URNet: An UNet-Based Model with Residual Mechanism for Monocular Depth Estimation

Autonomous vehicle systems rely heavily upon depth estimation, which facilitates the improvement of precision and stability in automated decision-making systems. Noteworthily, technique monocular estimation is critical for one these feasible implementations. In area segmentation medical images, UNet a well-known encoder–decoder structure. Moreover, several studies have proven its further potential estimation. Similarly, based on UNet, we aim to propose novel model constructed from benefits classical residual learning mechanisms named URNet. Particularly, employ KITTI dataset conjunction with Eigen split strategy determine efficacy our model. Compared other studies, URNet significantly better, basis higher lower error rate. Hence, it can deal properly issue autonomous driving