Self-prompting semantic segmentation of bridge point cloud data using a large computer vision model

Abstract

Semantic segmentation of bridge Point Cloud Data (PCD) is an intermediate process required for the tasks such as deformation detection and digital twin. However, existing methods either require a substantial amount of training data or exhibit limited generalization ability. To address these issues, this paper presents an unsupervised framework for semantic segmentation of bridge PCD. A visible point rendering method is first employed to bridge the modal gap between 2D and 3D, and then a self-prompting segmentation method based on a large computer vision model is introduced to achieve instance segmentation. Experiment results on the real-world reinforced concrete bridge dataset and suspension bridge dataset showed the proposed method achieved the outstanding performance on all overall evaluation metrics of overall accuracy (98.31 % and 98.10 %), mean precision (97.67 % and 93.96 %), mean recall rate (97.50 % and 97.51 %) and mean F1 score (97.46 % and 95.55 %). The comparisons with existing methods demonstrate that without the need of training data, our method can achieve competitive or even superior accuracy to learning-based methods.