Evaluating Pavement Lane Markings in Metropolitan Road Networks with a Vehicle-Mounted Retroreflectometer and AI-Based Image Processing Techniques

The objectives of this study were to evaluate pavement lane markings in a metropolitan road network and develop maintenance strategy for safe daytime night-time driving. To achieve this, data on the retroreflectivity physical defect ratio collected remotely using vehicle-mounted retroreflectometer high-resolution camera. was measured analyzed by type (city freeways, arterial roads, collector roads) color (yellow, white, blue) over total length 6790.34 km. results indicate that retroreflective performance deteriorates most case white lanes, regardless classification, especially first lane. Additionally, defects investigated 502.82 km categorized classification color. Mask R-CNN Otsu Threshold method used automatically calculate ratios defects. city freeways show lower than roads all colors. Moreover, there is no significant difference between lanes types roads. distribution trends relationship discussed according color, selecting priority suggested. number requiring restoration increases as increases. Therefore, we suggest prioritizing work with higher defects, covering proportion low-retroreflectivity sections. In addition, unit averaging can be adjusted improve efficiency.