🤖 AI Summary
To address camera perception failure under adverse weather and lighting conditions, this paper proposes a road marking segmentation method leveraging reflectance data from a 64-channel LiDAR. The method first performs road-plane segmentation followed by region-growing clustering; it then robustly extracts markings using reflectance—rather than raw intensity—combined with adaptive Otsu thresholding and RANSAC-based line model fitting. Key contributions include: (1) the first systematic empirical validation that LiDAR reflectance significantly improves marking segmentation accuracy and robustness over intensity-based approaches; and (2) an end-to-end, annotation-free, lightweight segmentation pipeline. Evaluated on real-world urban roads at 60 km/h and highways at 100 km/h, the method demonstrates stable and reliable performance across diverse environmental conditions. It enables all-weather, high-confidence lane marking perception for autonomous driving systems.
📝 Abstract
Lane detection algorithms are crucial for the development of autonomous vehicles technologies. The more extended approach is to use cameras as sensors. However, LIDAR sensors can cope with weather and light conditions that cameras can not. In this paper, we introduce a method to extract road markings from the reflectivity data of a 64-layers LIDAR sensor. First, a plane segmentation method along with region grow clustering was used to extract the road plane. Then we applied an adaptive thresholding based on Otsu's method and finally, we fitted line models to filter out the remaining outliers. The algorithm was tested on a test track at 60km/h and a highway at 100km/h. Results showed the algorithm was reliable and precise. There was a clear improvement when using reflectivity data in comparison to the use of the raw intensity data both of them provided by the LIDAR sensor.
