首页|Reports from Concordia University Describe Recent Advances in Machine Learning ( Dynamic Graph Cnn Based Semantic Segmentation of Concrete Defects and As-inspect ed Modeling)
Reports from Concordia University Describe Recent Advances in Machine Learning ( Dynamic Graph Cnn Based Semantic Segmentation of Concrete Defects and As-inspect ed Modeling)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Machine Learning are pre sented in a new report. According to news reporting originating from Montreal, C anada, by NewsRx correspondents, research stated, "Obtaining accurate informatio n of defective areas of infrastructures helps to perform repair actions more eff iciently. Recently, LiDAR scanners have been used for the inspection of surface defects." Our news editors obtained a quote from the research from Concordia University, " Moreover, machine learning methods have attracted the attention of researchers f or semantic segmentation and classification based on point cloud data. Although much work has been done for processing visual information with images, research on machine learning methods for semantic segmentation of raw point cloud data is still in its early stages. Moreover, LiDAR technology is commonly used to creat e as-is BIM models. Therefore, the BIM model needs to be integrated with the res ults of defect semantic segmentation after the LiDARbased inspection. Addressin g the above issues, this paper has the following objectives: (1) Developing a me thod for point cloud-based concrete surface defects semantic segmentation; and ( 2) Developing a semi-automated process for as-inspected modeling. The challenges related to the size of the dataset and imbalanced classes are studied. Sensitiv ity analysis is applied to capture the best combination of hyperparameters and i nvestigate their effects on the network performance. The proposed method resulte d in 98.56% and 96.50% recalls for semantic segmenta tion of cracks and spalls, respectively. Furthermore, post-processing of the res ults of the concrete surface defects semantic segmentation is done to semiautom ate the process of as-inspected modeling. As-inspected BIM includes the updated information of the facilities at the time of data collection."
MontrealCanadaNorth and Central Amer icaCyborgsEmerging TechnologiesMachine LearningConcordia University
NETL
NSTL
