To ensure efficient railroad operation and maintenance management, the accurate reconstruction of railroad BIM models is a crucial step. This paper proposes a workflow for automated segmentation and reconstruction of railroad structures using point cloud data, without relying on intensity or trajectory information.
From a paper in MDPI by Chen et al.
The workflow consists of four main components: point cloud adaptive denoising, scene segmentation, structure segmentation combined with deep learning, and model reconstruction. The proposed workflow was validated using two datasets with significant differences in railroad line point cloud data.
The results demonstrated significant improvements in both efficiency and accuracy compared to existing methods. The techniques enable direct automated processing from raw data to segmentation results, providing data support for parameterized modeling and greatly reducing manual processing time.
The proposed algorithms achieved an intersection over union (IoU) of over 0.9 for various structures in a 450-m-long railroad line. Furthermore, for single-track railroads, the automated segmentation time was within 1 min per kilometer, with an average mean intersection over union (MIoU) and accuracy of 0.9518 and 1.0000, respectively.
Regarding the developed segmentation algorithm, this paper mainly focuses on extracting critical structures of the railroad line. For other accessory structures in the line, they have not been addressed. When facing structures that do not have obvious geometric features, the automatic segmentation process is often challenging. Therefore, corresponding segmentation methods should be designed for similar signal equipment, power supply equipment, and along-line stations’ data to provide data support for deep learning, or else there will be a large amount of manual segmentation work.
In general, current deep learning-based point cloud semantic segmentation solutions  and mainstream segmentation algorithms [22,48,74] mentioned earlier have made significant progress in point cloud processing in railroad environments. However, there still exist certain manual operations in dealing with noise, separating ground data, and handling complex situations such as multi-track steel rails and multiple power lines in railroads. Additionally, it remains challenging to perform point cloud semantic segmentation without relying on intensity information or trajectory information.
For the complete article CLICK HERE.
Note – If you liked this post click here to stay informed of all of the 3D laser scanning, geomatics, UAS, autonomous vehicle, Lidar News and more. If you have an informative 3D video that you would like us to promote, please forward to email@example.com and if you would like to join the Younger Geospatial Professional movement click here