Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF

Yusuke Nakayama, Toshihiro Honda, Hideo Saito, Masayoshi Shimizu, Nobuyasu Yamaguchi

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

12 Citations (Scopus)

Abstract

Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2149-2154
Number of pages6
ISBN (Print)9781479952083
DOIs
Publication statusPublished - 2014 Dec 4
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: 2014 Aug 242014 Aug 28

Other

Other22nd International Conference on Pattern Recognition, ICPR 2014
CountrySweden
CityStockholm
Period14/8/2414/8/28

Fingerprint

Fusion reactions
Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Nakayama, Y., Honda, T., Saito, H., Shimizu, M., & Yamaguchi, N. (2014). Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF. In Proceedings - International Conference on Pattern Recognition (pp. 2149-2154). [6977086] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2014.374

Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF. / Nakayama, Yusuke; Honda, Toshihiro; Saito, Hideo; Shimizu, Masayoshi; Yamaguchi, Nobuyasu.

Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2149-2154 6977086.

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

Nakayama, Y, Honda, T, Saito, H, Shimizu, M & Yamaguchi, N 2014, Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF. in Proceedings - International Conference on Pattern Recognition., 6977086, Institute of Electrical and Electronics Engineers Inc., pp. 2149-2154, 22nd International Conference on Pattern Recognition, ICPR 2014, Stockholm, Sweden, 14/8/24. https://doi.org/10.1109/ICPR.2014.374
Nakayama Y, Honda T, Saito H, Shimizu M, Yamaguchi N. Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF. In Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2149-2154. 6977086 https://doi.org/10.1109/ICPR.2014.374
Nakayama, Yusuke ; Honda, Toshihiro ; Saito, Hideo ; Shimizu, Masayoshi ; Yamaguchi, Nobuyasu. / Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF. Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 2149-2154
@inproceedings{547f157c76594ebc87930c4ec8d3bef5,
title = "Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF",
abstract = "Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.",
author = "Yusuke Nakayama and Toshihiro Honda and Hideo Saito and Masayoshi Shimizu and Nobuyasu Yamaguchi",
year = "2014",
month = "12",
day = "4",
doi = "10.1109/ICPR.2014.374",
language = "English",
isbn = "9781479952083",
pages = "2149--2154",
booktitle = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF

AU - Nakayama, Yusuke

AU - Honda, Toshihiro

AU - Saito, Hideo

AU - Shimizu, Masayoshi

AU - Yamaguchi, Nobuyasu

PY - 2014/12/4

Y1 - 2014/12/4

N2 - Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.

AB - Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.

UR - http://www.scopus.com/inward/record.url?scp=84919910802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919910802&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2014.374

DO - 10.1109/ICPR.2014.374

M3 - Conference contribution

SN - 9781479952083

SP - 2149

EP - 2154

BT - Proceedings - International Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

ER -