Image Based 3D Reconstruction for Rail Profile Measurement

To find surface defects on rails and prevent further damage, it is important to regularly inspect and record measurement data of railway tracks. This thesis investigates and implements a railhead measurement method using image-based three-dimensional reconstruction, which enables rapid scanning of railheads and production of detailed cross-sectional measurements. A complete workflow for reconstructing railheads from images and extracting cross-sectional measurements from the reconstructed model is presented. Experiments in the laboratory environment and the real railway site have both been performed. The results show that the proposed method provides comparable results with industrial practices.