A feature‐based pavement image registration method for precise pavement deterioration monitoring

Over the past decade, pavement imaging systems, particularly 3D laser technology, have been widely adopted by transportation agencies for network-level pavement condition evaluations. State Highway Agencies, including Georgia Department of Transportation (DOT), Florida DOT, and Texas DOT, have been collecting pavement images for over 5 years. However, these multi-year pavement images have not been fully utilized for analyzing detailed pavement deterioration. One challenge is the accurate and efficient registration of multi-temporal pavement images. This study pioneers the use of feature-based methods to address this challenge. It evaluates various feature-based image registration methods, including both state-of-the-art and novel combinations of feature detectors and descriptors. These methods are rigorously assessed using hybrid “step-by-step” and “end-to-end” performance evaluation metrics, with a ground reference dataset containing 100 pavement image pairs featuring diverse crack types and varying year gaps. The results confirm the feasibility of using feature-based techniques to register multi-temporal pavement images. A novel combination of the AKAZE detector and the Binary Robust Independent Elementary Features (BRIEF) descriptor was identified as the best-performing method, successfully registering 96 out of 100 image pairs. This advancement enables pavement engineers to accurately monitor pavement deterioration using multi-temporal images.