Object attitude estimation method, device and equipment

Abstract

The invention provides an object attitude estimation method, a device and equipment, relates to the technical field of computer vision, and is used for improving the robustness of object attitude estimation. The method comprises the following steps: predicting a target image of a target object by adopting a pre-trained multi-level feature extraction network model to obtain key point coordinate information of the target object; according to the coordinate information of the key points of the target object and the spatial position relationship of the key points of the target object, determininga coordinate conversion relationship of the camera relative to the object; wherein the multi-level feature extraction network model is used for performing feature extraction on a two-dimensional imageof a three-dimensional object by adopting a multi-level feature extraction network; and carrying out feature fusion on the output feature map of each layer of feature extraction network to obtain a target feature map, and then carrying out attitude regression prediction on the target feature map to obtain projection coordinates of key points of the three-dimensional object on the two-dimensionalimage.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to an object attitude estimation method, device and equipment. Background technique [0002] With the development of information technology and artificial intelligence, society has increasingly strong requirements for automation and intelligence, and technologies such as virtual reality, autonomous driving and robots are also receiving more and more attention. Among them, the object attitude estimation technology based on monocular vision can solve the attitude information of the camera relative to the object, and the spatial shape around the object can be constructed according to the attitude information, so it plays an important role in technologies such as virtual reality, automatic driving and robots. . [0003] At present, object pose estimation methods based on monocular vision are mainly divided into two categories: the first is the pose estimation method for...

AI Technical Summary

Problems solved by technology

[0005] However, the current object pose estimation methods only consider how to fuse multiple information. For monocular cameras with far and near changes, it is difficult to estimate the object pose information, so the robustness is low.

Images