):137–153
Morris RJ, Hogg DC (2000) Statistical models of object interaction. Int J Comput Vis 37(2):209–215
Badenas J, Bober M, Pla F (2001) Segmenting traffic scenes from gray level and motion information. Pattern Anal Appl 4(1):28–38
Setchell C, Dagless EL (2001) Vision-based road-traffic monitoring sensor. IEE Proc Vis Image Signal Process 148(1):78–84
Cavallaro A, Steiger O, Ebrahimi T (2002) Multiple video object tracking in complex scenes. In: ACM multimedia conference. Juan Les Pins, France, pp 523–532
Kato J, Watanabe T, Joga S, Rittscher J, Blake A (2002) HMM-based segmentation method for traffic monitoring movies. IEEE Trans Pattern Anal Mach Intell 24(9):1291–1296
Gupte S, Masoud O, Martin RFK, Papanikolopoulos NP (2002) Detection and classification of vehicles. IEEE Trans Intell Transport Syst 3(1):37–47
Yoneyama A, Yeh C, Kuo CJJ (2003) Highway traffic analysis with vision-based surveillance systems. In: SPIE symposium on visual information processing XII. Orlando, FL, USA
Stubbs K, Arumugam H, Masoud O, McMillen C, Veeraraghavan H, Janardan R, Papanikolopoulos N (2003) A real-time collision warning system for intersections. In: 13th annual meeting on intelligent transportation systems America. Minneapolis, MN, USA
Veeraraghavan H, Masoud O, Papanikolopoulos N (2003) Computer vision algorithms for intersection monitoring. IEEE Trans Intell Transport Syst 4(2):78–89
Zanin M, Messelodi S, Modena CM (2003) An efficient vehicle queue detection system based on image processing. In: 12th international conference on image analysis and processing. Mantova, Italy, pp 232–237
Foresti GL, Micheloni C, Snidaro L (2003) Advanced visual-based traffic monitoring systems for increasing safety in road transportation. Adv Transport Stud Int J 1:27–47
Hoose N, Willumsen LG (1987) Automatically extracting traffic data from video-tape using the clip4 parallel image processor. Pattern Recogn Lett 6:199–213
Fathy M, Siyal MY (1997) Measuring traffic movements at junctions using image processing techniques. Pattern Recogn Lett 18:493–500
Haralick RM (1989) Determining camera parameters from the perspective projection of a rectangle. Pattern Recogn 22(3):225–230
Worrall AD, Sullivan GD, Baker KD (1994) A simple, intuitive camera calibration tool for natural images. In: 5th British machine vision conference. pp 781–790
Andra S, Al-Kofahi O, Radke RJ, Roysam B (2004) Image change detection algorithms: a systematic survey. Rensselaer Poly Technic Institute, Troy, NY, USA, unpublished
Rosin PL (1998) Thresholding for change detection. In: 6th international conference on computer vision. IEEE Computer Society Press, pp 274–279
Kameda Y, Minoh M (1996) A human motion estimation method using 3-successive video frames. In: International conference on virtual systems and multimedia. pp 135–140
Kalman RE (1960) A new approach to linear filtering and prediction problems. Trans ASME J Basic Eng 82(Series D):35–45
Karman K, Brandt A, Gerl R (1990) Moving object segmentation based on adaptive reference images. In: Signal processing V: theories and applications. Barcelona, Spain, pp 951–954
Boninsegna M, Bozzoli A (2000) A tunable algorithm to update a reference image. Signal Process: Image Commun 16(4):353–365
Rosin PL, Ioannidis E (2003) Evaluation of global image thresholding for change detection. Pattern Recogn Lett 24(14):2345–2356
Cattoni G, Messelodi S, Modena CM (2004) Vision-based bicycle/motorcycle classification with support vector machines. Technical report T04-10-01, ITC-irst
Prati A, Mikic I, Trivedi MM, Cucchiara R (2003) Detecting moving shadows: algorithms and evaluation. IEEE Trans Pattern Anal Mach Intell 25(7):918–923
Acknowledgements
This work was partially supported by Comune di Trento and Italian Ministero delle Infrastrutture e Trasporti. We thank Luca Leonelli, Servizio Reti of Comune di Trento, for testing the system, reporting bugs, and suggesting improvements.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Messelodi, S., Modena, C.M. & Zanin, M. A computer vision system for the detection and classification of vehicles at urban road intersections. Pattern Anal Applic 8, 17–31 (2005). https://doi.org/10.1007/s10044-004-0239-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-004-0239-9