Registration of RGB and Thermal Point Clouds Generated by Structure from Motion

Trong Phuc Truong, Masahiro Yamaguchi, Shohei Mori, Vincent Nozick, Hideo Saito

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

4 Citations (Scopus)

Abstract

Thermal imaging has become a valuable tool in various fields for remote sensing and can provide relevant information to perform object recognition or classification. In this paper, we present an automated method to obtain a 3D model fusing data from a visible and a thermal camera. The RGB and thermal point clouds are generated independently by structure from motion. The registration process includes a normalization of the point cloud scale, a global registration based on calibration data and the output of the structure from motion, and a fine registration employing a variant of the Iterative Closest Point optimization. Experimental results demonstrate the accuracy and robustness of the overall process.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages419-427
Number of pages9
Volume2018-January
ISBN (Electronic)9781538610343
DOIs
Publication statusPublished - 2018 Jan 19
Externally publishedYes
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: 2017 Oct 222017 Oct 29

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
CountryItaly
CityVenice
Period17/10/2217/10/29

Fingerprint

Object recognition
Infrared imaging
Remote sensing
Cameras
Calibration
Hot Temperature

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Truong, T. P., Yamaguchi, M., Mori, S., Nozick, V., & Saito, H. (2018). Registration of RGB and Thermal Point Clouds Generated by Structure from Motion. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 (Vol. 2018-January, pp. 419-427). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2017.57

Registration of RGB and Thermal Point Clouds Generated by Structure from Motion. / Truong, Trong Phuc; Yamaguchi, Masahiro; Mori, Shohei; Nozick, Vincent; Saito, Hideo.

Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 419-427.

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

Truong, TP, Yamaguchi, M, Mori, S, Nozick, V & Saito, H 2018, Registration of RGB and Thermal Point Clouds Generated by Structure from Motion. in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 419-427, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 17/10/22. https://doi.org/10.1109/ICCVW.2017.57
Truong TP, Yamaguchi M, Mori S, Nozick V, Saito H. Registration of RGB and Thermal Point Clouds Generated by Structure from Motion. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 419-427 https://doi.org/10.1109/ICCVW.2017.57
Truong, Trong Phuc ; Yamaguchi, Masahiro ; Mori, Shohei ; Nozick, Vincent ; Saito, Hideo. / Registration of RGB and Thermal Point Clouds Generated by Structure from Motion. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 419-427
@inproceedings{5eb3cab7c53a4ff5909009f8a777c53f,
title = "Registration of RGB and Thermal Point Clouds Generated by Structure from Motion",
abstract = "Thermal imaging has become a valuable tool in various fields for remote sensing and can provide relevant information to perform object recognition or classification. In this paper, we present an automated method to obtain a 3D model fusing data from a visible and a thermal camera. The RGB and thermal point clouds are generated independently by structure from motion. The registration process includes a normalization of the point cloud scale, a global registration based on calibration data and the output of the structure from motion, and a fine registration employing a variant of the Iterative Closest Point optimization. Experimental results demonstrate the accuracy and robustness of the overall process.",
author = "Truong, {Trong Phuc} and Masahiro Yamaguchi and Shohei Mori and Vincent Nozick and Hideo Saito",
year = "2018",
month = "1",
day = "19",
doi = "10.1109/ICCVW.2017.57",
language = "English",
volume = "2018-January",
pages = "419--427",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Registration of RGB and Thermal Point Clouds Generated by Structure from Motion

AU - Truong, Trong Phuc

AU - Yamaguchi, Masahiro

AU - Mori, Shohei

AU - Nozick, Vincent

AU - Saito, Hideo

PY - 2018/1/19

Y1 - 2018/1/19

N2 - Thermal imaging has become a valuable tool in various fields for remote sensing and can provide relevant information to perform object recognition or classification. In this paper, we present an automated method to obtain a 3D model fusing data from a visible and a thermal camera. The RGB and thermal point clouds are generated independently by structure from motion. The registration process includes a normalization of the point cloud scale, a global registration based on calibration data and the output of the structure from motion, and a fine registration employing a variant of the Iterative Closest Point optimization. Experimental results demonstrate the accuracy and robustness of the overall process.

AB - Thermal imaging has become a valuable tool in various fields for remote sensing and can provide relevant information to perform object recognition or classification. In this paper, we present an automated method to obtain a 3D model fusing data from a visible and a thermal camera. The RGB and thermal point clouds are generated independently by structure from motion. The registration process includes a normalization of the point cloud scale, a global registration based on calibration data and the output of the structure from motion, and a fine registration employing a variant of the Iterative Closest Point optimization. Experimental results demonstrate the accuracy and robustness of the overall process.

UR - http://www.scopus.com/inward/record.url?scp=85046279450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046279450&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2017.57

DO - 10.1109/ICCVW.2017.57

M3 - Conference contribution

AN - SCOPUS:85046279450

VL - 2018-January

SP - 419

EP - 427

BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -