Rail Track Extraction from Rasterized Classified Point Clouds Using a Full-Resolution, Fully Convolutional Recurrent Neural Network

Researchers introduced a method for extracting rail tracks from classified 3D point clouds using a fully convolutional recurrent neural network trained on synthetic data. The approach rasterizes points, applies the network to reduce noise, and uses morphological operations and Dynamic Time Warping to produce accurate track centerlines with minimal manual intervention. Experimental results demonstrated high-quality extraction, supporting automated railway inspection and mapping.

arXiv:2607.06829v1 Announce Type: new Abstract: Rail track extraction is essential for effective railway asset management and maintenance, especially in automated inspection and mapping workflows. This paper introduces a novel method for extracting rail tracks from classified 3D point clouds using a fully convolutional recurrent neural network that preserves full spatial resolution and is trained exclusively on synthetically generated data. This approach enhances per-pixel quality and is particularly suited for rail track extraction. The proposed method begins by rasterizing points corresponding to railroad tracks, then applies the neural network to reduce noise and yield a cleaner track representation suitable for vectorization 1 . Subsequent morphological operations further refine the resultant data, enabling accurate track centerline extraction. Next, the extracted centerlines undergo smoothing to eliminate residual irregularities 2, 3 . Finally, the algorithm transfers 3D information from lidar points onto 2D polylines and applies additional vertical smoothing. A single centerline for both tracks is found using the Dynamic Time Warping DTW algorithm 4 . The final outcome consists of rail top centerlines and track centerlines derived for rail pairs, with minimal manual intervention. Experimental validation confirms the effectiveness of this method in yielding high-quality rail track extraction.