Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving [dataset]

We present Dur360BEV, a novel single spherical camera autonomous driving dataset equipped with a high-resolution 128 channel 3D LiDAR and RTK-refined GNSS/INS localisation, as well as a sample benchmark architecture designed to generate Bird's-Eye-View (BEV) maps using only the single spherical camera input. This dataset and benchmark address the challenges of BEV generation in autonomous driving, particularly by reducing hardware complexity through the use of a single 360-degree camera instead of multiple perspective view cameras. Within our benchmark architecture, we propose a novel spherical-image-to-BEV module that leverages spherical imagery and a refined sampling strategy to project features from 2D to 3D. Our approach also includes an innovative application of focal loss, specifically adapted to address the extreme class imbalance often encountered in BEV segmentation tasks, that demonstrates improved segmentation performance on the Dur360BEV dataset. The results show that our benchmark not only simplifies the sensor setup but also achieves competitive performance against contemporary state of the art approaches.