Extracting roof sub-components from orthophotos using deep-learning -based semantic segmentation

Extracting roof sub-components from orthophotos using deep-learning -based semantic segmentation Jiajun Li, Boan Tao, Frédéric Bosché, Chris Xiaoxuan Lu, Lyn Wilson Pages 675-682 (2024 Proceedings of the 41st ISARC, Lille, France, ISBN 978-0-6458322-1-1, ISSN 2413-5844) Abstract: Best practice for the detection and annotation of visible defects in slated roofs is by annotation of photos, ideally orthophotos. If such a process is to be effectively automated in support of emerging Digital Twinning solutions, it is necessary to first recognise the external sub-components of the roof in the orthophotos, in particular the slated and leadwork areas. Using a dataset composed of many photos from two historic buildings, this study develops and compares different deep-learning -based semantic segmentation models to segment roof orthophotos into slated areas, leadwork, and `other' areas. Since orthophotos typically contain pixels which do not belong to the roof panel (black `background' pixels), the method employs a subsequent `background' label correction step. The best-performing model is found to be PointRend with Focal Loss: overall aAcc = 99, mIoU = 88.91, and mAcc = 92.77; for slate class, IoU and Acc is nearly 100; for leadwork class, IoU and Acc is around 90. Keywords: Semantic segmentation, Deep learning, Slated roof, Orthophoto DOI: https://doi.org/10.22260/ISARC2024/0088 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley