Stereo vision-based forward obstacle detection

H. G. Jung, Y. H. Lee, B. J. Kim, P. J. Yoon, Jaihie Kim

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

This paper proposes a stereo vision-based forward obstacle detection and distance measurement method. In general, stereo vision-based obstacle detection methods in automotive applications can be classified into two categories: IPM (Inverse Perspective Mapping)-based and disparity histogram-based. The existing disparity histogram-based method was developed for stop-and-go applications. The proposed method extends the scope of the disparity histogram-based method to highway applications by 1) replacing the fixed rectangular ROI (Region Of Interest) with the traveling lanebased ROI, and 2) replacing the peak detection with a constant threshold with peak detection using the threshold-line and peakness evaluation. In order to increase the true positive rate while decreasing the false positive rate, multiple candidate peaks were generated and then verified by the edge feature correlation method. By testing the proposed method with images captured on the highway, it was shown that the proposed method was able to overcome problems in previous implementations while being applied successfully to highway collision warning/avoidance conditions. In addition, comparisons with laser radar showed that vision sensors with a wider FOV (Field Of View) provided faster responses to cutting-in vehicles. Finally, we integrated the proposed method into a longitudinal collision avoidance system. Experimental results showed that activated braking by risk assessment using the state of the ego-vehicle and measuring the distance to upcoming obstacles could successfully prevent collisions.

Original languageEnglish
Pages (from-to)493-504
Number of pages12
JournalInternational Journal of Automotive Technology
Volume8
Issue number4
Publication statusPublished - 2007 Aug 1

Fingerprint

Stereo vision
Distance measurement
Correlation methods
Optical radar
Collision avoidance
Braking
Risk assessment
Sensors
Testing

All Science Journal Classification (ASJC) codes

  • Automotive Engineering

Cite this

Jung, H. G., Lee, Y. H., Kim, B. J., Yoon, P. J., & Kim, J. (2007). Stereo vision-based forward obstacle detection. International Journal of Automotive Technology, 8(4), 493-504.
Jung, H. G. ; Lee, Y. H. ; Kim, B. J. ; Yoon, P. J. ; Kim, Jaihie. / Stereo vision-based forward obstacle detection. In: International Journal of Automotive Technology. 2007 ; Vol. 8, No. 4. pp. 493-504.
@article{2fc7118232ed4fd5a1e2f11032f287c8,
title = "Stereo vision-based forward obstacle detection",
abstract = "This paper proposes a stereo vision-based forward obstacle detection and distance measurement method. In general, stereo vision-based obstacle detection methods in automotive applications can be classified into two categories: IPM (Inverse Perspective Mapping)-based and disparity histogram-based. The existing disparity histogram-based method was developed for stop-and-go applications. The proposed method extends the scope of the disparity histogram-based method to highway applications by 1) replacing the fixed rectangular ROI (Region Of Interest) with the traveling lanebased ROI, and 2) replacing the peak detection with a constant threshold with peak detection using the threshold-line and peakness evaluation. In order to increase the true positive rate while decreasing the false positive rate, multiple candidate peaks were generated and then verified by the edge feature correlation method. By testing the proposed method with images captured on the highway, it was shown that the proposed method was able to overcome problems in previous implementations while being applied successfully to highway collision warning/avoidance conditions. In addition, comparisons with laser radar showed that vision sensors with a wider FOV (Field Of View) provided faster responses to cutting-in vehicles. Finally, we integrated the proposed method into a longitudinal collision avoidance system. Experimental results showed that activated braking by risk assessment using the state of the ego-vehicle and measuring the distance to upcoming obstacles could successfully prevent collisions.",
author = "Jung, {H. G.} and Lee, {Y. H.} and Kim, {B. J.} and Yoon, {P. J.} and Jaihie Kim",
year = "2007",
month = "8",
day = "1",
language = "English",
volume = "8",
pages = "493--504",
journal = "International Journal of Automotive Technology",
issn = "1229-9138",
publisher = "Korean Society of Automotive Engineers",
number = "4",

}

Jung, HG, Lee, YH, Kim, BJ, Yoon, PJ & Kim, J 2007, 'Stereo vision-based forward obstacle detection', International Journal of Automotive Technology, vol. 8, no. 4, pp. 493-504.

Stereo vision-based forward obstacle detection. / Jung, H. G.; Lee, Y. H.; Kim, B. J.; Yoon, P. J.; Kim, Jaihie.

In: International Journal of Automotive Technology, Vol. 8, No. 4, 01.08.2007, p. 493-504.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Stereo vision-based forward obstacle detection

AU - Jung, H. G.

AU - Lee, Y. H.

AU - Kim, B. J.

AU - Yoon, P. J.

AU - Kim, Jaihie

PY - 2007/8/1

Y1 - 2007/8/1

N2 - This paper proposes a stereo vision-based forward obstacle detection and distance measurement method. In general, stereo vision-based obstacle detection methods in automotive applications can be classified into two categories: IPM (Inverse Perspective Mapping)-based and disparity histogram-based. The existing disparity histogram-based method was developed for stop-and-go applications. The proposed method extends the scope of the disparity histogram-based method to highway applications by 1) replacing the fixed rectangular ROI (Region Of Interest) with the traveling lanebased ROI, and 2) replacing the peak detection with a constant threshold with peak detection using the threshold-line and peakness evaluation. In order to increase the true positive rate while decreasing the false positive rate, multiple candidate peaks were generated and then verified by the edge feature correlation method. By testing the proposed method with images captured on the highway, it was shown that the proposed method was able to overcome problems in previous implementations while being applied successfully to highway collision warning/avoidance conditions. In addition, comparisons with laser radar showed that vision sensors with a wider FOV (Field Of View) provided faster responses to cutting-in vehicles. Finally, we integrated the proposed method into a longitudinal collision avoidance system. Experimental results showed that activated braking by risk assessment using the state of the ego-vehicle and measuring the distance to upcoming obstacles could successfully prevent collisions.

AB - This paper proposes a stereo vision-based forward obstacle detection and distance measurement method. In general, stereo vision-based obstacle detection methods in automotive applications can be classified into two categories: IPM (Inverse Perspective Mapping)-based and disparity histogram-based. The existing disparity histogram-based method was developed for stop-and-go applications. The proposed method extends the scope of the disparity histogram-based method to highway applications by 1) replacing the fixed rectangular ROI (Region Of Interest) with the traveling lanebased ROI, and 2) replacing the peak detection with a constant threshold with peak detection using the threshold-line and peakness evaluation. In order to increase the true positive rate while decreasing the false positive rate, multiple candidate peaks were generated and then verified by the edge feature correlation method. By testing the proposed method with images captured on the highway, it was shown that the proposed method was able to overcome problems in previous implementations while being applied successfully to highway collision warning/avoidance conditions. In addition, comparisons with laser radar showed that vision sensors with a wider FOV (Field Of View) provided faster responses to cutting-in vehicles. Finally, we integrated the proposed method into a longitudinal collision avoidance system. Experimental results showed that activated braking by risk assessment using the state of the ego-vehicle and measuring the distance to upcoming obstacles could successfully prevent collisions.

UR - http://www.scopus.com/inward/record.url?scp=36048963264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36048963264&partnerID=8YFLogxK

M3 - Article

VL - 8

SP - 493

EP - 504

JO - International Journal of Automotive Technology

JF - International Journal of Automotive Technology

SN - 1229-9138

IS - 4

ER -