Railway LiDAR semantic segmentation based on intelligent semi-automated data annotation

TL;DR

This paper presents a semi-automated annotation method and a 3D LiDAR semantic segmentation approach for railway environments, achieving high accuracy with limited labeled data through active learning.

Contribution

It introduces a novel semi-automated annotation process, a transfer labeling technique, and an active learning strategy for efficient training of 3D LiDAR segmentation in railway settings.

Findings

Achieved a mean IoU of 71.48% on 9 classes

Developed a semi-automated annotation pipeline for railway LiDAR data

Utilized active learning to improve training efficiency

Abstract

Automated vehicles rely on an accurate and robust perception of the environment. Similarly to automated cars, highly automated trains require an environmental perception. Although there is a lot of research based on either camera or LiDAR sensors in the automotive domain, very few contributions for this task exist yet for automated trains. Additionally, no public dataset or described approach for a 3D LiDAR semantic segmentation in the railway environment exists yet. Thus, we propose an approach for a point-wise 3D semantic segmentation based on the 2DPass network architecture using scans and images jointly. In addition, we present a semi-automated intelligent data annotation approach, which we use to efficiently and accurately label the required dataset recorded on a railway track in Germany. To improve performance despite a still small number of labeled scans, we apply an active learning approach to intelligently select scans for the training dataset. Our contributions are threefold: We annotate rail data including camera and LiDAR data from the railway environment, transfer label the raw LiDAR point clouds using an image segmentation network, and train a state-of-the-art 3D LiDAR semantic segmentation network efficiently leveraging active learning. The trained network achieves good segmentation results with a mean IoU of 71.48% of 9 classes.