What Is 3D Vision?
3D vision means the utilization of 3D information with the aid of machine
vision, allowing to approach applications which so far could not be
solved with classical 2D technologies. It includes two main
objectives, which both contain many different technologies:
3D reconstruction: the 3D shape of an object is reconstructed
from the images of a two camera setup.
3D aligment: using a camera image and various image
processing functions, the 3D pose of an object is determined. This
data is used to control the robot.
3D reconstruction – determining the 3D shape of
3D alignment – finding the 3D pose (position &
orientation) of an object.
From the Task to the Solution
For any project, in order to find a solution, you must identify the
specific vision task. First, you should ask the following questions
before deciding which 3D vision method is the right one for you:
For example, if you ask these questions for a
bin picking application,
the answers could be as follows:
- What do I want to find out?
- How accurately do I want to measure?
- Which are the characteristics of my object?
- What are the general conditions?
This analysis is very important, because the next step will be the
decision which technology to use. The different technologies have
various characteristics which must match the specific needs of your
What do I want to find out?
Shape is known,
position is required.
How accurately do I want to measure?
Adequate for the robot's movement.
Which are the characteristics of my object?
Object size 10-20 cm,
reflective metal surface.
What are the general conditions?
3D vision technologies are used in many different industries, such as
- photogrammetry & remote sensing
- precision farming
3D Vision Technologies