Transfer Learning Approach for Railway Technical Map (RTM) Component Identification

Railway Transportation is extremely popular all around the globe and urges the requirement of digitized databases that includes railway track information with all railway track components such as signals, switches and mileposts (Figure 1). A Railway Technical Map (RTM) is a complex diagram (Figure 1) which includes all the information associated with a railway track. At present, most railway companies maintain RTMs designed with computer aided software, yet they are only available in PDF format. These contain partially distorted map components where identifying those components using basic digital image processing techniques is hard due to its complexity. This work focuses on implementing an automated system to generate CSV formatted files for given RTM input images containing all the digitized data that can be used with further decision support tools. The final formatted text will include the component associativity with mileposts, component names and descriptions.