Proceedings of the second International Conference on Resources and Technology (RESAT 2023)

Development of Wide-Area Mineral Identification System Using Multispectral Camera Mounted on Drone for Beach Placer Deposits

Authors
Hiromasa Nozaki1, *, Natsuo Okada1, Brian Bino Sinaice2, Yoko Otomo3, Youhei Kawamura3
1Graduate School of Engineering, Hokkaido University, Kita13, Nishi8, Kita-ku, Sapporo, Hokkaido, 060-8628, Japan
2Graduate school of International Resource Sciences, Akita University, 1-1 Tegata-gakuenmachi, Akita, Akita Prefecture, 010-8502, Japan
3Faculty of Engineering, Hokkaido University, Kita13, Nishi8, Kita-ku, Sapporo, Hokkaido, 060-8628, Japan
*Corresponding author.
Corresponding Author
Hiromasa Nozaki
Available Online 31 December 2023.
DOI
10.2991/978-94-6463-318-4_17How to use a DOI?
Keywords
Smart mining; Surface mining; Multispectral; Deep learning; Drone; Placer deposit; Iron sand; Mineral sand
Abstract

Iron sand, a valuable mineral found in placer deposits, is difficult to identify and extract due to the constantly changing nature of beach placer deposits. Traditional visible light cameras mounted on drones are insufficient for identifying specific rocks and minerals. However, hyperspectral cameras provide more comprehensive assessments but can be bulky and time-consuming for data processing. A recent approach involving specialized multispectral bands has emerged as a solution to the disadvantages of hyperspectral imaging. This study proposes using a 6-band DJI P4 multispectral drone and Convolutional Neural Networks (CNN) to automatically identify the composition of mineral sand from the placer deposit located in Kunisaki peninsula, Japan. The combination of multispectral imaging and deep learning techniques has the potential to optimize several aspects of the mining chain, making it an attractive area of research. This study aims to evaluate an efficient approach for the automatic identification of mineral sand composition, using a commercial drone equipped with a multispectral camera, driving towards a more efficient and accurate mineral exploration and extraction processes for the mining industry.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the second International Conference on Resources and Technology (RESAT 2023)
Series
Advances in Engineering Research
Publication Date
31 December 2023
ISBN
10.2991/978-94-6463-318-4_17
ISSN
2352-5401
DOI
10.2991/978-94-6463-318-4_17How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Hiromasa Nozaki
AU  - Natsuo Okada
AU  - Brian Bino Sinaice
AU  - Yoko Otomo
AU  - Youhei Kawamura
PY  - 2023
DA  - 2023/12/31
TI  - Development of Wide-Area Mineral Identification System Using Multispectral Camera Mounted on Drone for Beach Placer Deposits
BT  - Proceedings of the second International Conference on Resources and Technology (RESAT 2023)
PB  - Atlantis Press
SP  - 214
EP  - 232
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-318-4_17
DO  - 10.2991/978-94-6463-318-4_17
ID  - Nozaki2023
ER  -