Integrasi Yolov8 Dan Opencv Untuk Sistem Verifikasi Kelengkapan Apd Pada State Machine
DOI:
https://doi.org/10.51903/pixel.v19i1.3745Keywords:
Verifikasi APD; YOLOv8; OpenCV; State Machine; ID Card; Helm; Masker.Abstract
This study proposes a computer vision-based system for automatically verifying the use of Personal Protective Equipment (PPE) in industrial environments. The system integrates the YOLOv8 object detection model, OpenCV for image processing, and a State Machine mechanism to manage the verification workflow. The verification process begins with employee identification through ID card scanning, followed by real-time detection of the head, safety helmet, and face mask using a camera, before generating a final PASS or FAIL decision. System evaluation was conducted using 250 testing scenarios to assess both model and system performance. The results show that the YOLOv8 model achieved an mAP@50 of 93.9%, while the overall verification system obtained 98.4% accuracy, 98.4% precision, 100% recall, and a 99.2% F1-score. The implementation of the State Machine contributed to a more stable and consistent verification process by ensuring that each inspection stage was executed in the correct sequence. These findings demonstrate that the proposed system can effectively support automated PPE compliance monitoring and has the potential to enhance occupational safety management in industrial workplaces.
References
1. Sri Wahyuni, Cut Putri Zaila Lheena, Kamalurrijal, Afriliansyah, Radhiah Zakaria. Pengaruh Penggunaan Alat Pelindung Diri. 2025;5:985–97. Available from: https://j-innovative.org/index.php/Innovative
2. Adelina A, Dhafa Al Abrar M, Emmanuela Simanjuntak Z, Maya Silvia E, Marcell Meliala A, Khairunisa T, et al. Analisis Risiko Keselamatan dan Kesehatan Kerja Melalui Metode Hiradc Pada UMKM Batik XYZ. Jabb. 2025;6(1):2025.
3. Aprilia. Peninjauan Keselamatan Dan Kesehatan Kerja. 2023;8(2).
4. Alfalah W. Pengenalan Keselamatan dan Kesehatan Kerja Di PT Cita Rasa Palembang. Terang. 2021;4(1):11–20.
5. Nashrulloh RA, Hakim A, Fasya Z, Nahdatul U, Surabaya U. Volume 2 Nomor 6 Juni 2023 KERJA TERHADAP KINERJA KARYAWAN. PENGARUH Keselam DAN Kesehat KERJA SERTA DISIPLIN KERJA TERHADAP KINERJA KARYAWAN Risda. 2023;2:1253–61.
6. More SS, Patil N, Lobo VB, Shet N, Goswami D, Rane P. Empowering the Visually Impaired: YOLOv8-based Object Detection in Android Applications. Procedia Comput Sci [Internet]. 2025;252:457–69. Available from: https://doi.org/10.1016/j.procs.2025.01.005
7. Deepthi shree AM, Brindha M. YOLOv8 for Robust Traffic Object Instance Segmentation using Image Quality Assessment. Procedia Comput Sci [Internet]. 2025;260:1060–70. Available from: https://doi.org/10.1016/j.procs.2025.03.291
8. Hasibuan NN, Zarlis M, Efendi S. Detection and Tracking Different Type of Cars With YOLO model combination and deep sort algorithm based on computer vision of traffic controlling. Sinkron. 2021;5(2B):210–21.
9. Santi R, Suwarningsih W, Sasongko A. Sistem Deteksi Helm Pengaman untuk Pemantauan Area Pabrik. J Infosecure. 2024;5(2):2087–1023.
10. Rizki AI, Regasari R, Putri M, Shaffan NH. Sistem Pintu Cerdas Berbasis Pengenalan Wajah dan Kartu Identitas Menggunakan YOLOv8 dan Optical Character Recognition ( OCR ). J Pengemb Teknol Inf dan Ilmu Komput. 2025;9(4):1–9.
11. Triyanto D, Zidan M, Wahyudi M, Pujiastuti L, Sumanto S. Pengembangan Sistem Deteksi Objek Botol Real-Time dengan YOLOv8 untuk Aplikasi Vision. Indones J Comput Sci. 2024;3(1):44–50.
12. Samperante J, Agus M, Putra W, Permana AG, Informasi S, Informatika M. Implementasi Arsitektur Yolo V8 Dalam Mendeteksi Alat Pelindung Diri (APD) Di Sektor Konstruksi Dan Industri. Semin Has Penelit Inform dan Komput | Inst Teknol dan Bisnis STIKOM Bali [Internet]. 2025;2(1):661–6. Available from: https://spinter.stikom-bali.ac.id/index.php/spinter/article/view/698
13. Visen, Charibaldi N. Penerapan Object Detection Menggunakan Deep Learning Yolov8 Untuk Mengidentifikasi Sampah Anorganik (Maksimal Sepuluh Objek) Dalam Satu Citra. J Teknol Inf dan Ilmu Komput. 2025;12(1):195–202.
14. Therino Elevan R, Hermanto D, Widiyanto EP. Deteksi Jumlah Kendaraan Roda Empat Menggunakan Yolo. Integr Perspect Soc Sci J. 2025;2(1):1647.
15. Li Q, Zhao F, Xu Z, Li K, Wang J, Liu H, et al. Improved YOLOv4 algorithm for safety management of on-site power system work. Energy Reports [Internet]. 2022;8:739–46. Available from: https://doi.org/10.1016/j.egyr.2022.08.170
16. Meena SD, Gayathri Siva Sameeraja V, Lasya NS, Sathvika M, Harshitha V, Sheela J. Hybrid Neural Network Architecture for Multi-Label Object Recognition using Feature Fusion. Procedia Comput Sci [Internet]. 2022;215:78–90. Available from: https://doi.org/10.1016/j.procs.2022.12.009
17. Darussalam, Arief G. Jurnal Resti. Resti. 2018;1(1):19–25.
18. Kurniawardhani A, Fudholi DH, Andaru GI, Alhanafi AA, Najmudin N. YOLO-based Small-scaled Model for On-Shelf Availability in Retail. J RESTI. 2024;8(2):265–71.
19. Hadi Supriyanto, Sarosa Castrena Abadi, Aliffa Shalsabilah. Deteksi Helm Keselamatan Menggunakan Jetson Nano dan YOLOv7. J Appl Comput Sci Technol. 2024;5(1):1–8.
20. Oklilas AF, Sukemi S, Apriliyanto R. Model Yolo Versi 4 Pada Pengenalan Kendaraan Di Jalan Raya Kota Palembang. Transm J Ilm Tek Elektro. 2023;25(3):136–9.
2.png)
