Cross-tie assessment for North American market with Holland Company
Rail Vision and Holland Company, USA are jointly working together on providing visual data analysis services to the North American market with the aim of improving tie inspection and maintenance. Please read the attached press release on this subject. [Press Release]. Since the publication of this article, Rail Vision has installed further systems on-board TrackStar vehicles for tie assessment over the last three years. Altogether three TrackStar vehicles now carry three linescan and two laser systems for tie grading and assessment.
Visual track inspection system for Union Pacific
Rail Vision and Union Pacific are working together on concrete and wood tie grading. Rail Vision installed a visual imaging system on-board EC-11 inspection vehicle in 2012 and have a contract to provide data processing service for all collected data. The system detected fine cracks in concrete, grades concrete and wood ties, and determines railhead defects and detects missing fasteners. In addition, Rail Vision successfully tested its EVI software on data collected by Cybernetix hardware on-board EC-5 track inspection car. The system is capable of synchronising multiple camera views for analysis, and detects a number of features including: classification of wood and concrete ties, spike and anchor patterns, tie cracks, rail head defects and grind marks, plates, jointbars and missing bolts, switches, level crossings, joins, and missing clips and insulator pads for concrete sleepers.
Rail Vision developed InfraVision RailVis software for Network Rail that takes as input a sequence of top or angular view images and generates both visual and statistical outputs. The software operates on a sequence of images taken by line or area scan camera with NMT train speed up to 200 km/hr. The hardware system was originally installed by Cybernetix of France.
RailVis software provides the image analysis software to process these images for detecting rail features, defects and condition that can be efficiently fed into asset and track maintenance systems. The software at present is capable of automated detection of the following components using a range of camera views through image analysis: sleepers, check rails, switches, level crossings, clamps, adjustment switches, clips, defects, fishplates, tpws, and joins. In addition, the software can detect missing components (clips, housings, etc.) and classify them. The front end software presents the results of analysis and reports in a format required by Network Rail.
Rail Vision developed a track imaging system for Channel Tunnel Rail Link. The system uses four line-scan cameras with dedicated lighting unit for capturing data at speeds up to 200 km/hr. Rail Vision installed the camera hardware on CTRL inspection vehicle and provide a complete software solution for image capture, archiving and image analysis for finding assets, defects and run by run exceptions.
Visual system prototypes for London Underground and Heathrow Express
Rail Vision developed proof-of-concept prototypes for Heathrow Express and London Undrground for clip recognition, classification, detecting missing clips, weld recognition, and measuring parameters from rail-wheel interface. During 2010, Asset Inspection Train will image these rail networks and Rail Vision is in discussion with Tubelines on how best to automate the visual recognition tasks.
Horus image interpretation system for Strukton
Rail Vision developed a prototype for Strukton's Horus hardware developed for high speed track imaging in 2007/2008. The system was designed to automate the process of extracting image features from Horus hardware. The system is capable of measuring rail width, reporting on rail head defects and performing check rail measurements.