An algorithm to estimate speed from traffic surveillance cameras in a variety of traffic congestion, weather, and lighting conditions is presented. The features from the images are projected into a one-dimensional sub-space and transformed into a linear coordinate system by using a simplified camera model. A cross-correlation technique is used to summarize the movement of features through a group of images and to estimate mean speed for each lane of vehicles. A Kalman filter technique with a set of maximum-likelihood optimal parameters is used to estimate the traffic speed by lane to create an optimal space-averaged speed.
Get full access to this article
View all access options for this article.
References
1.
SchoepflinT., and DaileyD.. Dynamic Calibration of Roadside Traffic Management Cameras. Proc., IEEE International Conference on Intelligent Transportation Systems, IEEE, New York City, 2002, pp. 25–30.
2.
YuM., JiangG., and YuB.. An Integrative Method for Video Based Traffic Parameter Extraction in ITS. Proc., IEEE Asia-Pacific Conference on Circuits and Systems, IEEE, New York City, 2000, pp. 136–139.
3.
BouzarS., LenoirF., BlossevilleJ. M., and GlachetR.. Traffic Measurement: Image Processing Using Road Markings. Proc., Eighth International Conference on Road Traffic Monitoring and Control, London, IEEE and FHWA, 1996, pp. 105–109.
4.
BeymerD., McLauchlanP., CoifmanB., and MalikJ.. A Real-Time Computer Vision System for Measuring Traffic Parameters. Proc., IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, New York City, 1997, pp. 495–501.
5.
ZhuZ., YangB., XuG., and ShiD.. A Real-Time Vision System for Automatic Traffic Monitoring Based on 2D Spatio-Temporal Images. Proc., Third IEEE Workshop on Application of Computer Vision, IEEE, New York City, 1996, pp. 162–167.
6.
TaniguchiH., NakamuraT., and FurusawaH.. Methods of Traffic Flow Measurement Using Spatio-Temporal Image. Proc., International Conference on Image Processing, Vol. 4, 1999, pp. 16–20.
7.
LiC., IkeuchiK., and SakauchiM.. Acquisition of Traffic Information Using a Video Camera with 2D Spatio-Temporal Image Transformation Technique. Proc., International Conference on Intelligent Transportation Systems, IEEE, Institute of Electrical Engineers of Japan, and Japanese Society for Artificial Intelligence, 1999, pp. 634–638.
8.
OtsukaK., HorikoshiT., and SuzukiS.. Image Velocity Estimation from Trajectory Surface in Spatiotemporal Space. Proc., IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, New York City, 1997, pp. 200–205.
9.
NashJ. M., CarterJ. N. and NixonM. S.. The Velocity Hough Transform: A New Technique for Dynamic Feature Extraction. Proc., International Conference on Image Processing, Vol. 2, 1997, pp. 386–389.
10.
YagiY., SatoK., and YachidaM.. Evaluating Effectivity of Map Generation by Tracking Vertical Edges in Omnidirectional Image Sequences. Proc., IEEE International Conference on Robotics and Automation, Vol. 3, 1995, pp. 2334–2339.
11.
SchoepflinT. N., and DaileyD. J.. Correlation Technique for Estimating Traffic Speed from Cameras. In Transportation Research Record: Journal of the Transportation Research Board, No. 1855, TRB, National Research Council, Washington, D.C., 2003, pp. 66–73.
12.
BellB.The Marginal Likelihood for Parameters in a Discrete Gauss-Markov Process. IEEE Transactions on Signal Processing, Vol. 48, 2000, pp. 870–873.
13.
HerreroJ., PortasJ., RodriguezF., and CorrederaJ.. Surface Movement Radar Data Processing Methods for Airport Surveillance. IEEE Transactions on Aerospace Electronic Systems, Vol. 37, 2001, pp. 563–585.
