Though the vast majority of machine vision applications are solved using two-dimensional imaging, machine vision applications utilizing 3D imaging are a growing niche within the industry.

This 3D machine vision technology is most commonly used for three- dimensional inspection and measurement of complex free formed surfaces. New applications are constantly being explored.

Basic 3D technologies involved include the time based ‘time of flight’ technique and techniques based on geometric, angle-based processes. The latter includes laser triangulation, stereo vision, light stripe projection, shape from shading and white light interferometry. The most commonly used method for 3D imaging is laser-scanning based triangulation which utilizes motion of the product the imaging process, see image. T

Today, this line scan principle is also accompanied with area scan systems. These technologies are less suitable for industrial 3D imaging because of their speed limitations.

With 3D vision technology the shape of an object can be captured, as opposed to 2D which only captures contrast. The (extra) height information can be very valuable when determining the quality of a part in its production process. 3D shape measures geometric features on a surface regardless of surface color. 

Potential blind spots caused by shadowing can be solved by using multiple cameras. The data of all these cameras is merged by special software to result in a single set of object data.

Also, 3D vision results in typical raw data that is not directly suitable to display. It is not like a photograph but rather a cloud of points (COD) or point cloud.

 

Other 3D vision methods are:

  • Structured light
  • Stereo or stereoscopic vision
  • Shape from shading
  • Light stripe projection
  • Light field
  • White light interferometry

 

3D vision technology is used because it provides

  • Volumetric measurement (X,Y, and Z-axis) for shape and position related parameters
  • Contrast invariant measurements, ideal for inspecting low contrast objects
  • Immunity to minor lighting variation or ambient light
  • Higher repeatability due to integrated optics, lighting, and pre-calibration
  • Simpler to build multi-sensor setups for large object inspection