基于混合针孔和鱼眼相机的多视图鸟眼图物体检测基准测试
Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras
AI总结：
本文提出混合相机配置下的多视图鸟眼图检测基准，通过转换KITTI-360为nuScenes格式，评估了三种BEV架构在不同策略下的性能，证明投影自由架构更抗鱼眼畸变。
摘要：
现代自动驾驶系统越来越多地依赖混合针孔和鱼眼相机配置以实现全方位感知。然而，鸟眼图（BEV）3D物体检测模型主要为针孔相机设计，导致在鱼眼畸变下性能下降。为此，我们引入了混合相机的多视图BEV检测基准，通过将KITTI-360转换为nuScenes格式。我们的研究涵盖三个适应：用于零样本评估的校正、对nuScenes训练模型的微调、基于MEI相机模型的视图转换模块（VTMs）以及极坐标表示以更好地对齐径向畸变。我们系统评估了三种代表性的BEV架构，即BEVFormer、BEVDet和PETR，在这些策略下的性能。我们证明投影自由架构在抗鱼眼畸变方面比其他VTMs更鲁棒和有效。本文建立了首个真实数据3D检测基准，包含鱼眼和针孔图像，并提供了系统适应和实际设计鲁棒且低成本3D感知系统的指南。代码可在https://github.com/CesarLiu/FishBEVOD.git获取。
英文摘要：
Modern autonomous driving systems increasingly rely on mixed camera configurations with pinhole and fisheye cameras for full view perception. However, Bird's-Eye View (BEV) 3D object detection models are predominantly designed for pinhole cameras, leading to performance degradation under fisheye distortion. To bridge this gap, we introduce a multi-view BEV detection benchmark with mixed cameras by converting KITTI-360 into nuScenes format. Our study encompasses three adaptations: rectification for zero-shot evaluation and fine-tuning of nuScenes-trained models, distortion-aware view transformation modules (VTMs) via the MEI camera model, and polar coordinate representations to better align with radial distortion. We systematically evaluate three representative BEV architectures, BEVFormer, BEVDet and PETR, across these strategies. We demonstrate that projection-free architectures are inherently more robust and effective against fisheye distortion than other VTMs. This work establishes the first real-data 3D detection benchmark with fisheye and pinhole images and provides systematic adaptation and practical guidelines for designing robust and cost-effective 3D perception systems. The code is available at https://github.com/CesarLiu/FishBEVOD.git.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
