Method and device for estimating near-end docking monocular pose of AUV (Autonomous Underwater Vehicle) based on dense point reconstruction

The invention discloses an AUV near-end docking monocular pose estimation method and device based on dense point reconstruction. The AUV near-end docking monocular pose estimation method comprises the steps that an underwater image is acquired through a built-in monocular camera of an AUV; carrying out image preprocessing on the underwater image; the preprocessed image is input into a deep learning model for near-end docking pose estimation for pose estimation, and the deep learning model comprises a target object detection module which is used for detecting a target object in the preprocessed image and generating a target object image block; a dense point reconstruction module of the target object in the docking station extracts features from the block diagram of the target object and reconstructs dense point coordinates of the target object by adopting a coding-decoding network; the normal vector supervision module is used for recovering a surface normal vector diagram of the object from the target object b