Discrimination of Plant Structures in 3D Point Cloud Through Back-Projection of Labels Derived from 2D Semantic Segmentation-Reference-Cited by-同舟云学术

Discrimination of Plant Structures in 3D Point Cloud Through Back-Projection of Labels Derived from 2D Semantic Segmentation

Published:2024-02-20 Issue:1 Volume:36 Page:63-70
ISSN:1883-8049
Container-title:Journal of Robotics and Mechatronics
language:en
Short-container-title:JRM

Author:

Imabuchi Takashi¹, ,Kawabata Kuniaki¹^ORCID

Affiliation:

1. Spatial Information Creation and Control System Group, Collaborative Laboratories for Advanced Decommissioning Science (CLADS), Japan Atomic Energy Agency (JAEA), 1-22 Nakamaru, Yamadaoka, Naraha-machi, Futaba-gun, Fukushima 979-0513, Japan

Abstract

In the decommissioning of the Fukushima Daiichi Nuclear Power Station, radiation dose calculations necessitate a 3D model of the workspace are performed to determine suitable measures for reducing exposure. However, the construction of a 3D model from a 3D point cloud is a costly endeavor. To separate the geometrical shape regions on 3D point cloud, we are developing a structure discrimination method using 3D and 2D deep learning to contribute to the advancement of 3D modeling automation technology. In this paper, we present a method for transferring and fusing labels to handle 2D prediction labels in 3D space. We propose an exhaustive label fusion method designed for plant facilities with intricate structures. Through evaluation on a mock-up plant dataset, we confirmed the method’s effective performance.

Publisher

Fuji Technology Press Ltd.

Reference21 articles.

1. I. Szőke, M. N. Louka, T. R. Bryntesen, J. Bratteli, S. T. Edvardsen, K. K. RøEitrheim, and K. Bodor, “Real-time 3D radiation risk assessment supporting simulation of work in nuclear environments,” J. of Radiological Protection., Vol.34, No.2, pp. 389-416, 2014. https://doi.org/10.1088/0952-4746/34/2/389

2. J. Lee, G.-H. Kim, I. Kim, D. Hyun, K. S. Jeong, B.-S. Choi, and J. Moon, “Establishment of the framework to visualize the space dose rates on the dismantling simulation system based on a digital manufacturing platform,” Annals of Nuclear Energy, Vol.95, pp. 161-167, 2016. https://doi.org/10.1016/j.anucene.2016.05.013

3. T. Imabuchi, Y. Tanifuji, and K. Kawabata, “Discrimination of the Structures in Nuclear Facility by Deep Learning Based on 3D Point Cloud Data,” Proc. of the 2022 IEEE/SICE Int. Symp. on System Integration (SII 2022), pp. 1036-1040, 2022. https://doi.org/10.1109/SII52469.2022.9708845

4. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “PointNet: Deep learning on point sets for 3D classification and segmentation,” Proc. of the 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 77-85, 2017. https://doi.org/10.1109/CVPR.2017.16

5. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “PointNet++: Deep hierarchical feature learning on point sets in a metric space,” arXiv:1706.02413, 2017. https://doi.org/10.48550/arXiv.1706.02413