Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment

Zongrun Tang; Yingyi Liu; Baoqin Cao; Hongjing Liu; Nan He; Haoyu Song; Lili Zhao

doi:10.3233/ATDE260277

Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment

Zongrun Tang
, Yingyi Liu^*
, Baoqin Cao
, Hongjing Liu
, Nan He
, Haoyu Song
, Lili Zhao

^*Corresponding author for this work

School of Automation Science and Electrical Engineering

Beihang University
Beijing Electric Power Company

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

With smart grid development, intelligent substation operation and maintenance (O&M) demands advanced equipment monitoring. Though infrared thermography effectively captures temperatures, its 2D nature limits spatial context and complicates fault localization. This paper studies 2D infrared data and 3D point cloud matching/fusion for substation equipment. We map 2D pixels to 3D coordinates via camera calibration and pose estimation, then propose a modified two-stage registration algorithm: a dynamic asymmetric four-point set (DA-4PCS) for efficient coarse registration and a region-corresponding iterative closest point (RC-ICP) for accurate fine registration. A 3D temperature field is constructed using fused temporal data, enabling dynamic digital twin integration. Experiments show high-precision fusion (200ms mapping), transitioning from 2D to 3D perception and supporting intelligent O&M.

Original language	English
Title of host publication	Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025
Editors	Isabel S. Jesus, Ke Wang
Publisher	IOS Press BV
Pages	660-670
Number of pages	11
ISBN (Electronic)	9781643686561
DOIs	https://doi.org/10.3233/ATDE260277
State	Published - 13 Mar 2026
Event	2nd Annual International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2025 - Wuhan, China Duration: 12 Dec 2025 → 14 Dec 2025

Publication series

Name	Advances in Transdisciplinary Engineering
Volume	91
ISSN (Print)	2352-751X
ISSN (Electronic)	2352-7528

Conference

Conference	2nd Annual International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2025
Country/Territory	China
City	Wuhan
Period	12/12/25 → 14/12/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

3D point cloud
4PCS algorithm
data fusion
digital twin
ICP algorithm
infrared temperature
substation

Access to Document

10.3233/ATDE260277

Cite this

Tang, Z., Liu, Y., Cao, B., Liu, H., He, N., Song, H., & Zhao, L. (2026). Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment. In I. S. Jesus, & K. Wang (Eds.), Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025 (pp. 660-670). (Advances in Transdisciplinary Engineering; Vol. 91). IOS Press BV. https://doi.org/10.3233/ATDE260277

Tang, Zongrun ; Liu, Yingyi ; Cao, Baoqin et al. / Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment. Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025. editor / Isabel S. Jesus ; Ke Wang. IOS Press BV, 2026. pp. 660-670 (Advances in Transdisciplinary Engineering).

@inproceedings{44e8b819bfce4e19bf71c511089748bc,

title = "Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment",

abstract = "With smart grid development, intelligent substation operation and maintenance (O\&M) demands advanced equipment monitoring. Though infrared thermography effectively captures temperatures, its 2D nature limits spatial context and complicates fault localization. This paper studies 2D infrared data and 3D point cloud matching/fusion for substation equipment. We map 2D pixels to 3D coordinates via camera calibration and pose estimation, then propose a modified two-stage registration algorithm: a dynamic asymmetric four-point set (DA-4PCS) for efficient coarse registration and a region-corresponding iterative closest point (RC-ICP) for accurate fine registration. A 3D temperature field is constructed using fused temporal data, enabling dynamic digital twin integration. Experiments show high-precision fusion (200ms mapping), transitioning from 2D to 3D perception and supporting intelligent O\&M.",

keywords = "3D point cloud, 4PCS algorithm, data fusion, digital twin, ICP algorithm, infrared temperature, substation",

author = "Zongrun Tang and Yingyi Liu and Baoqin Cao and Hongjing Liu and Nan He and Haoyu Song and Lili Zhao",

note = "Publisher Copyright: {\textcopyright} 2026 The Authors.; 2nd Annual International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2025 ; Conference date: 12-12-2025 Through 14-12-2025",

year = "2026",

month = mar,

day = "13",

doi = "10.3233/ATDE260277",

language = "英语",

series = "Advances in Transdisciplinary Engineering",

publisher = "IOS Press BV",

pages = "660--670",

editor = "Jesus, \{Isabel S.\} and Ke Wang",

booktitle = "Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025",

address = "荷兰",

}

Tang, Z, Liu, Y, Cao, B, Liu, H, He, N, Song, H & Zhao, L 2026, Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment. in IS Jesus & K Wang (eds), Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025. Advances in Transdisciplinary Engineering, vol. 91, IOS Press BV, pp. 660-670, 2nd Annual International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2025, Wuhan, China, 12/12/25. https://doi.org/10.3233/ATDE260277

Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment. / Tang, Zongrun; Liu, Yingyi; Cao, Baoqin et al.
Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025. ed. / Isabel S. Jesus; Ke Wang. IOS Press BV, 2026. p. 660-670 (Advances in Transdisciplinary Engineering; Vol. 91).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment

AU - Tang, Zongrun

AU - Liu, Yingyi

AU - Cao, Baoqin

AU - Liu, Hongjing

AU - He, Nan

AU - Song, Haoyu

AU - Zhao, Lili

PY - 2026/3/13

Y1 - 2026/3/13

N2 - With smart grid development, intelligent substation operation and maintenance (O&M) demands advanced equipment monitoring. Though infrared thermography effectively captures temperatures, its 2D nature limits spatial context and complicates fault localization. This paper studies 2D infrared data and 3D point cloud matching/fusion for substation equipment. We map 2D pixels to 3D coordinates via camera calibration and pose estimation, then propose a modified two-stage registration algorithm: a dynamic asymmetric four-point set (DA-4PCS) for efficient coarse registration and a region-corresponding iterative closest point (RC-ICP) for accurate fine registration. A 3D temperature field is constructed using fused temporal data, enabling dynamic digital twin integration. Experiments show high-precision fusion (200ms mapping), transitioning from 2D to 3D perception and supporting intelligent O&M.

AB - With smart grid development, intelligent substation operation and maintenance (O&M) demands advanced equipment monitoring. Though infrared thermography effectively captures temperatures, its 2D nature limits spatial context and complicates fault localization. This paper studies 2D infrared data and 3D point cloud matching/fusion for substation equipment. We map 2D pixels to 3D coordinates via camera calibration and pose estimation, then propose a modified two-stage registration algorithm: a dynamic asymmetric four-point set (DA-4PCS) for efficient coarse registration and a region-corresponding iterative closest point (RC-ICP) for accurate fine registration. A 3D temperature field is constructed using fused temporal data, enabling dynamic digital twin integration. Experiments show high-precision fusion (200ms mapping), transitioning from 2D to 3D perception and supporting intelligent O&M.

KW - 3D point cloud

KW - 4PCS algorithm

KW - data fusion

KW - digital twin

KW - ICP algorithm

KW - infrared temperature

KW - substation

UR - https://www.scopus.com/pages/publications/105035210883

U2 - 10.3233/ATDE260277

DO - 10.3233/ATDE260277

M3 - 会议稿件

AN - SCOPUS:105035210883

T3 - Advances in Transdisciplinary Engineering

SP - 660

EP - 670

BT - Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025

A2 - Jesus, Isabel S.

A2 - Wang, Ke

PB - IOS Press BV

T2 - 2nd Annual International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2025

Y2 - 12 December 2025 through 14 December 2025

ER -

Tang Z, Liu Y, Cao B, Liu H, He N, Song H et al. Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment. In Jesus IS, Wang K, editors, Intelligent Manufacturing and Cloud Computing - Proceedings of the 2nd International Conference, ICIMCC 2025. IOS Press BV. 2026. p. 660-670. (Advances in Transdisciplinary Engineering). doi: 10.3233/ATDE260277

Research on Matching and Fusion Methods for Infrared Temperature Data and 3D Point Cloud Data of Substation Equipment

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this