Search papers, labs, and topics across Lattice.
This paper presents a novel approach for extracting rail tracks from classified 3D point clouds using a fully convolutional recurrent neural network that maintains full spatial resolution and is trained on synthetic data. The method enhances per-pixel quality through a series of processes, including rasterization, noise reduction, and morphological operations, ultimately enabling accurate extraction of rail track centerlines with minimal manual intervention. Experimental results demonstrate the method's effectiveness, yielding high-quality representations suitable for automated railway asset management and maintenance workflows.
Achieving high-quality rail track extraction with minimal manual intervention could revolutionize automated railway inspections.
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.
