Field Imaging Based Assessment of In-Service Ballast Condition Authors

Ballast degradation can cause poor drainage, settlement and reduced lateral stability, which adversely affect railroad track safety and performance. Two indices are commonly used in the North American railroad industry to quantify the level of ballast degradation. These are (i) Fouling Index (FI) and (ii) Percentage Fouling (PF). Identifying these two traditional indices involve ballast sampling and mechanical sieve analyses in the laboratory, which can be time consuming, laborious and costly. Additionally, the locations along the track where ballast samples are collected are localized and like in any other sampling methods may not properly represent the entire ballast cross section. As an automated alternative, machine-vision-based inspection systems have the potential to directly and objectively assess ballast condition and degradation levels from high resolution images of ballast layers captured in the field. This paper presents the initial development and implementation of an innovative computer vison approach for assessing the degradation levels of ballast cross sections. Advanced image enhancement methods,