3D System for Robotics Applications

While many machine vision systems are two-dimensional, a growing trend towards 3D technology is making substantial headway, particularly with robotics applications.

3D vision systems deliver highly-accurate, real time data. 3D machine vision systems can detect objects, no matter what their position, giving robots more flexibility and independence.

Vision Systems Design featured an article by Andrew Wilson titled “Choosing a 3D Vision System for Automated Robotics Applications” addressing some key issues in 3D vision systems. Wilson explores 3D systems and suggests which system should be used for a range of applications.

Choosing a 3D Vision System

While robotic bin picking, object tracking, and product profiling demand three-dimensional image data generation, Wilson acknowledges that integrators must weigh their options with both passive and active techniques to capture the data. There are often price-performance tradeoffs.

According to Wilson:

While passive 3D systems such as stereo camera implementations only require ambient lighting, active lighting such as structured laser light and projected pattern-based lighting systems use external lighting sources to illuminate the object to be measured. This difference in illumination method is important since the less well-defined features an object may have, the less accurate the system will be when passive lighting is used.

This is not the case, however with active lighting systems, since a known structured light or projected light pattern light pattern is used to illuminate the object. However, using active lighting can result in measurement inaccuracies, especially when the edge of objects or objects with varying surface finishes need to be imaged.

The article determined that choosing a 3D vision system is highly dependent on the parts being measured.

“While laser range finders using time of flight methods can be used to locate distant objects, stereo imaging systems may be better suited to imaging high-contrast objects. Where such objects are highly specular, it may be more useful to employ projected texture techniques. Luckily, numerous articles are now available to guide the systems developers towards the correct choice of 3D imaging systems,” said Wilson.

To read the full article, visit Vision Systems Design.

Reach Out