by Ren, F, Huang, J, Jiang, R and Klette, R
Abstract:
Traffic sign recognition is a technology which allows us to recognize signs in real time, typically in videos, or sometimes just (off-line) in photos. It is used for Driver Assistance Systems (DAS), road surveys, or the management of road assets (to improve road safety). In this paper, we propose a method for general traffic sign recognition (tested for the New Zealand road signs) which combines previously designed steps, but with an overall adaptation towards general traffic sign recognition (i.e., not just speed or stop signs). First, color input images or frames are converted from RGB color space into HSV color space. Second, special shapes as potential signs are detected (circles, triangles, squares) using Hough transform. Third, potential signs are compared with the template signs as given in the database by using feature matching methods (SIFT or SURF features). At the end, we recognize the traffic sign in an image aiming at realtime DAS. Experiments show that the proposed method is robust for the selected test data, with over 95 percent success rate on average. On a single frame of size 1024 × 768, the system uses on average 80 ms for preprocessing, and 100 ms for matching a traffic sign candidate. © 2009 IEEE.
Reference:
General traffic sign recognition by feature matching (Ren, F, Huang, J, Jiang, R and Klette, R), In 2009 24th International Conference Image and Vision Computing New Zealand, IVCNZ 2009 – Conference Proceedings, 2009.
Bibtex Entry:
@inproceedings{ren2009generalmatching,
author = "Ren, F and Huang, J and Jiang, R and Klette, R",
booktitle = "2009 24th International Conference Image and Vision Computing New Zealand, IVCNZ 2009 - Conference Proceedings",
pages = "409--414",
title = "General traffic sign recognition by feature matching",
year = "2009",
abstract = "Traffic sign recognition is a technology which allows us to recognize signs in real time, typically in videos, or sometimes just (off-line) in photos. It is used for Driver Assistance Systems (DAS), road surveys, or the management of road assets (to improve road safety). In this paper, we propose a method for general traffic sign recognition (tested for the New Zealand road signs) which combines previously designed steps, but with an overall adaptation towards general traffic sign recognition (i.e., not just speed or stop signs). First, color input images or frames are converted from RGB color space into HSV color space. Second, special shapes as potential signs are detected (circles, triangles, squares) using Hough transform. Third, potential signs are compared with the template signs as given in the database by using feature matching methods (SIFT or SURF features). At the end, we recognize the traffic sign in an image aiming at realtime DAS. Experiments show that the proposed method is robust for the selected test data, with over 95 percent success rate on average. On a single frame of size 1024 × 768, the system uses on average 80 ms for preprocessing, and 100 ms for matching a traffic sign candidate. © 2009 IEEE.",
doi = "10.1109/IVCNZ.2009.5378370",
isbn = "9781424446988",
keyword = "Driver assistance systems",
keyword = "Feature detection",
keyword = "Object detection",
keyword = "SIFT",
keyword = "SURF",
keyword = "Traffic sign recognition",
language = "eng",
}