Smart Cost Estimation for Construction Planning: An Automated Framework Leveraging Computer Vision and Collaborative Filtering
Keywords:
Construction estimation, Generative AI, Hybrid computer vision, IS 1200, SMEAbstract
In the traditional construction landscape, particularly within developing economies, the pre-planning phase is severely bottlenecked by manual quantity take-offs (QTO) from two-dimensional blueprints. This conventional approach is labour-intensive, computationally opaque, and susceptible to human error, often leading to budget variances exceeding 20%. This paper introduces a novel “Smart Hybrid” framework designed to democratise professional-grade estimation for Small and Medium Enterprises (SMEs). Moving beyond fragile edge-detection techniques, the solution integrates a multi-stage Hybrid Vision Pipeline. This pipeline uniquely synergises the semantic reasoning of large language models (specifically Google Gemini 2.0) to interpret room topology, with the geometric precision of OpenCV and PaddleOCR for exact dimension extraction. Furthermore, the system incorporates a deterministic civil engineering logic engine that strictly adheres to IS 1200 standards. For visualisation, a Generative Layout algorithm using Breadth-First Search (BFS) to reconstruct 2D plans into interactive 3D models via React Three Fibre. Finally, procurement is optimised through a recommender engine applying collaborative filtering to real-time supplier data from IndiaMART.
References
Z. Zeng, X. Li, Y. K. Yu and C. -W. Fu, “Deep floor plan recognition using a multi-task network with room-boundary-guided attention,” 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 9095–9103.
A. Kalervo, J. Ylioinas, M. Häikiö, A. Karhu, and J. Kannala, “CubiCasa5K: A dataset and an improved multi-task model for floorplan image analysis,” in Image Analysis, May 2019, pp. 28–40.
C. Liu, J. Wu, P. Kohli and Y. Furukawa, “Raster-to-Vector: Revisiting floorplan transformation,” 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2214–2222.
D. Park and S. Yun, “Construction cost prediction using deep learning with BIM properties in the schematic design phase,” Applied Sciences, vol. 13, no. 12, Jun. 2023.
M. Vidanapathirana, Q. Wu, Y. Furukawa, A. X. Chang and M. Savva, “Plan2Scene: Converting floorplans to 3D scenes,” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021, pp. 10728–10737.
Z. Yang, J. Wang, Y. Tang, K. Chen, H. Zhao, and P. H. Torr, “Semantics-aware dynamic localization and refinement for referring image segmentation,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 3, pp. 3222–3230, Jun. 2023.
S. Ahmed, M. Weber, M. Liwicki, C. Langenhan, A. Dengel, and F. Petzold, “Automatic analysis and sketch-based retrieval of architectural floor plans,” Pattern Recognition Letters, vol. 35, pp. 91–100, Jan. 2014.
G. Nagy, “Twenty years of document image analysis in PAMI” in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 22, no. 1, pp. 38–62, Jan. 2000.
F. Su, J. Song, and S. Cai, “A vectorization system for architecture engineering drawings,” in Graphics Recognition. Ten Years Review and Future Perspectives, Berlin, Heidelberg: Springer Berlin Heidelberg, 2006, pp. 11–22.
T. C. Henderson, Analysis of engineering drawings and raster map images. New York, NY: Springer New York, 2014.
S. Azhar, “Building Information Modeling (BIM): Trends, benefits, risks, and challenges for the AEC industry,” Leadership and Management in Engineering, vol. 11, no. 3, pp. 241–252, Jun. 2011.
R. Volk, J. Stengel, and F. Schultmann, “Building Information Modeling (BIM) for existing buildings — Literature review and future needs,” Automation in Construction, vol. 38, pp. 109–127, Mar. 2014.
P. Tang, D. Huber, B. Akinci, R. Lipman, and A. Lytle, “Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniques,” Automation in Construction, vol. 19, no. 7, pp. 829–843, Nov. 2010.
Y. Zhang, Y. He, S. Zhu, X. Di, “The direction-aware, learnable, additive kernels and the adversarial network for deep floor plan recognition,” arXiv, 2020.
R. Sacks, C. Eastman, G. Lee, and P. Teicholz, BIM handbook: A guide to building information modeling for owners, designers, engineers, contractors, and facility managers. Hoboken, NJ, USA: John Wiley & Sons, 2018.
J. Du and H. Jing, “Collaborative filtering-based matching and recommendation of suppliers in prefabricated component supply chain,” in International Conference on Applications and Techniques in Cyber Security and Intelligence, Cham: Springer International Publishing, Oct. 2017, pp. 128–139.
S. Rendle, “Factorization machines,” 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia, 2010, pp. 995–1000.
