Using terrestrial and UAS imagery collected over a period of time, L3Harris’
rail specific analytics can identify relevant changes that augment the
manual inspection of rail lines. This change detection analysis identifies
broken ties, fouled ballasts, missing fasteners, and more. When deep
learning technology is applied to terrestrial based LiDAR, assets along
the rail corridor can be extracted, and using aerial LiDAR data, this
capability can extract the rail lines themselves. When SAR data is analyzed,
subsidence can be monitored along rail corridors to enable rail operations
to correct issues before they become costly problems.