Machine Vision Technology

Machine vision uses a computer that attempts to directly understand the location of images sent to it by means of a video camera. Machine vision encompasses a variety of approaches. Fundamentally, the system attempts to measure its environment. This can be a very difficult task, so the system tries to simplify the problem. The system typically uses triangulation to determine position, and multiple markers to determine orientation. Accuracy is dependent on target size and baseline of the triangulation. However, in many medical applications, the environment (such as operating room lighting) can be difficult to control and may reduce the effectiveness of this technology.

Advantages and Disadvantages

Advantages	Disadvantages
Can be minimally intrusive to existing applications Targets tracked can be anything from an item itself to a simple black and white target	Requires line-of-sight between tracker and target A less intrusive system typically means a less robust or flexible system Lighting conditions and background interference (complexity) can cause tracking problems

Summary

Although machine vision looks appealing from the perspective of minimal impact (with the exception of line-of-sight), there are many difficult implementation and environmental problems. These problems prevent machine vision from being broadly applicable. It is rare to find a machine vision solution that considers usability and minimizes application interference.

An alternative to products using machine vision technology is the Polaris family of products, which use another form of optical measurement as their core technology. The Polaris technology has been widely accepted within the medical market.