Evaluasi Trade-off Akurasi dan Kecepatan YOLOv5 dalam Deteksi Kebakaran pada Edge Devices
Main Article Content
Real-time object detection using the YOLO (You Only Look Once) algorithm has shown promising performance in various computer vision applications. However, its application on devices with limited resources is still a challenge due to its high computational requirements. This study aims to optimize the YOLOv5 model for fire and smoke detection on Orange Pi Zero 3 devices using quantization techniques. Using a dataset of 2247 fire and smoke images, this study applies static quantization techniques to improve model efficiency. The methodology includes training of standard YOLOv5 models, conversion to ONNX format, and application of static quantization. Results show a significant improvement in computational efficiency, with a 42.2% reduction in model size and a 65.21% increase in inference speed. Despite a decrease in the mAP value by 25.6%, the optimized model was still able to perform object detection at a significantly higher speed. In conclusion, the quantization technique is effective in optimizing the YOLOv5 model for deployment on edge computing devices, despite the trade-off between speed and accuracy.
Casas, E., Ramos, L., Bendek, E., & Rivas-Echeverria, F. (2024). YOLOv5 vs. YOLOv8: Performance Benchmarking in Wildfire and Smoke Detection Scenarios. Journal of Image and Graphics, 12(2). https://doi.org/10.18178/joig.12.2.127-136.
Fang, W., Wang, L., & Ren, P. (2019). Tinier-YOLO: A real-time object detection method for constrained environments. Ieee Access, 8, 1935–1944. https://doi.org/10.1109/ACCESS.2019.2961959.
Jani, M., Fayyad, J., Al-Younes, Y., & Najjaran, H. (2023). Model compression methods for YOLOv5: A review. ArXiv Preprint ArXiv:2307.11904.
Johnson, S. J., Blackman, D. A., & Buick, F. (2018). The 70: 20: 10 framework and the transfer of learning. Human Resource Development Quarterly, 29(4), 383–402.
Li, T., Ma, Y., & Endoh, T. (2020). A systematic study of tiny YOLO3 inference: Toward compact brainware processor with less memory and logic gate. IEEE Access, 8, 142931–142955. https://doi.org/10.1109/ACCESS.2020.3013934.
Li, Z., Wang, Y., Chen, K., & Yu, Z. (2022). Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection. ArXiv Preprint ArXiv:2204.13699.
Nalbant, K. G., & Uyanık, Ş. (2021). Computer vision in the metaverse. Journal of Metaverse, 1(1), 9–12.
Nguyen, D. T., Nguyen, T. N., Kim, H., & Lee, H.-J. (2019). A high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 27(8), 1861–1873. https://doi.org/10.1109/TVLSI.2019.2905242.
Putri, A. R., Dewi, R., & Ramiati, R. (2024). Penerapan Metode Yolov5 dan Teknologi Text-To-Speech dalam Aplikasi Pengenalan Abjad dan Objek Sekitar untuk Anak Usia Dini. Elektron: Jurnal Ilmiah, 94–101.
Sary, I. P., Andromeda, S., & Armin, E. U. (2023). Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection using Aerial Images. Ultima Computing: Jurnal Sistem Komputer, 15(1), 8–13. https://doi.org/10.1109/CVPR.2016.91.
Sholahuddin, M. R., Harika, M., Awaludin, I., Dewi, Y. C., Fauzan, F. D., Sudimulya, B. P., & Widarta, V. P. (2023). Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy. Jurnal Online Informatika, 8(2), 261–270. https://doi.org/10.15575/join.v8i2.1196.
Wahyudi, A. A., Khumaidi, A., Rahmat, M. B., Riananda, D. P., Syai’in, M., & Endrasmono, J. (2024). Implementasi Robot Operating System (ROS) Untuk Meningkatkan Akurasi Deteksi Bola Menggunakan YOLO V5 Pada KRSBI-Beroda. Jurnal Elektronika Dan Otomasi Industri, 11(2), 590–603.
Wang, M., Sun, H., Shi, J., Liu, X., Cao, X., Zhang, L., & Zhang, B. (2023). Q-YOLO: Efficient inference for real-time object detection. Asian Conference on Pattern Recognition, 307–321.
Yusup, R. M., Anugrah, A. F., Muslimah, D. D., Permana, S. M. W. N., & Yuliani, S. (2024). PENDETEKSIAN OBJEK MENGGUNAKAN OPENCV DAN METODE YOLOv4-TINY UNTUK MEMBANTU TUNANETRA. Journal of Computer Science and Information Technology, 1(2), 59–68.
