Colour-based bottom-up saliency for traffic sign detection

Anh Cat Le Ngo, Li Minn Ang, Kah Phoai Seng, Guoping Qiu

Research output: Book chapter/Published conference paperConference paper

Abstract

On roads, drivers can detect traffic sign extraordinarily fast and accurately; however, the computer vision system does not easily imitate this natural ability although using a lot of image processing techniques. This weakness can be tackled by a bottom-up visual saliency method based on traffic-sign colours which occupy certain ranges of RGB values. These values can be used to modulate the bottom-up visual saliency, so the proposed system can focus on traffic signs detection. The method is tested on the UNMC Automotive Vision Database and compared with results of the purely bottom-up visual saliency method.

Original languageEnglish
Title of host publicationICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics
Pages453-457
Number of pages5
DOIs
Publication statusPublished - 01 Dec 2010
Event2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010 - Kuala Lumpur, Malaysia
Duration: 05 Dec 201007 Dec 2010

Conference

Conference2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010
CountryMalaysia
CityKuala Lumpur
Period05/12/1007/12/10

Fingerprint

Traffic signs
Color
Computer vision
Image processing

Cite this

Le Ngo, A. C., Ang, L. M., Seng, K. P., & Qiu, G. (2010). Colour-based bottom-up saliency for traffic sign detection. In ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics (pp. 453-457). [5735122] https://doi.org/10.1109/ICCAIE.2010.5735122
Le Ngo, Anh Cat ; Ang, Li Minn ; Seng, Kah Phoai ; Qiu, Guoping. / Colour-based bottom-up saliency for traffic sign detection. ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. pp. 453-457
@inproceedings{8692687fa453405297c38ff2ff9f9c45,
title = "Colour-based bottom-up saliency for traffic sign detection",
abstract = "On roads, drivers can detect traffic sign extraordinarily fast and accurately; however, the computer vision system does not easily imitate this natural ability although using a lot of image processing techniques. This weakness can be tackled by a bottom-up visual saliency method based on traffic-sign colours which occupy certain ranges of RGB values. These values can be used to modulate the bottom-up visual saliency, so the proposed system can focus on traffic signs detection. The method is tested on the UNMC Automotive Vision Database and compared with results of the purely bottom-up visual saliency method.",
author = "{Le Ngo}, {Anh Cat} and Ang, {Li Minn} and Seng, {Kah Phoai} and Guoping Qiu",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICCAIE.2010.5735122",
language = "English",
isbn = "9781424490554",
pages = "453--457",
booktitle = "ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics",

}

Le Ngo, AC, Ang, LM, Seng, KP & Qiu, G 2010, Colour-based bottom-up saliency for traffic sign detection. in ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics., 5735122, pp. 453-457, 2010 International Conference on Computer Applications and Industrial Electronics, ICCAIE 2010, Kuala Lumpur, Malaysia, 05/12/10. https://doi.org/10.1109/ICCAIE.2010.5735122

Colour-based bottom-up saliency for traffic sign detection. / Le Ngo, Anh Cat; Ang, Li Minn; Seng, Kah Phoai; Qiu, Guoping.

ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. p. 453-457 5735122.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Colour-based bottom-up saliency for traffic sign detection

AU - Le Ngo, Anh Cat

AU - Ang, Li Minn

AU - Seng, Kah Phoai

AU - Qiu, Guoping

PY - 2010/12/1

Y1 - 2010/12/1

N2 - On roads, drivers can detect traffic sign extraordinarily fast and accurately; however, the computer vision system does not easily imitate this natural ability although using a lot of image processing techniques. This weakness can be tackled by a bottom-up visual saliency method based on traffic-sign colours which occupy certain ranges of RGB values. These values can be used to modulate the bottom-up visual saliency, so the proposed system can focus on traffic signs detection. The method is tested on the UNMC Automotive Vision Database and compared with results of the purely bottom-up visual saliency method.

AB - On roads, drivers can detect traffic sign extraordinarily fast and accurately; however, the computer vision system does not easily imitate this natural ability although using a lot of image processing techniques. This weakness can be tackled by a bottom-up visual saliency method based on traffic-sign colours which occupy certain ranges of RGB values. These values can be used to modulate the bottom-up visual saliency, so the proposed system can focus on traffic signs detection. The method is tested on the UNMC Automotive Vision Database and compared with results of the purely bottom-up visual saliency method.

UR - http://www.scopus.com/inward/record.url?scp=79953878376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953878376&partnerID=8YFLogxK

U2 - 10.1109/ICCAIE.2010.5735122

DO - 10.1109/ICCAIE.2010.5735122

M3 - Conference paper

AN - SCOPUS:79953878376

SN - 9781424490554

SP - 453

EP - 457

BT - ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics

ER -

Le Ngo AC, Ang LM, Seng KP, Qiu G. Colour-based bottom-up saliency for traffic sign detection. In ICCAIE 2010 - 2010 International Conference on Computer Applications and Industrial Electronics. 2010. p. 453-457. 5735122 https://doi.org/10.1109/ICCAIE.2010.5735122