13 June 2024 in IEEE Transactions on Intelligent Transportation Systems
Light detection and ranging sensors (LiDARs) have become indispensable for autonomous vehicles because of their high detection accuracy and independence from lighting conditions. At present, although LiDARs with various beams have been developed, their performance is degraded to varying degrees in severe weather such as rain and snowfall. This restricts the reliable operation of autonomous vehicles in all weather and all scenes. To quantitatively evaluate the impact of snow on LiDAR performance, this paper creates and publishes a LiDAR point cloud dataset (MSP dataset) covering different LiDAR models, snowfall intensities, and test scenarios. Through theoretical and data-driven analysis, the influence of snow on the performance parameters of LiDAR, such as point cloud distribution, detection range, and sensing accuracy, is evaluated qualitatively and quantitatively. The experimental results show that the presence of snow induces a significant amount of noise in LiDAR systems. The level of noise varies with distance and height, following the Gamma and t location-scale distributions, respectively. During heavy snowfall, the recognition of vehicles and pedestrians by LiDARs is reduced by 50% and 20%, respectively. The target detection accuracy is reduced by about 9 percentage points, and the effective detection distance is reduced by 14-17m. The sensing performance of LiDAR will be significantly reduced within the range affected by snowflake noise. The research results of this paper provide important data and a theoretical basis for evaluating the performance of LiDAR-based autonomous driving systems during snowfall conditions and designing corresponding LiDAR sensing and processing methods.
25 October 2022 in IEEE Sensors Journal
Rain and snowfall will increase noise, change the resolution of objects in the point cloud and present great challenges to the accurate recognition of traffic objects. Accordingly, this paper proposes an efficient real-time method for roadside 3D Light Detection and Ranging (LIDAR) background point cloud extraction and object segmentation under snowy weather. We first use a historical point cloud sequence to quickly construct a background model, extract the background point cloud from the current frame by using a background difference method and update the background model in real-time. Then, the noise caused by snowfall in the non-background point cloud is filtered based on the beam density difference of the object point clouds. Finally, the remaining object point cloud is accurately segmented based on the proposed hierarchical object clustering method. We use an intelligent roadside system equipped with 3D roadside LIDAR to collect point cloud data in a snowfall environment and evaluate the proposed method qualitatively and quantitatively. Experimental results show that the proposed method effectively avoids the problem of under-segmentation and over-segmentation of object point clouds under snowy conditions, and the precision and recall rate of traffic object segmentation reached 96.41% and 95.02%, respectively, thereby indicating a significant improvement in the accuracy and reliability of traffic object detection using roadside LIDAR under snowy conditions.
7 May 2026 in Expert Systems with Applications
27 February 2026 in IEEE Transactions on Intelligent Transportation Systems
LiDAR is widely used in autonomous driving and intelligent roadside perception systems due to its high detection accuracy and light independence. However, snowfall has a significant impact on LiDAR, increasing noise and changing object resolution in point clouds, posing a significant challenge to the task of traffic object detection using LiDAR. This paper proposes a probabilistic model-driven adaptive filter for effectively removing snowfall noise from LiDAR point clouds and improving LiDAR detection capabilities under snowfall conditions. First, the proposed filter extracts snow noise from a point cloud, creates a spatial distribution model for the snow noise, and obtains the model’s key parameters. Then, the snow noise is extracted using a density filter based on the spatial model, which is iteratively optimized. Compared to existing methods, the filter is more scene-adaptable and less dependent on priori datasets, and it can effectively remove snow noise from various types of LiDAR sensors under varying snowfall intensities. Experimental evaluation on publicly available datasets, including CADC, BOREAS, and WADS, demonstrates that the proposed method achieves an F1-Score of more than 90 on all three datasets, indicating excellent accuracy and generalizability. Additionally, testing object detection algorithms under snowfall conditions reveal that the proposed filter improves the accuracy of three typical detection algorithms by 5.9, 9.7, and 6.4 percentage points, indicating that our filter improves the performance of downstream 3D target detection tasks under snowfall.