The question often comes up as to what is the most appropriate approach to take in implementing a machine vision system - using a Smart Camera or using some sort of PC-based approach. There is no question that as the microprocessor, DSPs and FPGAs are getting faster and, therefore, more capable, Smart Cameras are getting smarter. Hence, they are a challenge to more ''traditional'' approaches to machine vision. Significantly, however, ''traditional'' approaches are also taking advantage of the advances and so, too, are faster and smarter.

''Traditional'' approaches more often than not today mean an implementation based on a PC. This could be either using a camera with the capability to interface directly to the PC (IEEE 1394/Firewire, CameraLink, LVDS, USB, etc.), or a system designed based on a frame grabber or other intelligent image processing board or vision engine that plugs into the PC. In this latter case, more conventional analog cameras are used as the input device.

A Smart Camera, on the other hand, is a self-contained unit. It includes the imager as well as the ''intelligence'' and related I/O capabilities. Because this format resembles the format of many intelligent sensors, these products are often referred to as ''vision sensors.'' More often than not, however, a vision sensor has a limited and fixed performance envelope, while a Smart Camera has more flexibility or tools, inherently capable of being programmed to handle many imaging algorithms and application functions. A PC-based vision system is generally recognized as having the greatest flexibility and, therefore, capable of handling a wider range of applications. One significant difference is that vision sensors/Smart Cameras are essentially single socket units, while PC-based vision systems can generally handle multiple camera inputs.

Another style machine vision system that falls somewhere between the PC-based vision system and a Smart Camera/vision sensor is what some call an ''embedded vision computer.'' This type system is essentially a stand-alone box with frame storage and intelligence. It generally has limited flexibility and comes with a number of fixed application-specific routines. These are distinct from Smart Cameras in that the camera is tethered to the unit rather than self-contained. They often have the ability to handle multiple camera arrangements, which can be useful for many applications.

All these systems can be found with high-resolution imagers (nominally 1000 X 1000) and/or color imagers. Interestingly, versions are often competitively priced. Some smart cameras and virtually all PC-based imaging capabilities can handle applications that require line scan cameras as well.

1. What are the advantages/disadvantages of PC-based machine vision versus Smart Camera-based machine vision?

PC Based Machine vision advantages:

Flexibility - The PC offers greater flexibility in the number of options that can be selected. For example one can use a line scan versus an area scan camera with the PC. One can use third party software packages with the PC approach (Smart Cameras tend to be single source software).

Power - PC's tend to offer greater power and speed due in large part to the speed of the Intel processors used internally. This power in turn means that PC's are used to handle the ''tougher'' applications in machine vision.

Smart Camera Advantage:

Cost - Smart Cameras are generally less expensive to purchase and set up than the PC solution since they include the camera, lenses, lighting (sometimes), cabling and processing.

Simplicity - Software tools available with Smart Cameras are of the point-and-click variety and are easier to use than those available on PC's. Algorithms come pre-packaged and do not need to be developed, thus making the Smart Camera quicker to setup and use.

Integration - Given their unified packaging, Smart Cameras are easier to integrate into the manufacturing environment.

Reliability - With fewer moving components (fans, hard drives) and lower temperatures, Smart Cameras are more reliable than PC's.''

2. Does one approach have limitations that the other one does not have?

Philip Colet: ''Absolutely, but while one approach has a strength (simplicity for example), the other approach has a different opposite strength. So while PC's are not as simple as Smart Cameras, they are more flexible and can handle a wider variety of applications. What it comes down to are classes of applications and users. When they are evaluating each approach they will use their own criteria to make their selection. Perhaps for a manufacturer of pill bottles, flexibility is not as important as reliability, and they would, therefore, opt for a Smart Camera.''

3. Are these competing products or complementary products? How so? Please explain why you answered the way you did.

Philip Colet: ''Smart Cameras and PC based solutions fulfill different segments of the market. Smart Cameras are not displacing the use of PC's; rather they are fulfilling a need, which was not being addressed by the PC-based solution. This differentiation continues to this day. In this way they do not compete, but are targeted solutions for different niche segments.''

4. Are there applications for which one approach is better suited than the other? What are they?

Philip Colet: ''Any application that is very high speed, or requires a complex algorithm is more suited for the PC based approach. So for example gauging, and part placement are good applications for Smart Cameras. Surface inspection on the other hand is more suited to the PC approach.''

5. What differentiates performance between the two approaches? Hardware? Software?

Philip Colet: ''Hardware definitely differentiates between the two approaches. In a Smart Camera, the central processor will be limited in performance because of concerns over power consumption/dissipation, reliability, and maximum package size. In the PC approaches these concerns are not present allowing much higher speed processors to be used, and thus much higher performance.''

6. Is one approach easier to integrate than the other? Please explain why.

Philip Colet: ''Smart Cameras are easier to integrate, since the camera/processor/lenses and cable are usually sourced from one vendor.''

7. How do installation prices compare when all components are included?

Philip Colet: ''For a single camera installation, the price of both approaches is approximately equal. When multiple cameras are being used, then the PC approach is definitely cheaper, since one PC can handle multiple cameras.''

8. Are there technology trends (e.g., in components) that will have an impact that will favor one approach over the other?

Philip Colet: ''Yes, in general the performance of the Smart Camera will continue to increase. This will mean that the Smart Camera will be used for more difficult applications, slowly displacing the PC approach.''

Conclusion

Is there a conclusion one can draw from all this? Clearly, there are a number of different products with different performance envelopes that are competing in the machine vision market. The difference in their performance envelopes is getting less and less clear given the advances in the underlying compute technology. Assessing which is the most appropriate product for an application requires 1) an understanding of the functional requirements, interface requirements, shop floor personnel capabilities, material handling and 2) definition of whether the actual system integration will be handled internally or externally - where will the machine vision application engineering skills come from. Ultimately the application requirements and where the vision skill set will come from will dictate which approach is best.

Fortunately as the costs of the underlying technology on which all these machine vision approaches are based gets cheaper, the prices of all machine vision technical approaches will become cheaper. However, bare in mind, the integration costs are not coming down for applications that do not involve ''off-the-shelf'' solutions.

This article appears courtesy of the AIA. October 7th, 2002.