In the field of autonomous driving, environmental perception is crucial for driving safety. Addressing the limitations of existing visual perception methods in complex scenarios, this study proposes a deformable depth visual perception framework based on a multi-camera system. The framework processes multi-camera data through a feature extraction network to generate and fuse multi-scale features. And a deformable depth prediction mechanism incorporating self-vehicle temporal difference features is introduced to enhance the accuracy of the model in depth prediction. Experimental results show that on the NuScenes dataset, our method achieves a detection accuracy (mAP) of 0.508 using only 5 random cameras out of 6, surpassing existing technologies such as Lift-Splat (0.446), RC-BEVFusion (0.476), and SOGDet-SE (0.474). Future research will focus on improving the prediction accuracy of distant vehicles to further enhance the performance of the model.