On the suitability of light field imaging for road surface crack detection

Abstract

During traditional road surveys, inspectors capture images of pavement surface using cameras that produce 2D images, which can then be automatically processed to get a road surface condition assessment. In this paper the use of a light field imaging sensor is proposed, notably the Lytro Illum camera, to explore whether the richer information captured by this imaging sensor provides additional cues useful to improve the automatic detection of road surface cracks. The preliminary results obtained indicate the interest in further exploring the disparity information captured by the light field sensor.