FRGB3D: Fast Reliability-Weighted Gaussian Background Modeling for Roadside LiDAR Traffic Monitoring

Abstract Intelligent transportation systems rely on accurate perception technologies for traffic monitoring, with light detection and ranging (LiDAR) emerging as a critical sensing modality. However, effective background–foreground separation is challenging due to the varying measurement reliability across point clouds caused by distance, reflectivity, and atmospheric conditions. This paper presents fast reliability-weighted Gaussian background modeling for 3D LiDAR traffic monitoring (FRGB3D), a novel unsupervised approach for LiDAR point cloud background modeling and foreground detection that explicitly incorporates physics-based reliability assessment with adaptive learning mechanisms. The key contributions include (1) a physics-based reliability metric that quantifies measurement quality using range and reflectivity characteristics, (2) a reliability-weighted adaptive learning approach for Gaussian background modeling that dynamically adjusts learning rates based on point reliability, and (3) an adaptive thresholding mechanism that incorporates both measurement reliability and learned model uncertainty. Through comprehensive experiments using both the Car Learning to Act (CARLA) simulator and real-world LiDAR data collected in Lowell, Massachusetts, we demonstrate that FRGB3D achieves superior foreground detection performance compared with baseline methods. FRGB3D achieved F1-scores of 0.84, 0.68, and 0.77 across base, adverse-weather, and high-density traffic scenarios, respectively, consistently outperforming simple difference, moving average, and standard Gaussian background modeling approaches. Real-world experiments demonstrated competitive object-level performance average precision (AP) ([email protected] = 0.48) while maintaining real-time processing capabilities with 19.1 frames per second (FPS), making it suitable for practical traffic monitoring applications.