Pemanfaatan Teknologi Image Processing Sebagai Proses Penilaian Fisik Dan Monitoring Kemajuan Progres Proyek Cluster BSD City

Ahmad Luthfi Mubarok; Budi Santoso

doi:10.55606/jitek.v6i2.12239

Authors

Ahmad Luthfi Mubarok Universitas Gunadarma
Budi Santoso Universitas Gunadarma

DOI:

https://doi.org/10.55606/jitek.v6i2.12239

Keywords:

AI, CNN, Construction, Image Processing, Progress Monitoring

Abstract

Application of Image Processing Technology for Physical Assessment and Progress Monitoring of Cluster Projects in Bsd City. The construction industry often faces challenges in project monitoring due to subjective assessments, inefficiencies, and risks of data manipulation. This study introduces a vision-based inspection system utilizing image processing and Convolutional Neural Networks (CNN) to automate progress evaluation in the Enchante BSD City housing project, specifically on foundation and column works. Field images were collected and processed through augmentation, pre-processing, and feature extraction, then used to train an EfficientNet model. The model achieved outstanding results with 100% accuracy, precision, recall, and F1-score, validated through both testing datasets and real field experiments. A prototype web-based application was also developed to integrate the AI model into a practical monitoring tool. The findings demonstrate that this approach can provide real-time, objective, and reliable progress evaluation, offering a promising solution to improve efficiency, transparency, and accountability in construction project management.

References

[1] Capela, S., Silva, R., Khanal, S., Campaniço, A., Barroso, J. & Filipe, V. (2020). Engine Labels Detection for Vehicle Quality Verification in the Assembly Line: A Machine Vision Approach (pp. 740–751). https://doi.org/10.1007/978-3-030-58653-9_71

[2] Ercan, M. & Wang, R. (2022). Computer Vision-Based Inspection System for Worker Training in Build and Construction Industry. Computers, 11. https://doi.org/10.3390/computers11060100

[3] Kim, J.-W., Choi, H.-W., Kim, S.-K. & Na, W. S. (2024). Review of Image-Processing-Based Technology for Structural Health Monitoring of Civil Infrastructures. Journal of Imaging, 10(4). https://doi.org/10.3390/jimaging10040093

[4] Lv, K., Liu, Z., Zhang, H., Jia, H., Mao, Y., Zhang, Y. & Bi, G. (2025). Wheeled Permanent Magnet Climbing Robot for Weld Defect Detection on Hydraulic Steel Gates. Applied Sciences, 15(14). https://doi.org/10.3390/app15147948

[5] Mittal, R. (2021). ‘Automatic Inspection System Using Machine Vision’ A Report. https://doi.org/10.13140/RG.2.2.31934.00321

[6] Nwankpa, C., Eze, S., Ijomah, W., Gachagan, A. & Marshall, S. (2019, October). Deep Learning Based Vision Inspection System for Remanufacturing Application.

[7] Park, M. & Jeong, J. (2022). Design and Implementation of Machine Vision-Based Quality Inspection System in Mask Manufac-turing Process. Sustainability, 14(10). https://doi.org/10.3390/su14106009

[8] Pugo-Mendez, E. & Serpa, L. (2022, October). Development of a platform based on artificial vision with SVM and KNN algo-rithms for the identification and classification of ceramic tiles. https://doi.org/10.54941/ahfe1001460

[9] Senthilnathan, R. (2022). Deep Learning in Vision-Based Automated Inspection: Current State and Future Prospects (pp. 159–175). https://doi.org/10.1007/978-3-030-75847-9_8

[10] Shi, Y., Li, A. & Wang, L. (2011). Design and Implementation of a Computer Vision Based Inspection System Using CUDA. Advanced Materials Research, 383–390, 18–24. https://doi.org/10.4028/www.scientific.net/AMR.383-390.18

[11] Tan, S., Lam, C. K., Kamarudin, K., Ismail, A. H., Abdul Rahim, N., Muhamad Azmi, M. S., Wan Yahya, W. M. N., Sneah, G., Seng, M., Hai, T. & Lye, O. (2021). Vision-Based Edge Detection System for Fruit Recognition. Journal of Physics: Conference Series, 2107, 12066. https://doi.org/10.1088/1742-6596/2107/1/012066

[12] Wang, J., Ma, Y., Zhang, L., Gao, R. X. & Wu, D. (2018). Deep learning for smart manufacturing: Methods and applications. Journal of Manufacturing Systems, 48, 144–156. https://doi.org/10.1016/j.jmsy.2018.01.003

[13] Wei, W., Lu, Y., Zhong, T., Li, P. & Liu, B. (2022). Integrated vision-based automated progress monitoring of indoor construction using mask region-based convolutional neural networks and BIM. Automation in Construction, 140, 104327. https://doi.org/10.1016/j.autcon.2022.104327