Cross-Dataset Experimental Study of Radar-Camera Fusion in Bird's-Eye View
This addresses perception robustness for autonomous driving systems, but appears incremental as it builds on existing fusion paradigms with new network architecture.
The authors tackled radar-camera fusion for object detection in bird's-eye view, proposing a flexible fusion network and evaluating it on nuScenes and View-of-Delft datasets. Their results show the fusion approach significantly outperforms camera-only and radar-only baselines, with transfer learning improving camera performance on smaller datasets.
By exploiting complementary sensor information, radar and camera fusion systems have the potential to provide a highly robust and reliable perception system for advanced driver assistance systems and automated driving functions. Recent advances in camera-based object detection offer new radar-camera fusion possibilities with bird's eye view feature maps. In this work, we propose a novel and flexible fusion network and evaluate its performance on two datasets: nuScenes and View-of-Delft. Our experiments reveal that while the camera branch needs large and diverse training data, the radar branch benefits more from a high-performance radar. Using transfer learning, we improve the camera's performance on the smaller dataset. Our results further demonstrate that the radar-camera fusion approach significantly outperforms the camera-only and radar-only baselines.