Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)

<Previous Article In Volume
Next Article In Volume>

Deep Learning for Agricultural Crime Prevention: YOLOv8-x for Real-Time Durian Theft Detection in Low-Light Conditions

Authors
I Nyoman Eddy Indrayana1, *, Gde Brahupadhya Subiksa1, Putu Indah Ciptayani1, I Wayan Suasnawa1, I Putu Sutawinaya2
1Information Technology Department, Politeknik Negeri Bali, Bali, Indonesia
2Electrical Engineering Department, Politeknik Negeri Bali, Bali, Indonesia
*Corresponding author. Email: eddyindrayana@pnb.ac.id
Corresponding Author
I Nyoman Eddy Indrayana
Available Online 31 October 2025.
DOI
10.2991/978-94-6463-878-3_16How to use a DOI?
Keywords
Deep Learning; Durian Theft Detection; Yolov8
Abstract

Nocturnal durian theft poses a significant challenge for farmers, leading to substantial economic losses. This research proposes a deep learning approach for night-time durian theft detection, leveraging the capabilities of the YOLOv8 object detection network. A unique dataset was collected in a nocturnal environment, simulating actual theft scenarios, including actors carrying tools like sickles and sacks, with their faces obscured by cloth and hats. This presented complex detection challenges. To optimize detection performance under these demanding conditions, various YOLOv8 variants (n, s, m, l, and x) were extensively evaluated. Experimental results consistently show that YOLOv8-x achieved the best detection performance, with the highest mean Average Precision (mAP) compared to other variants. These findings highlight the potential of YOLOv8-x as an effective and robust solution for preventing nocturnal durian theft, contributing to enhanced agricultural security and mitigating losses for farmers. This study paves the way for developing computer vision-based early warning systems to protect agricultural assets.

Copyright
© 2025 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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
Series
Advances in Engineering Research
Publication Date
31 October 2025
ISBN
978-94-6463-878-3
ISSN
2352-5401
DOI
10.2991/978-94-6463-878-3_16How to use a DOI?
Copyright
© 2025 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

risenwbib
TY  - CONF
AU  - I Nyoman Eddy Indrayana
AU  - Gde Brahupadhya Subiksa
AU  - Putu Indah Ciptayani
AU  - I Wayan Suasnawa
AU  - I Putu Sutawinaya
PY  - 2025
DA  - 2025/10/31
TI  - Deep Learning for Agricultural Crime Prevention: YOLOv8-x for Real-Time Durian Theft Detection in Low-Light Conditions
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 133
EP  - 141
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_16
DO  - 10.2991/978-94-6463-878-3_16
ID  - Indrayana2025
ER  -