Marker-less AR system based on line segment feature

Yusuke Nakayama, Hideo Saito, Masayoshi Shimizu, Nobuyasu Yamaguchi

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

3 Citations (Scopus)

Abstract

We propose a method of marker-less AR which uses line segment feature. Estimating camera poses is important part of AR system. In most of conventional marker-less AR system, feature point matching between a model and its image is required for the camera pose estimation. However, a sufficient number of correspondence points is not always detected to estimate accurate camera poses. To solve this problem, we propose the use of line segments feature that can possibly be detected even when only a few feature points can be detected. In this paper, we propose a marker-less AR system that uses line segment features for camera pose estimation. In this system, we propose a novel descriptor of the line segment feature for achieving fast computation of the camera pose estimation. We also construct a database which contains a k-d tree of line feature and 3D line segment position for finding 2D-3D line segment correspondences from input image and the database, so that we can estimate the camera pose and perform AR. We demonstrated that our proposed method can estimate the camera pose and provide robust marker-less AR in the situation where point matching method fails.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSPIE
Volume9392
ISBN (Print)9781628414820
DOIs
Publication statusPublished - 2015
EventEngineering Reality of Virtual Reality 2015 - San Francisco, United States
Duration: 2015 Feb 92015 Feb 10

Other

OtherEngineering Reality of Virtual Reality 2015
CountryUnited States
CitySan Francisco
Period15/2/915/2/10

Fingerprint

Line segment
markers
Camera
Cameras
cameras
Pose Estimation
Feature Point
Correspondence
estimates
Estimate
boundary value problems
Descriptors
estimating
Sufficient
Line

Keywords

  • Line segment
  • Line segment feature
  • Line segment matching
  • Marker-less AR
  • The camera pose estimation

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Nakayama, Y., Saito, H., Shimizu, M., & Yamaguchi, N. (2015). Marker-less AR system based on line segment feature. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 9392). [93920I] SPIE. https://doi.org/10.1117/12.2083673

Marker-less AR system based on line segment feature. / Nakayama, Yusuke; Saito, Hideo; Shimizu, Masayoshi; Yamaguchi, Nobuyasu.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9392 SPIE, 2015. 93920I.

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

Nakayama, Y, Saito, H, Shimizu, M & Yamaguchi, N 2015, Marker-less AR system based on line segment feature. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 9392, 93920I, SPIE, Engineering Reality of Virtual Reality 2015, San Francisco, United States, 15/2/9. https://doi.org/10.1117/12.2083673
Nakayama Y, Saito H, Shimizu M, Yamaguchi N. Marker-less AR system based on line segment feature. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9392. SPIE. 2015. 93920I https://doi.org/10.1117/12.2083673
Nakayama, Yusuke ; Saito, Hideo ; Shimizu, Masayoshi ; Yamaguchi, Nobuyasu. / Marker-less AR system based on line segment feature. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9392 SPIE, 2015.
@inproceedings{d75c1b969c11488eb96b950b035a114c,
title = "Marker-less AR system based on line segment feature",
abstract = "We propose a method of marker-less AR which uses line segment feature. Estimating camera poses is important part of AR system. In most of conventional marker-less AR system, feature point matching between a model and its image is required for the camera pose estimation. However, a sufficient number of correspondence points is not always detected to estimate accurate camera poses. To solve this problem, we propose the use of line segments feature that can possibly be detected even when only a few feature points can be detected. In this paper, we propose a marker-less AR system that uses line segment features for camera pose estimation. In this system, we propose a novel descriptor of the line segment feature for achieving fast computation of the camera pose estimation. We also construct a database which contains a k-d tree of line feature and 3D line segment position for finding 2D-3D line segment correspondences from input image and the database, so that we can estimate the camera pose and perform AR. We demonstrated that our proposed method can estimate the camera pose and provide robust marker-less AR in the situation where point matching method fails.",
keywords = "Line segment, Line segment feature, Line segment matching, Marker-less AR, The camera pose estimation",
author = "Yusuke Nakayama and Hideo Saito and Masayoshi Shimizu and Nobuyasu Yamaguchi",
year = "2015",
doi = "10.1117/12.2083673",
language = "English",
isbn = "9781628414820",
volume = "9392",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",

}

TY - GEN

T1 - Marker-less AR system based on line segment feature

AU - Nakayama, Yusuke

AU - Saito, Hideo

AU - Shimizu, Masayoshi

AU - Yamaguchi, Nobuyasu

PY - 2015

Y1 - 2015

N2 - We propose a method of marker-less AR which uses line segment feature. Estimating camera poses is important part of AR system. In most of conventional marker-less AR system, feature point matching between a model and its image is required for the camera pose estimation. However, a sufficient number of correspondence points is not always detected to estimate accurate camera poses. To solve this problem, we propose the use of line segments feature that can possibly be detected even when only a few feature points can be detected. In this paper, we propose a marker-less AR system that uses line segment features for camera pose estimation. In this system, we propose a novel descriptor of the line segment feature for achieving fast computation of the camera pose estimation. We also construct a database which contains a k-d tree of line feature and 3D line segment position for finding 2D-3D line segment correspondences from input image and the database, so that we can estimate the camera pose and perform AR. We demonstrated that our proposed method can estimate the camera pose and provide robust marker-less AR in the situation where point matching method fails.

AB - We propose a method of marker-less AR which uses line segment feature. Estimating camera poses is important part of AR system. In most of conventional marker-less AR system, feature point matching between a model and its image is required for the camera pose estimation. However, a sufficient number of correspondence points is not always detected to estimate accurate camera poses. To solve this problem, we propose the use of line segments feature that can possibly be detected even when only a few feature points can be detected. In this paper, we propose a marker-less AR system that uses line segment features for camera pose estimation. In this system, we propose a novel descriptor of the line segment feature for achieving fast computation of the camera pose estimation. We also construct a database which contains a k-d tree of line feature and 3D line segment position for finding 2D-3D line segment correspondences from input image and the database, so that we can estimate the camera pose and perform AR. We demonstrated that our proposed method can estimate the camera pose and provide robust marker-less AR in the situation where point matching method fails.

KW - Line segment

KW - Line segment feature

KW - Line segment matching

KW - Marker-less AR

KW - The camera pose estimation

UR - http://www.scopus.com/inward/record.url?scp=84928473660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928473660&partnerID=8YFLogxK

U2 - 10.1117/12.2083673

DO - 10.1117/12.2083673

M3 - Conference contribution

AN - SCOPUS:84928473660

SN - 9781628414820

VL - 9392

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - SPIE

ER -