Removing Snowfall Noise From Point Clouds Without Considering the Nearest Neighbors

Light detection and ranging (LiDAR) is crucial for recognizing the surrounding environment in autonomous driving. However, snowfall can generate noise in the reflected laser beam of LiDAR, affecting downstream tasks such as object detection in autonomous driving systems. The accuracy and processing speed of existing methods for removing snowfall noise, which primarily adopt approaches based on the nearest neighbors, do not meet the requirements for autonomous driving systems. Considerably, we propose a novel method for snowfall noise removal that does not consider the nearest neighbors; instead, our method establishes threshold values for intensity, distance, and height from the LiDAR by analyzing snowfall noise characteristics. Thus, our method differs from the existing methods. We evaluated the removal accuracy and processing time of our method using the winter adverse driving dataset (WADS). Compared to the existing methods, our method achieves a similar recall but higher precision (by approximately 13.7%) and F-measure (by approximately 7.4%). Furthermore, our method significantly reduces processing time by approximately 93.7%, indicating a substantial improvement in processing speed. Furthermore, to validate its effectiveness, our method was adopted as a preprocessing step for object detection under snowfall conditions, and the Canadian adverse driving conditions (CADC) dataset was employed for evaluation. Results demonstrate that adopting our method led to an approximately 7.6% improvement in the object detection rates (ODRs) compared to detection without our method.