A real-time visual-based front-mounted vehicle collision warning system

Chiung Yao Fang, Jui Hung Liang, Chiao Shan Lo, Sei Wang Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

This paper proposes a real-time collision warning system for the front of a vehicle, which contains three stages: lane marking detection, vehicle detection, and vehicle distance estimation. Sobel edge detection and Hough transform techniques are used in the lane marking detection stage to extract lane marking information. In the vehicle detection stage, two very different situations are considered: daytime and nighttime. In the daytime, two kinds of features, vehicle shadows and horizontal edges, are extracted to detect the locations of vehicles. These two features can respectively be obtained by Otsu's method and a horizontal edge detection method. For the nighttime or in days of poor visibility, vehicle tail light features are used to detect the location of vehicles. These features can be obtained from the Cr component of the YCrCb color model and the hue component of the Hue, Saturation and Intensity (HSI) color model respectively. In the vehicle distance estimation stage, the system estimates the distance between the host vehicle and the front vehicles using exponential functions. Some warning messages will be output to the drivers if necessary. In this study, a recorder is set on the front windscreen to obtain the input sequences. The experimental results show that the proposed method has great stability and usability. We intend for the proposed method to be embedded into driving assistance systems and installed in vehicles in the future.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages1-8
Number of pages8
DOIs
Publication statusPublished - 2013 Oct 28
Event2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: 2013 Apr 162013 Apr 19

Publication series

NameProceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

Other

Other2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period13/4/1613/4/19

Fingerprint

Alarm systems
Edge detection
Color
Windshields
Hough transforms
Exponential functions
Visibility

Keywords

  • distance estimation
  • lane marking detection
  • vehicle collision warning system
  • vehicle detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Automotive Engineering

Cite this

Fang, C. Y., Liang, J. H., Lo, C. S., & Chen, S. W. (2013). A real-time visual-based front-mounted vehicle collision warning system. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 1-8). [6612282] (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). https://doi.org/10.1109/CIVTS.2013.6612282

A real-time visual-based front-mounted vehicle collision warning system. / Fang, Chiung Yao; Liang, Jui Hung; Lo, Chiao Shan; Chen, Sei Wang.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-8 6612282 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fang, CY, Liang, JH, Lo, CS & Chen, SW 2013, A real-time visual-based front-mounted vehicle collision warning system. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6612282, Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, pp. 1-8, 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 13/4/16. https://doi.org/10.1109/CIVTS.2013.6612282
Fang CY, Liang JH, Lo CS, Chen SW. A real-time visual-based front-mounted vehicle collision warning system. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-8. 6612282. (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013). https://doi.org/10.1109/CIVTS.2013.6612282
Fang, Chiung Yao ; Liang, Jui Hung ; Lo, Chiao Shan ; Chen, Sei Wang. / A real-time visual-based front-mounted vehicle collision warning system. Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 1-8 (Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013).
@inproceedings{4cf85f5ddd8e404aad29365c34bba0bb,
title = "A real-time visual-based front-mounted vehicle collision warning system",
abstract = "This paper proposes a real-time collision warning system for the front of a vehicle, which contains three stages: lane marking detection, vehicle detection, and vehicle distance estimation. Sobel edge detection and Hough transform techniques are used in the lane marking detection stage to extract lane marking information. In the vehicle detection stage, two very different situations are considered: daytime and nighttime. In the daytime, two kinds of features, vehicle shadows and horizontal edges, are extracted to detect the locations of vehicles. These two features can respectively be obtained by Otsu's method and a horizontal edge detection method. For the nighttime or in days of poor visibility, vehicle tail light features are used to detect the location of vehicles. These features can be obtained from the Cr component of the YCrCb color model and the hue component of the Hue, Saturation and Intensity (HSI) color model respectively. In the vehicle distance estimation stage, the system estimates the distance between the host vehicle and the front vehicles using exponential functions. Some warning messages will be output to the drivers if necessary. In this study, a recorder is set on the front windscreen to obtain the input sequences. The experimental results show that the proposed method has great stability and usability. We intend for the proposed method to be embedded into driving assistance systems and installed in vehicles in the future.",
keywords = "distance estimation, lane marking detection, vehicle collision warning system, vehicle detection",
author = "Fang, {Chiung Yao} and Liang, {Jui Hung} and Lo, {Chiao Shan} and Chen, {Sei Wang}",
year = "2013",
month = "10",
day = "28",
doi = "10.1109/CIVTS.2013.6612282",
language = "English",
isbn = "9781467359139",
series = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",
pages = "1--8",
booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

TY - GEN

T1 - A real-time visual-based front-mounted vehicle collision warning system

AU - Fang, Chiung Yao

AU - Liang, Jui Hung

AU - Lo, Chiao Shan

AU - Chen, Sei Wang

PY - 2013/10/28

Y1 - 2013/10/28

N2 - This paper proposes a real-time collision warning system for the front of a vehicle, which contains three stages: lane marking detection, vehicle detection, and vehicle distance estimation. Sobel edge detection and Hough transform techniques are used in the lane marking detection stage to extract lane marking information. In the vehicle detection stage, two very different situations are considered: daytime and nighttime. In the daytime, two kinds of features, vehicle shadows and horizontal edges, are extracted to detect the locations of vehicles. These two features can respectively be obtained by Otsu's method and a horizontal edge detection method. For the nighttime or in days of poor visibility, vehicle tail light features are used to detect the location of vehicles. These features can be obtained from the Cr component of the YCrCb color model and the hue component of the Hue, Saturation and Intensity (HSI) color model respectively. In the vehicle distance estimation stage, the system estimates the distance between the host vehicle and the front vehicles using exponential functions. Some warning messages will be output to the drivers if necessary. In this study, a recorder is set on the front windscreen to obtain the input sequences. The experimental results show that the proposed method has great stability and usability. We intend for the proposed method to be embedded into driving assistance systems and installed in vehicles in the future.

AB - This paper proposes a real-time collision warning system for the front of a vehicle, which contains three stages: lane marking detection, vehicle detection, and vehicle distance estimation. Sobel edge detection and Hough transform techniques are used in the lane marking detection stage to extract lane marking information. In the vehicle detection stage, two very different situations are considered: daytime and nighttime. In the daytime, two kinds of features, vehicle shadows and horizontal edges, are extracted to detect the locations of vehicles. These two features can respectively be obtained by Otsu's method and a horizontal edge detection method. For the nighttime or in days of poor visibility, vehicle tail light features are used to detect the location of vehicles. These features can be obtained from the Cr component of the YCrCb color model and the hue component of the Hue, Saturation and Intensity (HSI) color model respectively. In the vehicle distance estimation stage, the system estimates the distance between the host vehicle and the front vehicles using exponential functions. Some warning messages will be output to the drivers if necessary. In this study, a recorder is set on the front windscreen to obtain the input sequences. The experimental results show that the proposed method has great stability and usability. We intend for the proposed method to be embedded into driving assistance systems and installed in vehicles in the future.

KW - distance estimation

KW - lane marking detection

KW - vehicle collision warning system

KW - vehicle detection

UR - http://www.scopus.com/inward/record.url?scp=84886002362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886002362&partnerID=8YFLogxK

U2 - 10.1109/CIVTS.2013.6612282

DO - 10.1109/CIVTS.2013.6612282

M3 - Conference contribution

AN - SCOPUS:84886002362

SN - 9781467359139

T3 - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

SP - 1

EP - 8

BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

ER -