Comparative Study of Machine Learning Approaches for Fixed Radar-Based Road User Classification

This study investigates radar-based road user classification using a fixed infrastructure setup. It evaluates two machine learning (ML) strategies: (1) deploying separate classifiers for single-point and multi-point radar detections and (2) utilizing a unified classifier for both object types. The study uses four supervised learning models: Random Forest (RF), Extreme Gradient Boosting (XGB), Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM), which are trained on statistical features extracted from annotated 3D radar point clouds in the INFRA-3DRC dataset. Feature extraction procedures are adapted to address the structural disparity between single- and multi-point detections, with feature padding applied to ensure compatibility with the unified model. Experimental results show that XGB and RF consistently achieve the highest F1-scores, exceeding 97%, under both modeling approaches. The unified classifier offers deployment simplicity and real-time readiness, while the separate strategy provides lower prediction latency for time-sensitive applications. Overall, the findings confirm the viability of scalable, radar-only traffic monitoring systems and underscore the trade-offs between accuracy, computational cost, and architectural complexity. Future work will explore temporal modeling using recurrent neural networks to capture object dynamics across frames.