Integrating Computer Vision in Construction Estimations and 3D Modelings

Abstract:

Computer vision and building information modeling (BIM) have gained significant attention in various fields, including construction, architecture, and infrastructure management. This study presents a novel method for automatically generating 3D models and estimating quantities of construction materials from 2D scanned floor plans using computer vision techniques. The proposed Python-based program integrates complex steps, such as image processing, line and room detection, wall recognition, and 3D model generation using Blender. Additionally, the program accurately calculates the areas of different elements in the floor plan and provides detailed cost estimations for materials like cement, steel, bricks, and tiles for various masonry construction. The results of the program are encouraging, showcasing its potential to be a valuable tool in the future for digital 3D modeling and estimation in construction projects. The program aims to minimize human effort and automate processes, making it user-friendly and efficient for architects, contractors, and clients alike. However, some limitations exist, such as resolution restrictions and sub-structure estimations, which can be addressed in future enhancements.

• Periodical: Construction Technologies and Architecture (Volume 13)
• Pages: 181-187
• DOI: https://doi.org/10.4028/p-yQH52B
• Online since: July 2024
• Authors: Mamoona Rasheed*, Hamza Munsif, Saqib Mehboob
• Keywords: 3D Model Generation, Automated Construction Decision-Making, Building Information Modeling (BIM), Computer Vision Integration, Quantity Estimation

References

[1] Shah, A., et al. Smart Web Application on Quantity Survey, Estimation and Costing. in 2018 International Conference on Smart City and Emerging Technology (ICSCET). 2018. IEEE.

DOI: 10.1109/icscet.2018.8537348

[2] Xu, S., et al., Computer vision techniques in construction: a critical review. Archives of Computational Methods in Engineering, 2021. 28: pp.3383-3397.

[3] Ruwanthika, R., et al. Dynamic 3D model construction using architectural house plans. in 2017 6th National Conference on Technology and Management (NCTM). 2017. IEEE.

DOI: 10.1109/nctm.2017.7872850

[4] Zeng, Z., et al. Deep floor plan recognition using a multi-task network with room-boundary-guided attention. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.

DOI: 10.1109/iccv.2019.00919

[5] Moledina, M.M.G., et al. Building information modelling technological innovations in industrialised building systems cost estimation. in 2017 International Conference on Research and Innovation in Information Systems (ICRIIS). 2017. IEEE.

DOI: 10.1109/icriis.2017.8002480

[6] Yang, R., T. Lu, and S. Cai. 3D building reconstruction based on interpretation of architectural drawings. in 2008 International Conference on Information and Automation. 2008. IEEE.

DOI: 10.1109/icinfa.2008.4608235

[7] Uzoegbo, H. and J. Ngowi, Structural behaviour of dry-stack interlocking block walling systems subject to in-plane loading. Concrete Beton, 2003. 103(1): pp.9-13.

[8] Hashemi, A., H. Cruickshank, and A. Cheshmehzangi, Environmental impacts and embodied energy of construction methods and materials in low-income tropical housing. Sustainability, 2015. 7(6): pp.7866-7883.

DOI: 10.3390/su7067866

[9] Elfahham, Y., Estimation and prediction of construction cost index using neural networks, time series, and regression. Alexandria Engineering Journal, 2019. 58(2): pp.499-506.

DOI: 10.1016/j.aej.2019.05.002

[10] García de Soto, B., B.T. Adey, and D. Fernando, A hybrid methodology to estimate construction material quantities at an early project phase. International Journal of Construction Management, 2017. 17(3): pp.165-196.

DOI: 10.1080/15623599.2016.1176727