DocumentCode :
3265915
Title :
A Tracking System for Automated Inventory of Road Signs
Author :
Lafuente-Arroyo, S. ; Maldonado-Bascón, S. ; Gil-Jiménez, P. ; Acevedo-Rodríguez, J. ; López-Sastre, R.J.
Author_Institution :
Univ. de Alcala, Madrid
fYear :
2007
fDate :
13-15 June 2007
Firstpage :
166
Lastpage :
171
Abstract :
This paper describes the tracking stage of a road sign identification system with the use of a Kalman filter estimator. Although traditionally traffic sign recognition systems work in a single-frame way, tracking using inter-frame information is crucial in order to reduce false alarms. In applications that involve maintenance systems, the purpose of tracking is to give a single stroke of each road sign although it is presented in several frames of a sequence. The tracking module uses the output of the recognition stage, which processes each frame independently. Each traffic sign is followed for a specific distance which is computed in each case based on the system parameters. This setup has permitted improve the accuracy of the performance with respect to the obtained at the output of the recognition system. Additionally most false alarms are eliminated because their characteristic are temporally incoherent.
Keywords :
Kalman filters; image recognition; tracking; Kalman filter estimator; automated inventory; recognition system; road signs; tracking module; tracking system; traffic sign recognition systems; Automated highways; Automation; Distance measurement; Global Positioning System; Intelligent vehicles; Inventory management; Investments; Object detection; Road accidents; Support vector machines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Vehicles Symposium, 2007 IEEE
Conference_Location :
Istanbul
ISSN :
1931-0587
Print_ISBN :
1-4244-1067-3
Electronic_ISBN :
1931-0587
Type :
conf
DOI :
10.1109/IVS.2007.4290109
Filename :
4290109
Link To Document :
بازگشت