Road traffic sign detection and classification

A vision-based vehicle guidance system for road vehicles can have three main roles: (1) road detection; (2) obstacle detection; and (3) sign recognition. The first two have been studied for many years and with many good results, but traffic sign recognition is a less-studied field. Traffic signs provide drivers with very valuable information about the road, in order to make driving safer and easier. The authors think that traffic signs most play the same role for autonomous vehicles. They are designed to be easily recognized by human drivers mainly because their color and shapes are very different from natural environments. The algorithm described in this paper takes advantage of these features. It has two main parts. The first one, for the detection, uses color thresholding to segment the image and shape analysis to detect the signs. The second one, for the classification, uses a neural network. Some results from natural scenes are shown.

[1]  Hans-Hellmut Nagel,et al.  Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene , 1981, Comput. Graph. Image Process..

[2]  Ramesh C. Jain,et al.  Detecting time-varying corners , 1984, Comput. Vis. Graph. Image Process..

[3]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[4]  Mubarak Shah,et al.  Optimal Corner Detector , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[5]  Dean A. Pomerleau,et al.  Neural Network Based Autonomous Navigation , 1990 .

[6]  Charles E. Thorpe,et al.  UNSCARF-a color vision system for the detection of unstructured roads , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[7]  Larry S. Davis.  Visual navigation at the University of Maryland , 1991, Robotics Auton. Syst..

[8]  Ren C. Luo,et al.  Natural scene segmentation using fractal based autocorrelation , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[9]  Ren C. Luo,et al.  Translation And Scale Invariant Landmark Recognition Using Receptive Field Neural Networks , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Marie de Saint Blancard,et al.  Road sign recognition: a study of vision-based decision making for road environment recognition , 1992 .

[11]  C..  Vision-based Vehicle Guidance , 1992, Springer Series in Perception Engineering.

[12]  Masumi Yoshida,et al.  A visual control system using image processing and fuzzy theory , 1992 .

[13]  B. Ulmer,et al.  Shape Classification for Traffic Sign Recognition , 1993 .

[14]  M. Campani,et al.  Robust road sign detection and recognition from image sequences , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[15]  Ren C. Luo,et al.  Landmark recognition using projection learning for mobile robot navigation , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[16]  Marco Campani,et al.  Robust method for road sign detection and recognition , 1996, Image Vis. Comput..

[17]  Han Wang,et al.  Gray Level Corner Detection , 1998, MVA.