| description abstract | In the United States, around 1/3 of the rail network is operated by short lines. These railroads play an important role in the nation’s transportation system by serving as the feeder and distributor for the rail network, but often lack a digitized rail track inventory for timely and efficient rail asset management due to limited resources. Much research has been conducted to develop automatic rail extraction methods, since it is a critical step toward a comprehensive digitized rail track inventory. However, existing methods strongly rely on high-density point cloud data sets, sensor property and configuration, and assumptions on global features; therefore, their applications in short lines are limited, since rail tracks will travel through different terrains with various global features, and data sets owned by short lines are mostly low-density data sets with unknown sensor property and configuration. To address these limitations, this study proposes an automatic rail extraction method that can be applied to low-density data sets and is independent of sensor properties/configurations, and global features. The proposed method is tested on the grade-crossing data sets collected by the Federal Railroad Administration (FRA) with a low point density around the track bed area. The performance shows an average completeness of 97.1%, correctness of 99.7%, and quality of 96.8%. This approach helps short lines to establish their own digitized rail track inventory, allowing for effective operation planning and investment strategy, and builds the foundation for future geometry measurements and infrastructure management, thereby improving operational safety and efficiency without significant investment in high-end sensors and high-density data sets. This research introduces a cutting-edge automatic rail extraction method using low-cost light detection and ranging (LiDAR) technology, specifically designed to support short line railroads, which form a significant portion of the US rail network, but often lack digitized rail track inventories. By leveraging deep learning and local feature–based filters, the proposed method efficiently extracts rail tracks from low-density data sets without requiring detailed sensor configurations. This innovation allows short line railroads to create accurate digital rail track inventories, facilitating better operational planning, strategic investment, and infrastructure management. Importantly, it enables these railroads to improve safety and efficiency without significant financial outlay on high-end sensors. The method’s robustness and adaptability to various terrains make it a valuable tool for enhancing the operational capabilities and competitiveness of short line railroads. The extraction result of the study also provides a foundation for future precise detection of rail anomalies and wear patterns, leading to enhanced predictive maintenance and comprehensive railroad management systems. By bridging the technology gap for short line railroads, this research contributes significantly to the overall efficiency, safety, and modernization of the US rail network. | |
