Weather Classification Using an Automotive LIDAR Sensor Based on Detections on Asphalt and Atmosphere

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.

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

“…The confined particles were distributed uniformly over the violet volume in Figure 4 but were emitted randomly with a lifetime of one frame. This generates a distribution of detections similar to the one observed in real rain measurements using the same sensor [ 8 , 10 ].…”

“…In order to calibrate the intensity of the light source, the accumulated histogram of the real and synthetic echo pulse width (EPW, proportional to the intensity of the reflection [ 8 ]) values were compared. This was done before adding the box to the simulation.…”

“…Recently, LIDAR sensors have also been used mostly due to their high resolution, ability to work under low light conditions and direct distance measurement [ 4 , 5 ]. However, the high resolution obtained by using infrared light comes at the cost of a reduced performance when dirt [ 6 ], rain, fog [ 7 ], snow [ 8 ], exhaust gases [ 9 ] and spray water [ 10 ] are present. Besides reducing range, these phenomena cause extra detections which can have negative effects like phantom braking.…”

Measuring the Influence of Environmental Conditions on Automotive Lidar Sensors

“…Sunlight has two different forms of impact on lidar sensors. The first one is ambient light or background radiation as already analyzed by [ 22 ] with a Valeo Scala lidar. In this study, no difference in detection intensity due to ambient brightness was detected for any of the three sensors.…”

“…The detections on the different materials are analyzed in terms of range, intensity, and the number of points on the objects of interest. Vargas Rivero et al [ 22 ] took a similar approach mounting a Valeo Scala lidar on the top of a roof, oriented downwards onto an asphalt parking lot. Measurements were taken over a period of 9 months covering rain, snow, fog, and different background lighting conditions.…”