Back to articles
Article
Volume: 35 | Article ID: 3DIA-100
Image
Few-shot learning on point clouds for railroad segmentation
  DOI :  10.2352/EI.2023.35.17.3DIA-100  Published OnlineJanuary 2023
Abstract
Abstract

Infrastructure maintenance of complex environments like railroads is a very expensive operation. Recent advances in mobile mapping systems to collect 3D point cloud data and in deep learning for detection and segmentation can prove to be very helpful in automating this maintenance and allowing preventive maintenance at certain locations before big failures occur. Some fully-supervised methods have been developed for understanding dynamic railroad environments. These methods often fail to generalize to infrastructure changes or new classes in low-labeled data. To address this issue, we propose a railroad segmentation method that leverages few-shot learning by generating class prototypes for the most relevant infrastructure classes. This method takes advantage of existing embedding networks for point clouds, taking the geometrical and spatial context into account for feature representation of complex connected classes. We evaluate our method on real-world data measured on Belgian railway tracks. Our model achieves promising results on connected classes, exposed to only a few annotated samples at test time.

Subject Areas :
Views 123
Downloads 65
 articleview.views 123
 articleview.downloads 65
  Cite this article 

Abdur Razzaq Fayjie, Patrick Vandewalle, "Few-shot learning on point clouds for railroad segmentationin Electronic Imaging,  2023,  pp 100-1 - 100-5,  https://doi.org/10.2352/EI.2023.35.17.3DIA-100

 Copy citation
  Copyright statement 
Copyright © 2023, Society for Imaging Science and Technology 2023
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA