Controlador de Tráfico Inteligente con Prelación para Vehículos de Emergencia

This paper describes the development of a traffic controller using fuzzy logic, combined with the analysis of video sequences through machine vision techniques. The controller is able to automatically manage the traffic flow in a set of intersections, giving priority to the traffic lights of roads where there are emergency vehicles waiting. The system uses a classification algorithm, which is trained in order to detect any vehicle the scene and an image processing algorithm that identifies emergency vehicles within the previously detected vehicles. Using the information of video sequences acquired with CCD cameras installed on the intersections, the system choose the sequence of actions that improves the traffic flow, so as to increase the mobility in the road where the emergency vehicle is detected. Results show that the system is able to detect vehicles in real time. Also, the system adapts in an efficient and fast way to the changes in traffic flow in order to establish a priority road for emergency vehicles.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jaesik Choi,et al.  Realtime On-Road Vehicle Detection with Optical Flows and Haar-Like Feature Detectors , 2012 .

[3]  Marzuki Khalid,et al.  INTELLIGENT TRAFFIC LIGHTS CONTROL BY FUZZY LOGIC , 1996 .

[4]  Ben Weber Generic Object Detection using AdaBoost , 2008 .

[5]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[6]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.

[7]  Lawrence A Klein,et al.  SUMMARY OF VEHICLE DETECTION AND SURVEILLANCE TECHNOLOGIES USED IN INTELLIGENT TRANSPORTATION SYSTEMS , 2000 .

[8]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[9]  O. Aviles,et al.  Dynamic traffic light controller using machine vision and optimization algorithms , 2012, 2012 Workshop on Engineering Applications.

[10]  Mahmood Fathy,et al.  Real-time image processing approach to measure traffic queue parameters , 1995 .

[11]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[12]  Youngjoon Han,et al.  Vehicle Detection Method using Haar-like Feature on Real Time System , 2009 .

[13]  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.

[14]  Daniel Robles,et al.  Control y simulación de tráfico urbano en Colombia: Estado del arte , 2009 .

[15]  M Higashikubo,et al.  TRAFFIC QUEUE LENGTH MEASUREMENT USING AN IMAGE PROCESSING SENSOR , 1996 .

[16]  Marco Wiering,et al.  Intelligent Trac Light Control , 2004 .

[17]  P. G. Michalopoulos,et al.  Vehicle detection video through image processing: the Autoscope system , 1991 .

[18]  Hyung Lee-Kwang,et al.  Distributed and cooperative fuzzy controllers for traffic intersections group , 1999, IEEE Trans. Syst. Man Cybern. Part C.