Efficient lane detection based on spatiotemporal images

Soonhong Jung, Junsic Youn, Sanghoon Sull

Research output: Contribution to journalArticle

48 Citations (Scopus)

Abstract

In this paper, we propose an efficient method for reliably detecting road lanes based on spatiotemporal images. In an aligned spatiotemporal image generated by accumulating the pixels on a scanline along the time axis and aligning consecutive scanlines, the trajectory of the lane points appears smooth and forms a straight line. The aligned spatiotemporal image is binarized, and two dominant parallel straight lines resulting from the temporal consistency of lane width on a given scanline are detected using a Hough transform, reducing alignment errors. The left and right lane points are then detected near the intersections of the straight lines and the current scanline. Our spatiotemporal domain approach is more robust missing or occluded lanes than existing frame-based approaches. Furthermore, the experimental results show not only computation times reduced to as little as one-third but also a slightly improved rate of detection.

Original languageEnglish
Article number7217838
Pages (from-to)289-295
Number of pages7
JournalIEEE Transactions on Intelligent Transportation Systems
Volume17
Issue number1
DOIs
Publication statusPublished - 2016 Jan 1

Fingerprint

Hough transforms
Pixels
Trajectories

Keywords

  • Alignment
  • Binarization
  • Cubic model
  • Hough transform
  • Lane detection
  • Lane tracking
  • Scanline
  • Spatiotemporal image
  • Temporal consistency

ASJC Scopus subject areas

  • Automotive Engineering
  • Computer Science Applications
  • Mechanical Engineering

Cite this

Efficient lane detection based on spatiotemporal images. / Jung, Soonhong; Youn, Junsic; Sull, Sanghoon.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 17, No. 1, 7217838, 01.01.2016, p. 289-295.

Research output: Contribution to journalArticle

@article{b4b5c0ba5b7a4feeb519639410eecb3f,
title = "Efficient lane detection based on spatiotemporal images",
abstract = "In this paper, we propose an efficient method for reliably detecting road lanes based on spatiotemporal images. In an aligned spatiotemporal image generated by accumulating the pixels on a scanline along the time axis and aligning consecutive scanlines, the trajectory of the lane points appears smooth and forms a straight line. The aligned spatiotemporal image is binarized, and two dominant parallel straight lines resulting from the temporal consistency of lane width on a given scanline are detected using a Hough transform, reducing alignment errors. The left and right lane points are then detected near the intersections of the straight lines and the current scanline. Our spatiotemporal domain approach is more robust missing or occluded lanes than existing frame-based approaches. Furthermore, the experimental results show not only computation times reduced to as little as one-third but also a slightly improved rate of detection.",
keywords = "Alignment, Binarization, Cubic model, Hough transform, Lane detection, Lane tracking, Scanline, Spatiotemporal image, Temporal consistency",
author = "Soonhong Jung and Junsic Youn and Sanghoon Sull",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/TITS.2015.2464253",
language = "English",
volume = "17",
pages = "289--295",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Efficient lane detection based on spatiotemporal images

AU - Jung, Soonhong

AU - Youn, Junsic

AU - Sull, Sanghoon

PY - 2016/1/1

Y1 - 2016/1/1

N2 - In this paper, we propose an efficient method for reliably detecting road lanes based on spatiotemporal images. In an aligned spatiotemporal image generated by accumulating the pixels on a scanline along the time axis and aligning consecutive scanlines, the trajectory of the lane points appears smooth and forms a straight line. The aligned spatiotemporal image is binarized, and two dominant parallel straight lines resulting from the temporal consistency of lane width on a given scanline are detected using a Hough transform, reducing alignment errors. The left and right lane points are then detected near the intersections of the straight lines and the current scanline. Our spatiotemporal domain approach is more robust missing or occluded lanes than existing frame-based approaches. Furthermore, the experimental results show not only computation times reduced to as little as one-third but also a slightly improved rate of detection.

AB - In this paper, we propose an efficient method for reliably detecting road lanes based on spatiotemporal images. In an aligned spatiotemporal image generated by accumulating the pixels on a scanline along the time axis and aligning consecutive scanlines, the trajectory of the lane points appears smooth and forms a straight line. The aligned spatiotemporal image is binarized, and two dominant parallel straight lines resulting from the temporal consistency of lane width on a given scanline are detected using a Hough transform, reducing alignment errors. The left and right lane points are then detected near the intersections of the straight lines and the current scanline. Our spatiotemporal domain approach is more robust missing or occluded lanes than existing frame-based approaches. Furthermore, the experimental results show not only computation times reduced to as little as one-third but also a slightly improved rate of detection.

KW - Alignment

KW - Binarization

KW - Cubic model

KW - Hough transform

KW - Lane detection

KW - Lane tracking

KW - Scanline

KW - Spatiotemporal image

KW - Temporal consistency

UR - http://www.scopus.com/inward/record.url?scp=84960800651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960800651&partnerID=8YFLogxK

U2 - 10.1109/TITS.2015.2464253

DO - 10.1109/TITS.2015.2464253

M3 - Article

VL - 17

SP - 289

EP - 295

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 1

M1 - 7217838

ER -