A Robust Camera-LiDAR Fusion Framework for 3D Object Detection in High-Dust Environments

The fusion of camera and LiDAR features in the Bird's Eye View (BEV) perspective has become a prevalent solution for 3D detection in autonomous driving due to its simplicity and efficiency. However, in challenging environments like mining areas with dusty roads, existing BEV-based fusion networks struggle due to dust occlusion and misidentification of dust as obstacles. To address this, we propose a robust fusion framework that integrates fine-grained depth supervision and channel-wise attention mechanisms. Combined with a temporal multi-frame mechanism, our framework effectively mitigates issues caused by dust occlusion and misidentification. We validated our method's detection accuracy on a self-constructed mining road dataset, achieving 89.6% mAP, surpassing BEVFusion's 88.3% mAP. Tests on sensor occlusion and failure further demonstrated its robustness in adverse conditions typical of unstructured road scenarios.