Depth image acquisition method

Abstract

The invention discloses a depth image acquisition method. An internal reference matrix of two depth cameras and a conversion matrix from two depth camera coordinate systems to a robot coordinate system are respectively acquired through calibration, conversion matrixes of the first depth camera and the second depth camera are acquired through calculation, and two depth images are fused to acquire a fusion depth image. The depth image acquisition method is advantaged in that the method is simple and reliable, holes of reflection objects appearing on the depth images can be reduced, and precision and the view field scope are improved.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a depth image acquisition method. Background technique [0002] With the continuous improvement of labor costs and the continuous improvement of automation equipment, the rate of using automation equipment instead of manual production is getting higher and higher. The initial automation equipment does not install any sensors, and can only perform some fixed actions in fixed scenes. As the application environment becomes more and more complex and changeable, it is necessary to install some sensors on the automation equipment so that the information of the object can be observed. A depth camera is a type of sensor that can observe the depth information of an object, so it can more accurately determine the position of the object in space. However, due to the active projection of the light source, when the depth camera shoots reflective objects such as metal, there will be obvious ref...

AI Technical Summary

Problems solved by technology

However, due to the active projection of the light source, when the depth camera shoots reflective objects such as metal, there will be obvious reflections, resulting in holes in the acquired depth image.

Images