A new study was just published on
by Mostafa Hoseini, Stefano Puliti, Stephan Hoffmann and Rasmus Astrup.
Sustainable forest management systems require operational measures to preserve the functional design of forest roads. In this recent study, an automated system using consumer-grade optical sensors to monitor forest road surface deterioration was developed. This solution utilizes the YOLOv5 model, enhanced with StrongSORT tracking, to detect and track potholes in footage from vehicle-mounted cameras in diverse geographical regions under different weather conditions. The trained model was applied to a forest road in southern Norway, recorded with a GNSS−fitted dashcam and an exemple road deterioration map was compiled, which can be used for scheduling road maintenance operations.