Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features

Robert D. Leary, Sean N. Brennan

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

Abstract

This paper presents a methodology for determining the geometric center and edges of a lane using intensity scans from a downward-facing LiDAR. This method is particularly useful for creating a baseline reference path for map building or autonomous vehicle control in path-following scenarios. For this work, each laser scan is sequentially aligned to create a top-down, bird's-eye view image of the road. Using image processing techniques, including image thresholding and the Hough Transform, the lane markers are extracted. All scans are re-aligned by the painted lanes under the assumption that the painted lines are continuous and linear in lane centerline s-coordinate. The extrema (peaks and valleys) of each LiDAR intensity profile in the lateral direction are extracted using an optimal extrema filter to determine the location of the painted lane markers. The lane center is determined by averaging the post-processed and aligned left and right lane marker positions. The algorithm is experimentally validated over multiple traversals of a one-mile test track with ground truth validation using a differential GPS. Over repeated traversals, the geometric center of the lane is determined to a lateral error (1-σ) of 7 mm. The results suggest that this process could be used as a validation step for roadway design specifications, to assess lane-keeping variation errors in human- and computer-driven vehicles, to assess situation- and location-specific repeated deviations from lane center, and to even evaluate the smoothness of the lane-painting process.

Original languageEnglish (US)
Title of host publication2018 IEEE Conference on Control Technology and Applications, CCTA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1133-1138
Number of pages6
ISBN (Electronic)9781538676981
DOIs
StatePublished - Oct 26 2018
Event2nd IEEE Conference on Control Technology and Applications, CCTA 2018 - Copenhagen, Denmark
Duration: Aug 21 2018Aug 24 2018

Publication series

Name2018 IEEE Conference on Control Technology and Applications, CCTA 2018

Other

Other2nd IEEE Conference on Control Technology and Applications, CCTA 2018
CountryDenmark
CityCopenhagen
Period8/21/188/24/18

Fingerprint

Lidar
Extremum
Lateral
Path Following
Facings
Hough Transform
Hough transforms
Autonomous Vehicles
Painting
Thresholding
Averaging
Global positioning system
Baseline
Smoothness
Image Processing
Image processing
Deviation
Filter
Specification
Laser

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Control and Optimization
  • Automotive Engineering
  • Safety, Risk, Reliability and Quality

Cite this

Leary, R. D., & Brennan, S. N. (2018). Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features. In 2018 IEEE Conference on Control Technology and Applications, CCTA 2018 (pp. 1133-1138). [8511347] (2018 IEEE Conference on Control Technology and Applications, CCTA 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCTA.2018.8511347
Leary, Robert D. ; Brennan, Sean N. / Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features. 2018 IEEE Conference on Control Technology and Applications, CCTA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1133-1138 (2018 IEEE Conference on Control Technology and Applications, CCTA 2018).
@inproceedings{cb7058c1b56d47ac8469575499917063,
title = "Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features",
abstract = "This paper presents a methodology for determining the geometric center and edges of a lane using intensity scans from a downward-facing LiDAR. This method is particularly useful for creating a baseline reference path for map building or autonomous vehicle control in path-following scenarios. For this work, each laser scan is sequentially aligned to create a top-down, bird's-eye view image of the road. Using image processing techniques, including image thresholding and the Hough Transform, the lane markers are extracted. All scans are re-aligned by the painted lanes under the assumption that the painted lines are continuous and linear in lane centerline s-coordinate. The extrema (peaks and valleys) of each LiDAR intensity profile in the lateral direction are extracted using an optimal extrema filter to determine the location of the painted lane markers. The lane center is determined by averaging the post-processed and aligned left and right lane marker positions. The algorithm is experimentally validated over multiple traversals of a one-mile test track with ground truth validation using a differential GPS. Over repeated traversals, the geometric center of the lane is determined to a lateral error (1-σ) of 7 mm. The results suggest that this process could be used as a validation step for roadway design specifications, to assess lane-keeping variation errors in human- and computer-driven vehicles, to assess situation- and location-specific repeated deviations from lane center, and to even evaluate the smoothness of the lane-painting process.",
author = "Leary, {Robert D.} and Brennan, {Sean N.}",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/CCTA.2018.8511347",
language = "English (US)",
series = "2018 IEEE Conference on Control Technology and Applications, CCTA 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1133--1138",
booktitle = "2018 IEEE Conference on Control Technology and Applications, CCTA 2018",
address = "United States",

}

Leary, RD & Brennan, SN 2018, Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features. in 2018 IEEE Conference on Control Technology and Applications, CCTA 2018., 8511347, 2018 IEEE Conference on Control Technology and Applications, CCTA 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1133-1138, 2nd IEEE Conference on Control Technology and Applications, CCTA 2018, Copenhagen, Denmark, 8/21/18. https://doi.org/10.1109/CCTA.2018.8511347

Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features. / Leary, Robert D.; Brennan, Sean N.

2018 IEEE Conference on Control Technology and Applications, CCTA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1133-1138 8511347 (2018 IEEE Conference on Control Technology and Applications, CCTA 2018).

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

TY - GEN

T1 - Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features

AU - Leary, Robert D.

AU - Brennan, Sean N.

PY - 2018/10/26

Y1 - 2018/10/26

N2 - This paper presents a methodology for determining the geometric center and edges of a lane using intensity scans from a downward-facing LiDAR. This method is particularly useful for creating a baseline reference path for map building or autonomous vehicle control in path-following scenarios. For this work, each laser scan is sequentially aligned to create a top-down, bird's-eye view image of the road. Using image processing techniques, including image thresholding and the Hough Transform, the lane markers are extracted. All scans are re-aligned by the painted lanes under the assumption that the painted lines are continuous and linear in lane centerline s-coordinate. The extrema (peaks and valleys) of each LiDAR intensity profile in the lateral direction are extracted using an optimal extrema filter to determine the location of the painted lane markers. The lane center is determined by averaging the post-processed and aligned left and right lane marker positions. The algorithm is experimentally validated over multiple traversals of a one-mile test track with ground truth validation using a differential GPS. Over repeated traversals, the geometric center of the lane is determined to a lateral error (1-σ) of 7 mm. The results suggest that this process could be used as a validation step for roadway design specifications, to assess lane-keeping variation errors in human- and computer-driven vehicles, to assess situation- and location-specific repeated deviations from lane center, and to even evaluate the smoothness of the lane-painting process.

AB - This paper presents a methodology for determining the geometric center and edges of a lane using intensity scans from a downward-facing LiDAR. This method is particularly useful for creating a baseline reference path for map building or autonomous vehicle control in path-following scenarios. For this work, each laser scan is sequentially aligned to create a top-down, bird's-eye view image of the road. Using image processing techniques, including image thresholding and the Hough Transform, the lane markers are extracted. All scans are re-aligned by the painted lanes under the assumption that the painted lines are continuous and linear in lane centerline s-coordinate. The extrema (peaks and valleys) of each LiDAR intensity profile in the lateral direction are extracted using an optimal extrema filter to determine the location of the painted lane markers. The lane center is determined by averaging the post-processed and aligned left and right lane marker positions. The algorithm is experimentally validated over multiple traversals of a one-mile test track with ground truth validation using a differential GPS. Over repeated traversals, the geometric center of the lane is determined to a lateral error (1-σ) of 7 mm. The results suggest that this process could be used as a validation step for roadway design specifications, to assess lane-keeping variation errors in human- and computer-driven vehicles, to assess situation- and location-specific repeated deviations from lane center, and to even evaluate the smoothness of the lane-painting process.

UR - http://www.scopus.com/inward/record.url?scp=85056899241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056899241&partnerID=8YFLogxK

U2 - 10.1109/CCTA.2018.8511347

DO - 10.1109/CCTA.2018.8511347

M3 - Conference contribution

AN - SCOPUS:85056899241

T3 - 2018 IEEE Conference on Control Technology and Applications, CCTA 2018

SP - 1133

EP - 1138

BT - 2018 IEEE Conference on Control Technology and Applications, CCTA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Leary RD, Brennan SN. Extracting Geometric Road Centerline and Lane Edges from Single-Scan LiDAR Intensity Using Optimally Filtered Extrema Features. In 2018 IEEE Conference on Control Technology and Applications, CCTA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1133-1138. 8511347. (2018 IEEE Conference on Control Technology and Applications, CCTA 2018). https://doi.org/10.1109/CCTA.2018.8511347