The conducted tests enabled the identification of brickwork in need of urgent repair. Moisture was also identified in some cases. The obtained radiometric information of the point cloud allowed us to identify changes in the surface of walls, such as cavities, cracks and previous repairs. Based on the collected geometric data of the point cloud, it was possible to create an exact model of the scanned objects. During the research programme, chosen brickwork heritage buildings were scanned. In this paper, TLS was harnessed for analysis of historic brickwork structures from the 19th century. Remote measurement of historic buildings and structures using the technology of terrestrial laser scanning (TLS) is becoming a more and more popular approach for conducting inventory activities, documentation and conservation works. With a training/testing ratio of only 1:6 and an overall training time of less than 70 min, the average precision, recall, and 1-of the SCL-GCN reached 75.7%, 75.1%, and 75.2%, respectively. The experimental results show that the developed SCL-GCN model outperforms state-of-the-art methods. This module supervises the learning process of the two branches to avoid learning bias caused by an imbalanced data distribution, promoting convergence and improving performance. Next, a graph feature contrastive learning module is proposed to take advantage of stratified features. The stratification strategy samples neighbors densely in the raw point clouds and sparsely in the downsampled subset to form the neighborhood for each point, utilizing long-range contexts to increase the effective receptive field while lowing the extra computation. This module creates strengthened spaces for the raw pavement point cloud and its downsampled subset, from which adjacency matrices and initial representations are generated. First, a multi-scale graph representation construction module was designed based on a stratification strategy. To address these issues, we developed SCL-GCN, a Stratified Contrastive Learning Graph Convolution Network with a novel dual-branch architecture for MLS-point cloud-based pavement crack detection. Most existing rule-or learning-based point-level approaches cannot achieve high detection accuracy and efficiency owing to the disorderly arrangement, scattered intensities, diverse crack structures, large data volumes, and complex annotation of mobile laser scanning (MLS) point clouds. Accurate pavement crack detection is important for routine maintenance of pavements and reduction of possible traffic accidents.
0 Comments
Leave a Reply. |