Method for automatically acquiring feature point parameters of target object

Abstract

The invention relates to a method for automatically acquiring feature point parameters of a target object, which comprises the following steps: S1, mounting an image acquisition device at the tail end of a mechanical arm, and driving the image acquisition device by the mechanical arm to shoot a two-dimensional image of the target object; s2, obtaining a mechanical arm coordinate system of a mechanical arm, and obtaining the relative position relation between an image collecting device and the mechanical arm coordinate system based on a hand-eye calibration mode; s3, obtaining pose parameters of the mechanical arm, and obtaining machine position pose parameters of the image collecting device on the basis of the pose parameters and the relative position relation; s4, acquiring an image projection coordinate system in the image acquisition device and a world coordinate system of the position of the target object; s5, acquiring a target pose of a target object in the two-dimensional image based on the camera pose parameters, the image projection coordinate system and the world coordinate system; and S6, obtaining feature point parameters of the target object based on the target pose. The method is high in efficiency.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for automatically acquiring the parameter of a feature point of a target object. Background technique [0002] Pose estimation has applications in many fields such as robot vision, motion tracking, and single-camera calibration. The sensors used for attitude estimation in different fields are different. Here we mainly talk about vision-based attitude estimation. Vision-based pose estimation can be divided into monocular vision pose estimation and multi-eye vision pose estimation according to the number of cameras used. [0003] At present, many research programs are basically based on the laser point cloud to estimate the target attitude, and the hardware equipment used to obtain the data is extremely expensive and has a short service life. At the same time, its processing process is complex and inefficient due to its large amount of data. Contents of the invention [0004]...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for automatically obtaining the parameter of the feature point of the target object to solve the problem of low efficiency of obtaining the parameter of the feature point

Images