Drone-Supervised Multimodal Sensor Fusion for Infrastructure-Based Vehicle Detection in Bird’s Eye View

Smart intersection monitoring systems face critical limitations when relying on single-sensor modalities, with cameras degrading under poor visibility and radar struggling with sparse point clouds. This work presents a novel multi-modal sensor fusion framework that integrates radar and camera detections through adaptive range-dependent strategies for robust vehicle detection across diverse operational conditions. We develop a radar detection pipeline that leverages drone-supervised learning to t