Pemantauan Aktivitas Pekerja Konstruksi Secara Real-Time Menggunakan Computer Vision Berbasis YOLOv8

Muhammad Yusuf Al-Firdaus; Muhammad Faizal Ardhiansyah Arifin; Very Iman Santosa

doi:10.31004/riggs.v5i2.9246

Authors

Muhammad Yusuf Al-Firdaus Universitas Negeri Semarang
Muhammad Faizal Ardhiansyah Arifin Universitas Negeri Semarang
Very Iman Santosa Universitas Negeri Semarang

DOI:

https://doi.org/10.31004/riggs.v5i2.9246

Keywords:

Computer Vision, YOLO v8, Deteksi Aktivitas Pekerja, Pemantauan Real-Time, Keselamatan Konstruksi

Abstract

Manajemen proyek konstruksi di Indonesia masih sangat bergantung pada metode pengawasan manual yang konvensional. Metode ini rentan terhadap kesalahan manusia, subjektivitas penilaian, kelelahan pengamat, serta tidak memiliki kemampuan responsivitas real-time. Penelitian ini bertujuan mengembangkan dan mengevaluasi sistem pemantauan aktivitas pekerja berbasis computer vision menggunakan algoritma YOLOv8. Sistem ini dirancang untuk mengklasifikasikan empat kategori aktivitas pekerjaan bata secara real-time, yaitu memasang bata, memotong bata, mengaduk semen, dan plester bata, sekaligus mendeteksi kepatuhan penggunaan helm keselamatan secara simultan dalam satu model terpadu. Dataset video direkam di lokasi konstruksi gedung FKIP Universitas Muria Kudus, Jawa Tengah, dengan melibatkan pekerja bata berpengalaman. Total 4.170 anotasi bounding box berhasil dikumpulkan dan terdistribusi ke dalam tujuh kelas objek. Model YOLOv8s dilatih selama 200 epoch menggunakan platform Google Colaboratory dengan akselerasi GPU NVIDIA T4 dan strategi transfer learning dari bobot pre-trained COCO. Hasil evaluasi kuantitatif pada subset pengujian menunjukkan bahwa akurasi tertinggi dicapai oleh kelas memotong bata dan plester bata sebesar 92%, diikuti oleh kelas mengaduk semen sebesar 82%, sedangkan kelas memasang bata mencapai akurasi 56%. Untuk deteksi kepatuhan helm, presisi kelas helm sangat tinggi, yaitu 94%, namun recall untuk kelas yang tidak memakai helm masih rendah, hanya 40%. Rata-rata F1-Score keseluruhan dari keenam kelas yang dievaluasi adalah 73%. Sistem ini membuktikan bahwa pendekatan YOLOv8 merupakan alternatif yang objektif, skalabel, dan layak untuk diterapkan dalam pengawasan konstruksi di Indonesia. Penelitian selanjutnya disarankan untuk memperluas variasi dataset dari lokasi dan kondisi pencahayaan yang beragam.

Downloads

Download data is not yet available.

References

A. F. Kineber et al., "Benefits of implementing occupational health and safety management systems for the sustainable construction industry: A systematic literature review," Sustainability, vol. 15, no. 17, p. 12697, 2023. https://doi.org/10.3390/su151712697

R. Kunodzia, L. Bikitsha, and R. Haldenwang, "Perceived factors affecting the implementation of occupational health and safety management systems in the South African construction industry," Safety, vol. 10, no. 1, p. 5, 2024. https://doi.org/10.3390/safety10010005

R. U. Latief et al., "Labor productivity study in construction projects viewed from influence factors," Civil Engineering Journal, vol. 9, no. 3, pp. 583-595, 2023. https://doi.org/10.28991/CEJ-2023-09-03-07

M. A. Musarat et al., "Automated monitoring innovations for efficient and safe construction practices," Results in Engineering, vol. 22, p. 102057, 2024. https://doi.org/10.1016/j.rineng.2024.102057

A. Jalil Al-Bayati et al., "PPE non-compliance among construction workers: An assessment of contributing factors utilizing fuzzy theory," Journal of Safety Research, vol. 85, pp. 242-253, 2023. https://doi.org/10.1016/j.jsr.2023.02.008

A. M. Vukicevic et al., "A systematic review of computer vision-based personal protective equipment compliance in industry practice," Artificial Intelligence Review, vol. 57, no. 12, 2024. https://doi.org/10.1007/s10462-024-10978-x

Y. Chen et al., "YOLO-MS: Rethinking multi-scale representation learning for real-time object detection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 6, pp. 4240-4252, 2025. https://doi.org/10.1109/TPAMI.2025.3538473

M. Safaldin, N. Zaghden, and M. Mejdoub, "An improved YOLOv8 to detect moving objects," IEEE Access, vol. 12, pp. 59782-59806, 2024. https://doi.org/10.1109/ACCESS.2024.3393835

J. Lee and S. Lee, "Construction site safety management: A computer vision and deep learning approach," Sensors, vol. 23, no. 2, p. 944, 2023. https://doi.org/10.3390/s23020944

A. Rauzana, A. Zahrah, and W. Dharma, "Critical delay factors for construction projects in Central Aceh District, Indonesia," F1000Research, vol. 11, p. 33, 2022. https://doi.org/10.12688/f1000research.110024.3

Y. Nakanishi, T. Kaneta, and S. Nishino, "A review of monitoring construction equipment in support of construction project management," Frontiers in Built Environment, vol. 7, p. 632593, 2022. https://doi.org/10.3389/fbuil.2021.632593

E. Naughton et al., "A structured model for continuous improvement methodology deployment and sustainment: A case study," Heliyon, vol. 10, no. 21, p. e40034, 2024. https://doi.org/10.1016/j.heliyon.2024.e40034

J. Li et al., "A review of computer vision-based monitoring approaches for construction workers' work-related behaviors," IEEE Access, vol. 12, pp. 7134-7155, 2024. https://doi.org/10.1109/access.2024.3350773

L. Ensslin et al., "Constructivist multi-criteria model to support the management of occupational accident risks in civil construction industry," PLoS ONE, vol. 17, no. 7, p. e0270529, 2022. https://doi.org/10.1371/journal.pone.0270529

K. Ibrahim, F. Simpeh, and O. Adebowale, "Benefits and challenges of wearable safety devices in the construction sector," Smart and Sustainable Built Environment, 2023. https://doi.org/10.1108/sasbe-12-2022-0266

S. F. A. Zaidi et al., "Vision-based construction safety monitoring utilizing temporal analysis to reduce false alarms," Buildings, vol. 14, no. 6, p. 1878, 2024. https://doi.org/10.3390/buildings14061878

W. Fang et al., "Computer vision applications in construction safety assurance," Automation in Construction, vol. 110, p. 103013, 2020. https://doi.org/10.1016/j.autcon.2019.103013

S. P. Gonzalez-Sabbagh and A. Robles-Kelly, "A survey on underwater computer vision," ACM Computing Surveys, vol. 55, no. 13s, p. 1-35, 2023. https://doi.org/10.1145/3578516

A. Barlybayev et al., "Personal protective equipment detection using YOLOv8 architecture on object detection benchmark datasets: A comparative study," Cogent Engineering, vol. 11, no. 1, p. 2333209, 2024. https://doi.org/10.1080/23311916.2024.2333209

U. U. Deshpande et al., "Computer-vision based automatic rider helmet violation detection using NVIDIA TAO toolkit and YOLOv8," Frontiers in Artificial Intelligence, vol. 8, p. 1582257, 2025. https://doi.org/10.3389/frai.2025.1582257

M. Sokolova and G. Lapalme, "A systematic analysis of performance measures for classification tasks," Information Processing & Management, vol. 45, no. 4, pp. 427-437, 2009. https://doi.org/10.1016/j.ipm.2009.03.002

B. F. Spencer, V. Hoskere, and Y. Narazaki, "Advances in computer vision-based civil infrastructure inspection and monitoring," Engineering, vol. 5, no. 2, pp. 199-222, 2019. https://doi.org/10.1016/j.eng.2018.11.030

L. Liu et al., "Multi-task intelligent monitoring of construction safety based on computer vision," Buildings, vol. 14, no. 8, p. 2429, 2024. https://doi.org/10.3390/buildings14082429

M. I. B. Ahmed et al., "Personal protective equipment detection: A deep-learning-based sustainable approach," Sustainability, vol. 15, no. 18, p. 13990, 2023. https://doi.org/10.3390/su151813990

B. I. Arianto, "Implementasi metode YOLO pada deteksi pakaian keselamatan yang lengkap di proyek konstruksi," Ranah Research, vol. 6, no. 1, pp. 56-63, 2023.

Y. Kim and Y. Choi, "Smart helmet-based proximity warning system to improve occupational safety using image sensor and artificial intelligence," Int. J. Environ. Res. Public Health, vol. 19, no. 23, p. 16312, 2022. https://doi.org/10.3390/ijerph192316312

L. Shen, B. Lang, and Z. Song, "DS-YOLOv8-based object detection method for remote sensing images," IEEE Access, vol. 11, pp. 125122-125137, 2023. https://doi.org/10.1109/ACCESS.2023.3330844

V. K. Reja, K. Varghese, and Q. P. Ha, "Computer vision-based construction progress monitoring," Automation in Construction, vol. 138, p. 104245, 2022. https://doi.org/10.1016/j.autcon.2022.104245

L.-W. Lung, Y.-R. Wang, and Y.-S. Chen, "Leveraging deep learning and Internet of Things for dynamic construction site risk management," Buildings, vol. 15, no. 8, p. 1325, 2025. https://doi.org/10.3390/buildings15081325

A. D. Rafindadi et al., "Caught-in/between accidents in the construction industry: A systematic review," Safety, vol. 11, no. 1, p. 12, 2025. https://doi.org/10.3390/safety11010012

J. Seo et al., "Computer vision techniques for construction safety and health monitoring," Advanced Engineering Informatics, vol. 29, no. 2, pp. 239-251, 2015. https://doi.org/10.1016/j.aei.2015.02.001

X. Luo et al., "Towards efficient and objective work sampling: Recognizing workers' activities in site surveillance videos with two-stream convolutional networks," Automation in Construction, vol. 94, pp. 360-370, 2018. https://doi.org/10.1016/j.autcon.2018.05.024

W. Fang et al., "Computer vision for automated safety compliance checking in construction: A review," Automation in Construction, vol. 129, p. 103838, 2021. https://doi.org/10.1016/j.autcon.2021.103838

B. Widodo, H. A. Armanto, and E. Setyati, "Deteksi pemakaian helm proyek dengan metode convolutional neural network," Journal of Intelligent System and Computation, vol. 3, no. 1, pp. 45-52, 2021. https://doi.org/10.52985/insyst.v3i1.157