Implementation of YOLOv8 in a Donation Box Monitoring System for Detecting Potential Theft

Authors

  • Galih Prasetyo Politeknik Negeri Sriwijaya
  • Yurni Oktarina Politeknik Negeri Sriwijaya
  • Abdurrahman Politeknik Negeri Sriwijaya

Keywords:

YOLOv8, Donation box, Security monitoring, Object detection, Raspberry Pi

Abstract

Donation boxes are widely used in mosques and other places of worship to collect funds for social and religious activities. Their accessible locations expose them to theft, while manual surveillance depends on personnel and cannot always be maintained continuously. This study presents a computer vision system for donation box security monitoring that deploys You Only Look Once version 8 (YOLOv8) on a Raspberry Pi 4. A webcam captures images for real-time detection of people and donation boxes. The system assigns four security categories, Safe, Suspicious, Highly Suspicious, and Danger, according to object presence, proximity, and duration. Suspicious activity triggers Telegram notifications accompanied by captured images. The model was trained for 55 epochs using an input image size of 640 × 640 pixels. The reported arithmetic means across the two classes were 70.5% for precision, 84.4% for recall, and 75.7% for the F1 score. System testing demonstrated detection of the defined security conditions and successful delivery of notifications. The implementation supports the feasibility of automated donation box monitoring and early warnings of potential theft under the tested conditions.

Downloads

Download data is not yet available.

References

Alaydrus, S. A. H. M., & Santoso, B. (2024). Development of an Accident Detection System on The Highway Using the YOLOv8 Algorithm and Automatic Notification Via Telegram. The Indonesian Journal of Computer Science, 13(4). https://doi.org/10.33022/ijcs.v13i4.4218.

Ahmad, B., Noon, S. K., Ahmad, T., Mannan, A., Khan, N. I., Ismail, M., & Awan, T. (2024). Efficient Real-Time Detection of Plant Leaf Diseases Using YOLOv8 and Raspberry Pi. VFAST Transactions on Software Engineering, 12(2), 250–259. https://doi.org/10.21015/vtse.v12i2.1869.

Kumar, P., Choudhary, S. K., Pallerla, S., Sangani, S., et al. (2024). Pi-Vision: Leveraging YOLO V8 for Real-Time Person Detection and Recognition on Raspberry Pi. Proceedings of ICDICI 2024. https://doi.org/10.1109/ICDICI62993.2024.10810836.

Yu, G. M., Kim, N. H., & Choi, G. M. (2024). Implementation of an Integrated Management System Using Forklift-Type Autonomous Transport Robots and YOLOv8 Object Detection Technology. Journal of Digital Contents Society, 25(10), 3013–3019. https://doi.org/10.9728/dcs.2024.25.10.3013.

Alzubaidi, L., Zhang, J., Humaidi, A. J., et al. (2021). Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal of Big Data, 8(53). https://doi.org/10.1186/s40537-021-00444-8.

Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. https://doi.org/10.48550/arXiv.2004.10934.

Yao, G., Zhu, S., & Zhang, L. (2024). HP-YOLOv8: High-Precision Small Object Detection Algorithm for Remote Sensing Images. Sensors, 24(15), 4858. https://doi.org/10.3390/s24154858.

Zhang, Y., Liu, H., & Chen, X. (2024). SGST-YOLOv8: An Improved Lightweight YOLOv8 for Real-Time Target Detection for Campus Surveillance. Applied Sciences, 14(12), 5341. https://doi.org/10.3390/app14125341.

Putra, Y. G. P., & Priambodo, A. S. (2024). Eggplant Leaf Diseases Detection and Counting System on Agricultural Robot Based on YOLOv8. JELIKU, 13(2), 227–236. https://doi.org/10.24843/JLK.2024.v13.i02.p01.

Narayana, C. V., Vamsi, K., Pallavi, P., & Dedeepya, G. (2024). Animal Deterrance Using Computer Vision and Raspberry Pi. ICCIET 2024 Proceedings. https://doi.org/10.2991/978-94-6463-471-6_73.

Yu, Y. C., & Kim, D. H. (2024). Implementation of a Smart Window System Controlling a PDLC Film Using an Object Detection Algorithm. Journal of Digital Contents Society, 25(3), 751–760. https://doi.org/10.9728/dcs.2024.25.3.751.

Khalili, B., & Smyth, A. W. (2024). SOD-YOLOv8: Enhancing YOLOv8 for Small Object Detection in Traffic Scenes. https://doi.org/10.48550/arXiv.2408.04786.

Silva, D. A., Smagulova, K., Elsheikh, A., Fouda, M. E., & Eltawil, A. M. (2024). A Recurrent YOLOv8-Based Framework for Event-Based Object Detection. https://doi.org/10.48550/arXiv.2408.05321.

Alqahtani, D. K., Cheema, A., & Toosi, A. N. (2024). Benchmarking Deep Learning Models for Object Detection on Edge Computing Devices. https://doi.org/10.48550/arXiv.2409.16808.

Kang, X., Chen, H. M., Chen, G., Chang, K. C., & Clemons, T. M. (2024). Joint Detection and Classification of Communication and Radar Signals in Congested RF Environments Using YOLOv8. https://doi.org/10.48550/arXiv.2406.00582.

Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2023). Real-Time Flying Object Detection with YOLOv8. https://doi.org/10.48550/arXiv.2305.09972.

Elshamy, M. R., Emara, H. M., Shoaib, M. R., & Badawy, A. A. (2024). P-YOLOv8: Efficient and Accurate Real-Time Detection of Distracted Driving. https://doi.org/10.48550/arXiv.2410.15602.

Rasjid, A. A., Rahmat, B., & Sihananto, A. N. (2024). Implementasi YOLOv8 Pada Robot Deteksi Objek. Journal of Technology and System Information. https://doi.org/10.47134/jtsi.v1i3.2969.

Nugroho, B., Azhar, N. F., Pratama, B. M., et al. (2025). Implementation of Sparrow Pest Detection Using YOLOv8 Method on Raspberry Pi and Google Coral USB Accelerator. Sebatik. https://doi.org/10.46984/sebatik.v29i1.2558.

Mujahidin, S., Kamil, M. I., & Abdullah, R. K. (2024). Pengembangan Deteksi Objek Dalam Rumah Bagi Tunanetra Berbasis Optimasi YOLOv8 Menggunakan Metode Ghost Module dan Attention Mechanism. Jurnal FASILKOM. https://doi.org/10.37859/jf.v14i3.8179.

Published

2026-10-29

How to Cite

Prasetyo, G., Oktarina, Y., & Abdurrahman. (2026). Implementation of YOLOv8 in a Donation Box Monitoring System for Detecting Potential Theft. Journal of Electrical Engineering and Informatics (JEEI), 1(3). Retrieved from https://jurnal.sttnlampung.ac.id/index.php/jeei/article/view/192