Abstract
A semi-/autonomous driving car requires local weather information to identify if it is working inside its operational design domain and adapt itself accordingly. This information can be extracted from changes in the detections of a light detection and ranging (LIDAR) sensor. These changes are caused by modifications in the volumetric scattering of the atmosphere or surface reflection of objects in the field of view of the LIDAR. In order to evaluate the use of an automotive LIDAR as a weather sensor, a LIDAR is placed outdoor in a fixed position for a period of 9 months covering all seasons. As target, an asphalt region from a parking lot is chosen. The collected sensor raw data is labeled depending on the occurring weather conditions as: clear, rain, fog and snow, and the presence of sunlight: with or without background radiation. The influence of different weather types and background radiations on the measurement results is analyzed and different parameters are chosen in order to maximize the classification accuracy. The classification is done per frame in order to provide fast update rates while still keeping an F1 score higher than 80%. Additionally, the field of view is divided into two regions: atmosphere and street, where the influences of different weather types are most notable. The resulting classifiers can be used separately or together increasing the versatility of the system. A possible way of extending the method for a moving platform and alternatives to virtually simulate the scene are also discussed.