DENOISING POINT CLOUDS WITH INTENSITY AND SPATIAL FEATURES IN RAINY WEATHER

LiDAR is important for 3D vision in autonomous vehicles, but rain causes inaccurate LiDAR point clouds due to reflec-tion and scattering. Rain noise removal without loss of en-vironmental features becomes an inevitable challenge. This paper presents a novel point cloud denoising method with intensity and spatial features to solve the problem. It utilizes a weighted edge-preserving filter to recover distorted con-tours and intensities of point clouds due to the reflection of the surface attached by raindrops. A low-intensity filtering method is also proposed to remove low-intensity noise due to the reflection of rainfall. In addition, a semi-synthetic rainy point cloud dataset with point-wise annotations is created, which benefits the research on improving LiDAR perception in adverse weather. Our method outperforms ex-isting methods in terms of precision when it achieves a high recall of 99.28%. Using denoised data by our method can improve target detection accuracy by 5.37%. It is also faster than the state-of-the-art methods and shows the potential for use in snowy weather, making it suitable for all-weather LiDAR applications.