Roadway signs represent a substantial investment of public money in road and highway infrastructure. However, the current level of automation in sign identification and recognition, size dimensioning, and location identification is not satisfactory. This paper targets the development of an automated road inventory system addressing these issues. A framework of combining the conventional image processing methods with the Kalman filter tracking method is applied to improve the accuracy and efficiency of the ROW image processing. Through the tracking technique, the candidate region of the road sign in the picture can be predicted based on the previous image frame. Detection efficiency and accuracy of the sign can be improved. The methodologies described in the paper fit a dynamic and motion environment, appropriate for a highway survey vehicle. There have been limited published literature on automated inventory of roadway signs, despite the fact that there were several attempts in recent years in the ITS arena to detect sign for the purpose of automated driving and navigation. A methodology for automated inventory of road sign by image analysis and Kalman filter tracking with ROW images has been tested successfully in this research. The algorithms have four main parts, the detection, tracking, recognition and GPS mapping. The detection is based on color and shape information. The Kalman filter tracking algorithm makes the detection more robust and efficiency. The recognition is accomplished by template matching. The GPS position system provides positioning data for road sign. It is also demonstrated that the techniques can successfully track and detect multiple signs in the same sequence of images. Based on our initial experimentation with the algorithms and models presented in the paper, the percentage of falsely identified signs is very low. It is hopeful that comprehensive and fully automated inventory of roadway signs can be realized with more signs built into the database.
Automated tracking system for inventory of roadway signs
2006
6 Seiten, 1 Bild, 1 Tabelle, 6 Quellen
Aufsatz (Konferenz)
Englisch
Automated Tracking System for Inventory of Roadway Signs
ASCE | 2006
|Automated Tracking System for Inventory of Roadway Signs
British Library Conference Proceedings | 2005
|Kalman Filter-Based Tracking System for Automated Inventory of Roadway Signs
Online Contents | 2006
|Kalman Filter-Based Tracking System for Automated Inventory of Roadway Signs
Transportation Research Record | 2006
|Kalman Filter-Based Tracking System for Automated Inventory of Roadway Signs
British Library Conference Proceedings | 2006
|