Automatic railway inspection and inventory updating using a compact mobile laser scanner

为了促进当今世界各地城市对安全和高效的城市地铁系统日益增长的需求，准确、有效的铁路检查做法是必要的。仅在加拿大，铁路系统就覆盖了6万公里的主要铁路线，每年运送7500万人和价值2500亿美元的货物。如此多的通勤者依赖于轨道交通，显然安全是组织公共交通系统的重中之重；由于大多数脱轨事故和碰撞是由于轨道缺陷造成的，因此对铁路基础设施进行仔细的检查和维护是必要的和经常性的任务。然而，目前的铁路检测方法在很大程度上依赖于人工进行这方面的工作，既浪费资源又浪费时间。为了解决这一问题，拟议的研究旨在开发一种新的遥感系统，专门为铁路资产的自动检查而设计。拟议的检测系统基于安装在移动车辆上的紧凑型光检测和测距扫描仪，能够在高速下以亚厘米精度密集测量整个铁路走廊。在过去的8年里，我们进行了研究，以开发自动分析激光雷达数据的新技术，以解决基础设施安全问题。在这项研究中，我们建议与泰利斯加拿大公司合作，扩展这项研究，开发最先进的遥感技术和算法，以重建准确的铁路网模型，这些模型具有关于铁轨和路旁物体的结构、空间和背景信息，用于全面的路线和基础设施文档和评估。该系统的实施不仅将提高轨道检测的准确性，从而防止任何潜在的灾难性铁路事故，而且还将降低成本和服务中断。此外，采用的系统将能够优化铁路运营并最大限度地提高效率，从而减少加拿大铁路系统的碳足迹。最后，这种自动轨道检测技术将使加拿大处于铁路发展和行业的前沿。

Precise, effectual railway inspection practices are necessary to facilitate the growing demand for safe and efficient urban metro systems in cities around the world today. In Canada alone, railway systems covers 60,000 km of main track-line, and transport 75 million people as well as $250 billion worth of goods each year. With such a high number of commuters relying on rail transit, it is evident that safety is a top priority in organizing public transportation systems; as the majority of derailment accidents and collisions are due to defects in the tracks, careful inspection and maintenance of railway infrastructure are necessary and regular tasks. However, current railway inspection methods rely heavily on manual work in this area, which is wasteful of both resources and time. To address this issue, the proposed research aims to develop a new remote sensing system specifically designed for the automatic inspection of railway assets. The proposed inspection system is based on a compact light detection and ranging scanner mounted on a moving vehicle, capable of densely measuring whole railway corridors in 3D with sub-centimeter accuracy at high speeds. For the past 8 years, we have conducted research to develop new technologies that automate the analysis of lidar data, in order to address the infrastructure safety concerns. In this study, we propose to extend this research, in partnership with Thales Canada, to develop state-of-the-art remote sensing technologies and algorithms for reconstructing accurate railway network models, which are attributed with structural, spatial, and contextual information about railway tracks and wayside objects, for comprehensive route and infrastructure documentation and assessments. The implemented system will not only increase the accuracy of track inspection, so as to prevent any potential disastrous railway accidents, but will also cut down on costs and service disruptions. Furthermore, the employed system will enable optimization of railway operations and maximize efficiency, consequently reducing the carbon footprint of Canada's railway systems. Finally, such automated track inspection technology will place Canada at the forefront of railway development and industries.