Computationally Efficient Vehicle Tracking for Detecting Accidents in Tunnels

It is becoming increasingly important to construct tunnel for transportation time and space utilization. To avoid the large scale of damages of vehicle accident in the tunnel, it is necessary to have a tunnel accidents monitoring system to minimize and discover the accidents as fast as possible. In this paper, a moving and stopped vehicle detection algorithm is proposed. It Detecting vehicle based on morphological size information of object according to distance and Adaboost algorithm. Kalman filter and LUV color informations of rear lamp are used to detect stopped vehicles. Results of computer simulations show that proposed algorithm increases detection rate more than other detection algorithms.

[1]  Nick Barnes,et al.  Fast sum of absolute differences visual landmark detector , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[2]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[3]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[4]  Mansour Jamzad,et al.  Real time classification and tracking of multiple vehicles in highways , 2005, Pattern Recognit. Lett..

[5]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Jangsik Park,et al.  Vehicle Tracking Based on Kalman Filter in Tunnel , 2011, ISA.

[8]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.