Automatic free parking space detection by using motion stereo-based 3D reconstruction

Jae Kyu Suhr, Ho Gi Jung, Kwanghyuk Bae, Jaihie Kim

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

This paper proposes a free parking space detection system by using motion stereo-based 3D reconstruction. An image sequence is acquired with a single rearview fisheye camera and the view behind the automobile is three-dimensionally reconstructed by using point correspondences. Metric information is recovered from the camera height ratio and free parking spaces are detected by estimating the positions of adjacent vehicles. Since adjacent vehicles are usually located near the epipole, their structures are seriously degraded. To solve this problem, we select point correspondences by using a de-rotation-based method and mosaic 3D structures by estimating a similarity transformation. Unlike in previous work, our system proposes an efficient way of locating free parking spaces in 3D point clouds. Odometry is not used because its accuracy depends largely on road conditions. In the experiments, the system was tested in 154 different parking situations and its success rate was 90% (139 successes in 154 cases). The detection accuracy was evaluated by using ground truth data that was acquired with a laser scanner.

Original languageEnglish
Pages (from-to)163-176
Number of pages14
JournalMachine Vision and Applications
Volume21
Issue number2
DOIs
Publication statusPublished - 2010 Feb 1

Fingerprint

Parking
Cameras
Automobiles
Lasers
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Suhr, Jae Kyu ; Jung, Ho Gi ; Bae, Kwanghyuk ; Kim, Jaihie. / Automatic free parking space detection by using motion stereo-based 3D reconstruction. In: Machine Vision and Applications. 2010 ; Vol. 21, No. 2. pp. 163-176.
@article{c153ca46d06f434fb867f5827100a419,
title = "Automatic free parking space detection by using motion stereo-based 3D reconstruction",
abstract = "This paper proposes a free parking space detection system by using motion stereo-based 3D reconstruction. An image sequence is acquired with a single rearview fisheye camera and the view behind the automobile is three-dimensionally reconstructed by using point correspondences. Metric information is recovered from the camera height ratio and free parking spaces are detected by estimating the positions of adjacent vehicles. Since adjacent vehicles are usually located near the epipole, their structures are seriously degraded. To solve this problem, we select point correspondences by using a de-rotation-based method and mosaic 3D structures by estimating a similarity transformation. Unlike in previous work, our system proposes an efficient way of locating free parking spaces in 3D point clouds. Odometry is not used because its accuracy depends largely on road conditions. In the experiments, the system was tested in 154 different parking situations and its success rate was 90{\%} (139 successes in 154 cases). The detection accuracy was evaluated by using ground truth data that was acquired with a laser scanner.",
author = "Suhr, {Jae Kyu} and Jung, {Ho Gi} and Kwanghyuk Bae and Jaihie Kim",
year = "2010",
month = "2",
day = "1",
doi = "10.1007/s00138-008-0156-9",
language = "English",
volume = "21",
pages = "163--176",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "2",

}

Automatic free parking space detection by using motion stereo-based 3D reconstruction. / Suhr, Jae Kyu; Jung, Ho Gi; Bae, Kwanghyuk; Kim, Jaihie.

In: Machine Vision and Applications, Vol. 21, No. 2, 01.02.2010, p. 163-176.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic free parking space detection by using motion stereo-based 3D reconstruction

AU - Suhr, Jae Kyu

AU - Jung, Ho Gi

AU - Bae, Kwanghyuk

AU - Kim, Jaihie

PY - 2010/2/1

Y1 - 2010/2/1

N2 - This paper proposes a free parking space detection system by using motion stereo-based 3D reconstruction. An image sequence is acquired with a single rearview fisheye camera and the view behind the automobile is three-dimensionally reconstructed by using point correspondences. Metric information is recovered from the camera height ratio and free parking spaces are detected by estimating the positions of adjacent vehicles. Since adjacent vehicles are usually located near the epipole, their structures are seriously degraded. To solve this problem, we select point correspondences by using a de-rotation-based method and mosaic 3D structures by estimating a similarity transformation. Unlike in previous work, our system proposes an efficient way of locating free parking spaces in 3D point clouds. Odometry is not used because its accuracy depends largely on road conditions. In the experiments, the system was tested in 154 different parking situations and its success rate was 90% (139 successes in 154 cases). The detection accuracy was evaluated by using ground truth data that was acquired with a laser scanner.

AB - This paper proposes a free parking space detection system by using motion stereo-based 3D reconstruction. An image sequence is acquired with a single rearview fisheye camera and the view behind the automobile is three-dimensionally reconstructed by using point correspondences. Metric information is recovered from the camera height ratio and free parking spaces are detected by estimating the positions of adjacent vehicles. Since adjacent vehicles are usually located near the epipole, their structures are seriously degraded. To solve this problem, we select point correspondences by using a de-rotation-based method and mosaic 3D structures by estimating a similarity transformation. Unlike in previous work, our system proposes an efficient way of locating free parking spaces in 3D point clouds. Odometry is not used because its accuracy depends largely on road conditions. In the experiments, the system was tested in 154 different parking situations and its success rate was 90% (139 successes in 154 cases). The detection accuracy was evaluated by using ground truth data that was acquired with a laser scanner.

UR - http://www.scopus.com/inward/record.url?scp=77649183422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649183422&partnerID=8YFLogxK

U2 - 10.1007/s00138-008-0156-9

DO - 10.1007/s00138-008-0156-9

M3 - Article

VL - 21

SP - 163

EP - 176

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 2

ER -