Fire and Smoke Object Detection Using Mask R-CNN

  • Fathorazi Nur Fajri Universitas Nurul Jadid
  • Syaiful Syaiful Universitas Nurul Jadid
  • Wahyu Galih Priambodo Universitas Nurul Jadid
Keywords: api dan asap, mask rcnn, kebakaran hutan

Abstract

Penelitian ini berfokus pada penggunaan teknologi computer vision, khususnya metode Mask R-CNN, dalam deteksi api dan asap pada kasus kebakaran hutan. Kebakaran hutan adalah masalah lingkungan yang serius, di mana metode deteksi tradisional sering terbatas oleh jangkauan visual dan kesalahan subjektif. Kami mengeksplorasi potensi teknologi computer vision sebagai solusi yang lebih efisien dan akurat. Dataset yang digunakan sebanyak 3465 gambar yang telah dianotasi dengan menggunakan roboflow. Jumlah dataset yang digunakan pada data training 2964 gambar, data validasi 854 gambar dan data testing 427 gambar. Model deteksi api dan asap menggunakan mask rcnn dengan menggunakan parameter learning rate 0.0025, image per batch 2 dan max iteration 10000. Adapun hasil yang diperolah pada average precision = 0.38 dan average recall = 0.29.

References

[1] S. Masri, Y. Jin and J. Wu, "Compound Risk of Air Pollution and Heat Days and the Influence of Wildfire by SES across California, 2018–2020: Implications for Environmental Justice in the Context of Climate Change," Climate, vol. 10, no. 10, p. 145, 2022. https://doi.org/10.3390/cli10100145

[2] S. Dos , J. F. Costa, J. M. N. Romeiro, J. B. d. Assis, F. T. P. Torres and J. M. Gleriani, "Potentials and limitations of remote fire monitoring in protected areas," Science of the total environment, pp. 1347-1355, 2018. https://doi.org/10.1016/j.scitotenv.2017.10.182

[3] M. F. Ridhani, and W. F. Mahmudy, "Advancements in Fire Alarm Detection using Computer Vision and Machine Learning: A Literature Review.," Journal of Information Technology and Computer Science, pp. 86-97, 2023. https://doi.org/10.25126/jitecs.202382554

[4] K. He, G. Gkioxari, P. Dollár and R. Girshick, "Mask r-cnn," Proceedings of the IEEE international conference on computer vision, pp. 2961-2969, 2017. https://doi.org/10.1109/ICCV.2017.322

[5] Z.-Q. Zhao, P. Zheng, S.-t. Xu and X. Wu, "Object detection with deep learning: A review," IEEE transactions on neural networks and learning systems, vol. 30, no. 11, pp. 3212-3232, 2019. https://doi.org/10.1109/TNNLS.2018.2876865

[6] Muhammad, Khan, J. Ahmad and S. W. Baik, "Early fire detection using convolutional neural networks during surveillance for effective disaster management," Neurocomputing , pp. 30-42, 2018. https://doi.org/10.1016/j.neucom.2017.04.083

[7] Z. Zou, K. Chen, Z. Shi, Y. Guo and J. Ye, "Object detection in 20 years: A survey," Proceedings of the IEEE, 2023. https://doi.org/10.1109/JPROC.2023.3238524

[8] A.-A. Dalal, Y. Shao, A. Alalimi and A. Abdu, "Mask R-CNN for geospatial object detection," International Journal of Information Technology and Computer Science, vol. 12, no. 5, pp. 63-72, 2020. https://doi.org/10.5815/ijitcs.2020.05.05

[9] D. Schweitzer and R. Agrawal, "Multi-class object detection from aerial images using Mask R-CNN," In 2018 IEEE International Conference on Big Data (Big Data), pp. 3470-3477, 2018. https://doi.org/10.1109/BigData.2018.8622536

[10] M. E. Laily, F. N. Fajri and G. Q. O. Pratamasunu, "Deteksi Penggunaan Alat Pelindung Diri (APD) Untuk Keselamatan dan Kesehatan Kerja Menggunakan Metode Mask Region Convolutional Neural Network (Mask R-CNN)," Jurnal Komputer Terapan, vol. 8, no. 2, pp. 279-288, 2022. https://doi.org/10.35143/jkt.v8i2.5732
Published
2024-06-04
Abstract viewed = 39 times
Full text downloaded = 34 times