Sistem Deteksi Perokok di Area Publik Menggunakan YOLOv8
DOI:
https://doi.org/10.26418/jp.v11i2.94182Keywords:
Deteksi Perokok, Deep Learning, YOLOv8, CNN, Ruang PublikAbstract
Merokok merupakan salah satu penyebab utama kematian yang dapat dicegah, baik bagi perokok aktif maupun pasif. Paparan asap rokok, bahkan dalam jumlah kecil, tetap berbahaya dan menimbulkan dampak serius, terutama bagi anak-anak. Meskipun berbagai regulasi telah diterapkan untuk melarang aktivitas merokok di ruang publik, seperti Perda Kota Medan No. 3 Tahun 2014, implementasinya masih menghadapi tantangan seperti keterbatasan anggaran, lemahnya pengawasan, dan rendahnya kesadaran masyarakat. Penelitian ini mengusulkan sistem deteksi perokok berbasis deep learning menggunakan model YOLOv8 untuk mendeteksi keberadaan aktivitas merokok dalam video pengawasan. Lima varian model YOLOv8 diuji, yaitu YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, dan YOLOv8x. Hasil pelatihan menunjukkan bahwa YOLOv8m dan YOLOv8l memperoleh nilai mAP tertinggi sebesar 0,987. Namun, pada pengujian implementasi menggunakan video CCTV Full HD dengan ketinggian kamera 2 meter dan jarak maximal 3 meter, YOLOv8s menunjukkan performa terbaik dengan akurasi 100% pada pencahayaan baik dan 95% pada pencahayaan kurang, serta kecepatan inferensi yang lebih tinggi. Dengan demikian, YOLOv8s merupakan varian model yang paling optimal untuk implementasi sistem deteksi perokok di ruang publik.References
A. Daley, M. Rahman, and B. Watson, “A breath of fresh air: The effect of public smoking bans on Indigenous youth,†Heal. Econ. (United Kingdom), vol. 30, no. 6, pp. 1517–1539, 2021, doi: 10.1002/hec.4276.
M. B. Reitsma, L. S. Flor, E. C. Mullany, V. Gupta, S. I. Hay, and E. Gakidou, “Spatial, temporal, and demographic patterns in prevalence of smoking tobacco use and initiation among young people in 204 countries and territories, 1990–2019,†Lancet Public Heal., vol. 6, no. 7, pp. e472–e481, 2021, doi: 10.1016/S2468-2667(21)00102-X.
Suthamancharri.S, Vaishnavi.S, Kumara Raja, Soundarya.S.P, and Sumaiya fathima, “Review on Effects of Passive Smoking,†Int. J. Community Dent., vol. 11, no. 1, pp. 26–31, 2023, doi: 10.56501/intjcommunitydent.v11i1.777.
J. Bommelé, B. H. Walters, S. van Dorsselaer, and M. C. Willemsen, “Outdoor smoking as a nuisance to non-smokers: The case for smoke-free outdoor public spaces in dense urban areas,†Tob. Prev. Cessat., vol. 8, no. February, pp. 1–9, 2022, doi: 10.18332/TPC/145502.
F. Nasution, F. P. Gurning, P. A. Siregar, A. Ahsan, and D. Kusuma, “Implementation of the Smoke‑Free Policy in Medan City, Indonesia: Compliance and Challenges,†Int. J. Prev. Med., vol. 13, pp. 1–5, 2022, doi: 10.4103/ijpvm.IJPVM_106_20.
M. Q. Gandapur and E. Verdú, “ConvGRU-CNN: Spatiotemporal Deep Learning for Real-World Anomaly Detection in Video Surveillance System,†Int. J. Interact. Multimed. Artif. Intell., vol. 8, no. 4, pp. 88–95, 2023, doi: 10.9781/ijimai.2023.05.006.
Y. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu, and M. S. Lew, “Deep learning for visual understanding: A review,†Neurocomputing, vol. 187, pp. 27–48, 2016, doi: 10.1016/j.neucom.2015.09.116.
A. J. Moshayedi, A. S. Roy, A. Kolahdooz, and Y. Shuxin, “Deep Learning Application Pros And Cons Over Algorithm,†EAI Endorsed Trans. AI Robot., vol. 1, pp. 1–13, 2022, doi: 10.4108/airo.v1i.19.
D. Bhatt et al., “Cnn variants for computer vision: History, architecture, application, challenges and future scope,†Electron., vol. 10, no. 20, pp. 1–28, 2021, doi: 10.3390/electronics10202470.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,†Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 779–788, 2016, doi: 10.1109/CVPR.2016.91.
S. M. Alkentar, B. Alsahwa, A. Assalem, and D. Karakolla, “Practical comparation of the accuracy and speed of YOLO, SSD and Faster RCNN for drone detection,†J. Eng., vol. 27, no. 8, pp. 19–31, 2021, doi: 10.31026/j.eng.2021.08.02.
A. Khan, S. Khan, B. Hassan, and Z. Zheng, “CNN-Based Smoker Classification and Detection in Smart City Application,†Sensors, vol. 22, no. 3, pp. 1–17, 2022, doi: 10.3390/s22030892.
N. D. Nguyen, T. Do, T. D. Ngo, and D. D. Le, “An Evaluation of Deep Learning Methods for Small Object Detection,†J. Electr. Comput. Eng., vol. 2020, 2020, doi: 10.1155/2020/3189691.
N. A. Gunarsih, S. Wiyono, D. I. Af’idah, T. Informatika, and H. Bersama, “JIP (Jurnal Informatika Polinema) APLIKASI DETEKSI PELANGGARAN MEROKOK DI TEMPAT LARANGAN MEROKOK,†JIP (Jurnal Inform. Polinema), vol. 10 No.3, pp. 351–358, 2024.
A. Harun, Mustakim, and O. Brilian Kharisma, “Implementasi Deep Learning Menggunakan Metode You Only Look Once untuk Mendeteksi Rokok,†J. Media Inform. Budidarma, vol. 7, no. 1, pp. 106–116, 2023, doi: 10.30865/mib.v7i1.5409.
C. Paramita, C. Supriyanto, and K. R. Putra, “Comparative Analysis of YOLOv5 and YOLOv8 Cigarette Detection in Social Media Content,†Sci. J. Informatics, vol. 11, no. 2, pp. 341–352, 2024, doi: 10.15294/sji.v11i2.2808.
J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,†Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, 2023, doi: 10.3390/make5040083.
A. Khan, “Dataset containing smoking and not-smoking images (smoker vs non-smoker) - Mendeley Data.†2020, doi: 10.17632/7b52hhzs3r.1.
