GS-CA:基于不确定性驱动的跨模态雷达相机三维目标检测OA

This work investigates the advantages of millimeter-wave radar-camera fusion over vision-only ap-proaches and addresses the challenge of dynamic modality reliability.Therefore,a new multimodal fusion framework,GS-CA,an adaptive camera-radar fusion method for handling 3D perception tasks in the BEV perspective,is designed by introducing the discrete selection mechanism of the Gumbel-Softmax differentiable.The description of feature uncer-tainty is added during fusion and incorporated into the model training to increase the interpretability and provide im-provement directions for model optimization.Additionally,a corresponding deformable cross-attention mechanism is de-signed to increase the interaction of the two-modal BEV features.In the model evaluation,the methods show consider-able performance on the nuScenes dataset,and the target detection model demonstrates promising results in rainy and dark scenes in addition to ordinary scenes.Overall,the proposed framework establishes a new paradigm for multimodal fusion and offers valuable insights for the advancement of sensor fusion technologies.