In-Motion Railroad Tie Deflection Measurement via Ultrasonic Airborne Sonar and Computer Vision Techniques

ABSTRACT It is known in the railroad maintenance engineering community that the deflection of railroad ties is an indicator of the quality of the tie–ballast interface, whose deterioration may cause dangerous train derailments. A new technology is proposed to reconstruct the full-field deflection profile of railroad ties in-motion by means of non-contact ultrasonic testing and computer vision techniques. The sensing layout consists of an array of air-coupled capacitive transducers (operated in pulse-echo sonar-based ranging mode) and a high frame-rate camera, rigidly connected to the main frame of a moving train car. The acquisition system is programmed such that the synchronized waveforms and images are collected and saved as train car moves. In the processing stage, a supervised machine learning-based image classification approach is developed to demarcate the tie boundaries. For this purpose, the Speeded-Up Robust Features (SURF) and Bag of Visual Words (BOVW) algorithms are employed to encode images into condensed feature vectors, which are subsequently fed into the Support Vector Machine (SVM) to train a classifier. The relative deflections of the identified ties are eventually computed by tracking the time-of-flight of the reflected waves from the surfaces flagged as tie. An image processing technique is also developed to estimate the spatial resolution of the tracking system, required to reconstruct the full-field deflection profile of the scanned ties. The importance of such a technique is stressed if the test run is performed without any dedicated positioning system. The proposed ‘tie sonar’ system was prototyped and used to reconstruct the deflection profile of the ties scanned during a series of test runs conducted at slow (walking) speed at the Rail Defect Testing Facility (RDTF) of UC San Diego as well as a BNSF yard in San Diego, CA, with a realistic train load. Further developments of this system should include a performance evaluation at higher speeds (e.g., revenue speed).