Image Segmentation Applied to Urban Surface and Aerial Constraints Analysis Marco Lorenzo Trani Politecnico di Milano, Italy Federica Madaschi Politecnico di Milano, Italy This is a section of CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality (DOI: 10.36253/979-12-215-0289-3) by Pietro Capone, Vito Getuli, Farzad Pour Rahimian, Nashwan Dawood, Alessandro Bruttini, Tommaso Sorbi Firenze University Press Florence 2023 https://doi.org/10.36253/10.36253/979-12-215-0289-3.90

Available for academic research purposes

Open Access

Copyright Author(s)

Content licence CC BY-NC 4.0

Metadata licence CC0 1.0

This is original content, published for academic research purposes

 Digital edition XML powered by Booksflow

The rapid progress of artificial intelligence (AI) has prompted the exploration of its potential applications in the construction industry, although at a slower rate. Since the starting point of a design is the analysis of the site’s constraints, the purpose of the ongoing research is the application of artificial intelligence in risk assessment for site areas. The primary objective of this research project is to develop an interactive map that employs AI to identify potential surface and aerial interferences. This map aims to support planners, engineers, and architects during the site context analysis phase by providing real-time visualization of obstacles. The interactive map allows users to explore and analyze identified obstacles, enabling cluster markers and filtering of features. The results obtained from applying this approach in Milan, Italy, demonstrate its functionality and usability, highlighting the tool's ability to provide valuable information in both localized and citywide scenarios. Potential improvements such as size assessment and advanced marker generation are also being examined to enhance the management of surface and air interferences. The goal is to enhance the tool's functionality, accuracy, and planning efficiency in construction projects

 Image Segmentation Risk Assessment Construction Site Clustering Techniques

It is available online at https://doi.org/10.36253/10.36253/979-12-215-0289-3.90

References Couto, João & José, Frederico & Santos, Barros & Rahnemay, Emilia & Kohlman Rabbani, Emilia. (2017). How Time Constraints Affect Safety Conditions at Construction Sites: Analysis of the Perception of Portuguese Construction Participants. EJGE. 2. 563. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. http://arxiv.org/abs/2010.11929 Farkas, D., Hilton, B., Pick, J., Ramakrishna, H., Sarkar, A., & Shin, N. (2016). A Tutorial on Geographic Information Systems: A ten-year update. Communications of the Association for Information Systems, 38, 190–234. 10.17705/1cais.03809 Liu, Y. (2021). Efficient Fully Convolutional Networks for Dense Prediction Tasks. [University of Adelaide]. https://hdl.handle.net/2440/134023 Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/cvpr.2015.7298965 Trani, M. L. (2012). Construction Site Design, Santarcangelo di Romagna (I), Maggioli Editore, 2012. Pan, Y., & Zhang, L. (2022). Integrating BIM and AI for Smart Construction Management: Current Status and Future Directions. Archives of Computational Methods in Engineering, 30(2), 1081–1110. 10.1007/s11831-022-09830-8 Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021). Vision Transformers for Dense Prediction. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 10.1109/iccv48922.2021.01196 Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013). OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. http://arxiv.org/abs/1312.6229