Camera Smarts

A discussion with Brad Munster, Visionary Technologies

Brad Munster has a background in electrical engineering and engineering sales and is the owner and president of Visionary Technologies (Holland, MI, USA; www.vis-tech.com). He has been working with smart cameras for more than 11 years. Editor in chief Conard Holton spoke to him about trends in machine-vision systems and service.

VSD: Please describe your company and its services.
Munster: Visionary Technologies is a machine-vision integrator that specializes in the development and deployment of smart vision camera systems. The company provides customers with turnkey inspection machines, retrofits cameras to existing manufacturing lines, and services existing camera systems. I have been in the automation field and with manufacturing companies for 15 years— the first three with a distributor in Australia. We focused on products to serve the mining industry. I later worked as a sales engineer for a high-tech distributor for industrial automation in Michigan and then for a system integrator before starting Visionary Technologies about five years ago.

VSD: What technologies and components do you use for your applications?
Munster: Visionary Technologies uses smart cameras for 90% of its applications. This is something our customers are more familiar with and therefore not as hesitant to implement. The cameras we use come from manufacturers such as Cognex, DALSA IPD, Keyence, National Instruments, and PPT Vision. We continually evaluate all latest technologies to stay current and provide our customers with the best solution within their budgets. We try to choose the best system for the application and not focus on the name on the side of the camera. Each manufacturer has strengths and weaknesses with its products and algorithms. Also we see customers favoring one camera brand over another, and we provide them with a realistic assessment of which system would be best for their application.

VSD: How do you approach a new application? Do you work with OEMs or other system integrators?
Munster: Machine vision is often an oversold technology, or customers think it is a magic pill. Many customers believe that the camera can inspect anything within the field of view—and sometimes out of it—and that it should work flawlessly out of the box. From the first meeting we endeavor to walk them through the integration steps and reset them to a more realistic set of expectations. Some customers think that a camera is like other pieces of automation equipment—once it is programmed everything is done. We prepare them for a lot longer debug time. Instead of two to five days we try to have them expect two to five weeks, or longer, depending on the variables. During this time we often find manufacturing issues that the customer did not believe were relevant or possibly did not know about. Some of our largest customers are other system integrators. In today’s market very few companies have the resources to have a person solely dedicated to a specific task such as a machine vision programmer. This is a problem when you are trying to implement machine vision because you need to be working with this technology every day or you will lose or have to relearn skills and techniques. Some system integrators or machine builders may implement a camera system once every three to six months. We are working on six to eight different projects per week. This keeps skills sharp and also exposes us to many different types of applications and therefore increases our knowledge base and techniques.

VSD: Recent software developments in image processing include pattern recognition, tracking, and three-dimensional modeling. What algorithms and specific software developments do you see emerging in the next five years? Munster: The company has started to develop its own set of tools and algorithms in any given platform. The software or hardware manufacturer often gives you a great starting place for basic inspections and typical applications, but customers can run into problems when they can’t go beyond standard software tools (see photo). We have developed more advanced tools and techniques that let us ‘go under the hood’ by combining multiple tools to make the customer’s algorithms more robust and error proof. Some of the new software developments will probably be based around better OCR and Data Matrix tools. These are becoming more prevalent, with traceability and accountability.

VSD: How do you design your systems for OEM product obsolescence?
Munster: Customers should consider the camera system as an asset and therefore keep in mind potential redeployment options in the future. Redeployment and retooling are definitely new buzz words on the manufacturing floor. Many of the smart cameras can be upgraded to newer versions of software and firmware. Sometimes for upfront incremental cost, the customer can purchase a platform that is more versatile for future use rather than for the immediate application. We have redeployed obsolete camera systems for new applications due to customer budget constraints. Obviously we need to determine in advance if this hardware and software will meet the requirements and if it can be integrated efficiently. Sometimes, a current camera system will offer more advanced software tools that will reduce integration time and therefore lower overall cost of the project.

VSD: In which areas do you see the most growth? What are users demanding from you in the design of new systems?
Munster: Smart camera systems still seem to dominate most factory floors. These systems are becoming easier to use, and the hardware cost continue to go down. While PC-based systems seem to be entering the main stream as customers become more camera savvy, they are still more difficult to deploy and maintain. The bottom line is customers are always demanding the most cost-effective solution to solve their problems. I think they realize more today than they did five years ago that cost of ownership is much more important than up-front cost.

VSD: How will OEM components have to change to meet future needs?
Munster: I think future-proofing projects is something that will help the longevity of any product. Many of the components we use are very versatile. Vision applications change so much from design to implementation that we need components that can change with the application.

VSD: How do you think that the machine-vision market differs in different national or international regions?
Munster: Typically we stay with North America. From an integrator or machine-builder aspect we see regulations as about the only major difference. Several of the principles and technologies are common across the world. Differences from national and international regions have more to do with understanding regulations and certifications than key differences in technologies or their application. It is much like going from plant to plant—each customer has its own set of requirements and standard practices.

VSD: What new markets and technologies do you see for your company in the future?
Munster: The company is growing into more of a service-oriented company rather than a machine builder or system integrator. We have found that we can serve more markets and customers by providing them with “vision experts” as opposed to providing a single machine or camera installation. I see us growing to meet the demand for applications that use PC-based systems. We have geared up to service and supply this technology in the future. Our value to customers is being able to solve their machine-vision problems regardless of platform. If we can come in and work on any type of system they have, we will always add value.

Evolution of software-development tools

Ben Dawson

BEN DAWSON is director of strategic development at DALSA IPD, Billerica, MA, USA; www.dalsa.com

In the beginning there was the library, and there was a multitude of them. The user interface was the library documentation or a text-based interpreter. Libraries and interpreters impose a large memory load--the amount of information a developer has to remember to use the software. The introduction of graphical user interfaces (GUIs) greatly reduced memory load by presenting image-processing functions and program flow as graphical elements that you can pick without remembering their details.

GUIs present functions and program flow control elements as icons or in option lists. They represent functions as icons and program flow control as lines connecting the icons. More recent GUI paradigms include automatic generation of blocks of C or Visual Basic code, spreadsheets, and imaging processing “building blocks” that can be graphically combined.

Most of these paradigms require a developer who is familiar with image processing, for example, knowing about “edge detectors.” To further reduce memory load, newer development tools build image-processing knowledge into domain-specific tools. For example, the DALSA IPD iNspect package provides a “caliper” tool that is familiar to developers doing metrology and that intelligently encapsulates knowledge of “edge detectors.” I think these kinds of development tools are the near-term trend, as they allow more developers to quickly solve most common vision tasks.

Longer term, I see three trends. First, the underlying algorithms will become smarter and more like human vision, so that the imaging setup doesn’t have to be as constrained. For example, image-processing algorithms should be better at ignoring lighting changes, so we can be less concerned with lighting.

Second, there will be more “machine learning,” so a developer can “show” the system defects and let it learn what these defects are and the best ways to find them. Third, the user interface will continue to evolve to reduce memory load. The vision-system designer of 2037 might develop applications by having a dialog with his or her vision system, the way we now instruct a human inspector.

Programming Success

A discussion with Ned Lecky, Lecky Integration

Ned Lecky is owner of Lecky Integration, Albany, NY, USA; www.lecky.com, which was established in 2007. He has held numerous positions in the machine-vision and electronics industries and has taught electrical and computer engineering.

VSD: Please describe your company and its services. What is your personal background in the machine-vision industry?

Lecky: I started my career in machine vision after graduating from college in 1984. I was a systems engineer for Control Automation (CA) in Princeton, NJ, where I was lead vision-system programmer and learned a great deal about custom frame grabbers, cameras, lighting/ optics, and motion control for printed-circuit- board applications. I started Intelec Corp. soon after and continued integrating systems for CA, Cognex, and Intelledex. I got the idea to build a better mousetrap in 1992 and wrote Sherlock, the first industrially focused machine-vision software application for Windows. Intelec became part of Imaging Technology, which then became Coreco Imaging, which then became DALSA. The much evolved and improved Sherlock is still available today. Lecky Integration is a small company that focuses on application-specific integrated solutions involving machine vision, fuel cells, robotics, or custom electronics. As a small business, I seek out vendors, integrators, machine builders, and software professionals to form multi-disciplinary teams to solve complete problems.

VSD: What technologies and components do you use for your applications? How often do you evaluate competing technologies?

Lecky: The distributors or integrators with whom I work often specify cameras and hardware accessories. Many sales leads come through these channels, and it is best business practice to use the hardware and software products that these partners are already representing and supporting. Fortunately, vision hardware and software components are much more inherently compatible than they were even five years ago; this is the blessing and a curse of open system standards. It is a blessing for the consumers of machine-vision technology but can seem a curse to the suppliers who may do a great deal of work to convince a customer that vision is a good solution for their problem, only to have another lower-cost provider come in and sell a competing component for follow-on systems. Ultimately, this is good for the component vendors, since it helps them understand the market, see where costs can be cut, and recognize their own true advantages. However, this “advantage” usually causes bump after bump along the road to knowledge and can be quite challenging.

VSD: How do you approach a new application? Do you work with OEMs or other system integrators?

Lecky: Know your customer. Know your customer’s boss. Understand the customer’s business, both financial and political. Know your customer’s customers and maybe some of their vendors, too. Solving the technical aspects of the application is usually much easier than these first parts, but a good technical solution that flies in the face of business needs is a huge failure. I’ve been there, and it is not pretty, fun, or profitable. All of our solutions involve teams and partners. Teams take time to build and maintain, and a certain trust develops as applications are solved in a professional way that protects and nurtures each team member’s business interests. I have worked with component vendors, distributors, vision-system suppliers, OEMs, R&D organizations, and technical/ nontechnical end users extensively and interchangeably since 1985.

VSD: Recent software developments in image processing include pattern recognition, tracking, and 3-D modeling. What algorithms and specific software developments do you see emerging in the next five years?

Lecky: I think we’re totally stuck, actually. I worked on bio-inspired cognitive computing hardware strategies while getting my M.S. and Ph.D. in electrical engineering. I have long felt that the key to the next advance in machine-vision algorithms is to abandon algorithms altogether and to start, instead, emulating the human image-processing system. The dissatisfaction I have with machinevision systems failing to recognize occluded, fuzzy, out-of-expected-location patterns in variable lighting conditions is not really much less today than it was 20 years ago. Try giving a capabilities demo of a state-of-the-art vision system to someone who has never seen machine vision before and you’ll know what I mean.

Ten or so years ago, I would carefully hand code new algorithms in MMX assembly language to get optimal speed (on 266-MHz Pentiums!). Now, image-processing libraries are comprehensive and effectively free and offer optimized code that can run on multigigahertz, multicore processors. If anything, the hardware is now too fast and too powerful to be fully engaged.

We must find more cognitive and truly intelligent architectures for both hardware and software before major advances can be made. Admittedly, the state of the art is excellent in pattern recognition, tracking, and three-dimensional modeling. However, the accuracy and overall image-processing capabilities of a housefly dwarf those of our current systems, all just using some fraction of a housefly’s million-neuron brain. I find this frustrating.

VSD: How do you design your systems for OEM product obsolescence?

Lecky:: Optics- and lighting-system product lines are quite stable, and same-or-better replacements are generally available when a vendor discontinues a product. Many of the specialty products are built to order anyway, and vendors are often pleased to build an “old” version of a lighting system or a lens. The camera market is extremely dynamic, but again, the new models tend to be same or better for lower cost, so updating to a different camera is often not very painful.

The software, of course, is the issue, especially when the system includes volumes of custom code written to integrate the standard system with a real factory-floor monitoring system. Since 1995, I have focused on Windows- based software using C++ for algorithms and time-critical functions and Visual Basic for operator interfaces and front-ends. This architecture has proven resilient, since this more-than-ten-year-old code will still compile and run on modern computers by taking advantage of the Windows development tools.

VSD: In which areas do you see the most growth? What are users demanding from you in the design of new systems?

Lecky: In North America, we know that the bulk of the machine-vision industry is in application- specific machine-vision (ASMV) systems, or turnkey solutions that sell for about $125K, on average. This ASMV market is projected at $1.2 billion for 2008, while component sales (cameras, lenses, lighting, and so forth) are projected at less than $200 million. So solving the customer’s problem with a complete ASMV is still where the bulk of the market is. In new designs, users continue to demand systems that are more tolerant of variation in lighting, product, or operator. And we continue to design systems that attempt to minimize variation in lighting and operators, since I still have never seen a reliable machine-vision system that permitted variation in either. Lower cost is always an issue, but the cost has come down so far from the good old $20K vision-system days that it is less important in most applications. Size and power consumption are rarely an issue for our clients.

VSD: How will OEM components targeted toward machine-vision applications have to change to meet future needs?

Lecky: As the cost and price of machine-vision components continues to tumble, the vendors of these components cannot afford to spend as much time training, supporting, or assisting their customers. This means that the components must be more reliable, self-calibrating, and self-training, and effectively bullet-proof. You see such product components coming out of most of the machine-vision software and system companies already. Unfortunately, one of the best ways to make a component more reliable is to reduce its feature set, which then renders the component less attractive to the broader customer base. So there is a continual rebalancing of feature set vs. ease of use that I think the component and system vendors are really struggling with right now.

VSD: Do you work outside North America? How do you think that the machine-vision market differs in different regions such as China?

Lecky: I’ve done machine-vision work in France, Germany, Ireland, Singapore, and China. China, of course, stands out due to the size and fluidity of its market in the present era. I was astounded by its competency in steel making, railroad building, and railway freight-car building.

The application I completed involved high-accuracy gauging of railway axles after grinding and prior to custom boring a pair of wheels to press onto them. This application required many large machines from several vendors, a football field full of material-handling equipment, and dozens of PLCs communicating with four PCs performing orchestration, control, and database management (see photo).

The local engineers were very adept at designing, building, and programming, or at least customizing, all of the equipment. I must say that the first time I saw ladder logic in Chinese characters I was a bit more overwhelmed than I usually am, even by ladder logic. The technical rank-and-file in China can do engineering and programming at the “Western” level, if not better—something that still surprises some of my colleagues. The Chinese people were also very kind, hospitable, playful, and patient with me. In North America, we often thought of machine vision as a labor-saving technology. In China, while labor costs are on the rise, they are still (and perhaps forever) much lower than those in the USA. However, repetitive tasks such as gauging, inspection, and verification are still unappealing jobs that people are simply not very good at, and so, like many others, I see a bright future for low-cost machine-vision components in China.

VSD: What new markets and technologies do you see for your company in the future?
Lecky: I believe in being very flexible and helping my clients solve their problems in ways that are acceptable and practical. I’m not going to use an FPGA-based solution for a customer who wants solution update control but doesn’t know Verilog or VHDL--it just wouldn’t be prudent.

I think the key to my staying power in the industry over the years has been a willingness to understand the customer’s business issues and corporate structure and to use these components just as much as the technical ones in tailoring solutions to their problems. Many of the professionals in our industry will be nodding their heads as they read this, I bet. So, at least in that way, we will continue to follow our customers, not lead them.

Complex Thinking

A discussion with Katrin Pape, CTMV

Katrin Pape is cofounder and managing director of CTMV (Consulting Team Machine Vision; Pforzheim, Germany; www.ctmv.de). She has worked in numerous positions in the machine-vision industry.

VSD: Please describe your company and its services.
Pape: CTMV is a solution provider with experience in the field of image processing. Its founders draw on expertise in developing new application areas and complex application scenarios and their implementation in workable business solutions. Applications are focused on surface inspection of visually difficult materials such as glass, ceramics, various metals, plastic tubes, and foils.

In addition, we provide precise dimensional- accuracy verification, mainly for the stamping industry, and on presence/absence checks in applications such as the assembly of gear shafts, as well as position detection of moving and/or complex parts for robots and handling. CTMV offers business solutions for quality assurance in the fields of medicine, electronics, and automotive, as well as for process optimization of manufacturing in the fields of metal working, extrusion, and foil/paper production.

VSD: What technologies and components do you use for your applications? How often do you evaluate competing technologies?
Pape: Depending on the inspection task and its general framework, we use area- or linescan camera technology combined with appropriate standard interfaces based on camera buses or network technology, as well as PC or embedded compact vision systems. We continuously evaluate new products and work in close cooperation with standard component suppliers. The decision on whether new products will finally be implemented in standard applications is based on their specific benefit and on whether they help solve problems in a more reliable, robust, and possibly cost-efficient way.

Application-specific software with straightforward user interfaces and reliable intelligent algorithms for feature extraction and analysis will usually be implemented by CTMV. Developing field-specific analysis software and tools with a minimum set of parameters but a maximum of intelligence and performance is one of our core competencies.

VSD: How do you approach a new application? Do you work with OEMs or other system integrators?
Pape: Conceptual design of new applications is the key intellectual property that distinguishes us from our competitors. With our broad experience basis as a team, we continue to be able to design new approaches and concepts. This starts by determining the appropriate method of image acquisition, as well as highlighting test criteria with the adequate optical and illumination setup. The process includes developing reliable and robust methods for analysis of the image content, and continues to integration into the process chain with adequate signal and data exchange.

Key requirements are usually specified by customers or mechanical engineers. The diversity of customer and field-specific needs—in each case based on a combination of image processing and process engineering— opens up completely new applications. One example is a system for continuous tube inspection during extrusion, with detection and classification of process-related defects combined with special failure management and alerting. Another is quality control of metallic gear wheels during production, detecting scratches, cracks, and broken parts (see figure).

VSD: How do you design your systems for OEM product obsolescence?
Pape: Our safeguard here is working exclusively with industry standards. Components are exchangeable quickly and easily, so our customers get continuous, reliable functionality. We are independent of operating systems because we cooperate with reputable partners such as National Instruments (Austin, TX, USA; www.ni.com). These companies develop and provide system and field-independent standard components that meet industrial camera interface and automation standards.

VSD: What are users demanding from you in the design of new systems?
Pape: The general expectation is the application of modern, open standard technologies. Based on the latest developments on the components market and the way we integrate these trends into our system concepts, we meet these expectations in every respect.

The bigger challenge, however, is the balancing act that is needed to cover the span between the requirements for maximum identification performance—frequently using highly complex methods of analysis— and the simultaneous required ease of use. Examples of this are the stamping industry, as well as packaging and food, or presence/absence checks and version monitoring.

In these cases, the variety of parts to be inspected is high, and operators want to be able to create test plans for modified or new products themselves. This requires robust test cells on the one hand, and on the other hand adaptable software with respective part management and the right balance between parameterization possibilities and hidden advanced functionality.

To meet these requirements, we generally develop customer-specific user interfaces and implement easy-to-use setup and inspection plan editors with a minimum set of algorithms, tailor-made for the respective application or field of industry. We make a point of thinking in and implementing the language of the respective user or application environment and not that of image processing. Based on these key strategies, we provide users with the necessary flexibility without requiring them to have specific knowledge of image processing.

VSD: How will OEM components targeted toward machine-vision applications have to change to meet future needs?
Pape: Scalability and adaptability are required not only for software, but also for system bases. We often encounter the issue that initial specifications are later enhanced, further inspection tasks are added, or solutions have to be adapted to specific customer environments—all while keeping development efforts as low as possible. The ongoing standardization in the field of camera interfaces is an essential step and key factor in this respect. It enables us to meet these requirements today and should definitely be pursued further into the future.

Another key point is that, as a rule, vision systems need to communicate with a complex network of instrumentation, control, and drive systems. The direct combination of industrial interfaces for process communication such as Ethernet, digital I/O, and so forth, with image-processing components is beneficial for us. Application of various modules, including those from different suppliers, can be minimized or might not be necessary at all. This saves time and limits technical risks.

Examples are modules that combine the camera bus with FPGA-based, digital I/O. The camera bus ensures the image acquisition, while the complete timing, trigger handling, and partly complex encoder handling in real time are done by the I/O module. In this way, and with the systems capable of being operated within networks, we can now solve 95% of inspection tasks using area-scan cameras. We would wish for additional, similar technologies—for example, with linescan or network-based camera interfaces (GigE).

VSD: How do you think that the machine vision market differs in Germany from that in other parts of Europe or North America? What changes have you seen recently in the German market?
Pape: Our customers usually are machinery manufacturers who provide sales and servicing of complete machinery and equipment including optical inspection systems. Machinery incorporating CTMV vision systems has been installed all over North America and Europe. General trends are global. However, in Germany, there is intense competition between suppliers of components and system integrators. On the other hand, mechanical engineers increasingly ask for industrial image processing solutions, identifying these as substantial competitive edge. In general, we see a market differentiation toward plug-and-play solutions that are easy to configure and will not require system integrator services in the future. At the same time, some customers are interested in solutions for new, complex inspection tasks that have not been tackled so far. This is where we as CTMV can provide know how.

VSD: What new markets and technologies do you see for CTMV in the future? Pape: In the next few years, we see continuous opportunities for growth. CTMV will focus on further development of business solutions in medical, electronics, plastics, and automotive markets. And, we will develop new, innovative image-processing solutions within the scope of strategic partnerships with mechanical-engineering companies.

Developing new machine-vision software applications

Christian Demant, NeuroCheck and Industrial Vision Systems, on the demands of advanced development platforms


The fast development cycles in the IT industry result in permanent pressure on machine-vision software developers to update their knowledge. Integral parts of that continuous learning process are new networked system architectures and software-development tools.

Advanced new development platforms like .NET provide the option to easily combine software modules written in several different programming languages. This supports the development in teams having different professional backgrounds. Therefore, developers managing these teams must have knowledge in all these programming languages.

The availability of the latest multicore CPU technology demands multithreaded software to take advantage of this new processing power. Enabling software for parallel computation adds a totally new level of complexity to the development process. The normal programming approach, being used for dozens of years, is now, in many cases, obsolete. The synchronization of parallel executing threads leads to new error situations, which are extremely difficult to predict and to simulate in advance.

In the future I see growing importance of an in-depth understanding of software design patterns. The growing size and complexity of machine-vision software applications requires a much more systematic approach during the design and planning stage. Even 10 years ago a software developer started the implementation a couple of hours after discussing the specification with his sales department.

The software-development process has moved toward something comparable to a team of architects in charge of a complex facility. The design of the building and the drafting of the plans and specifications are the main intellectual tasks and take a big part of the development time. The implementation afterward is handcraft, but both jobs together require skilled teams. Lone fighters have no chance of survival.

Christian Demant is general manager, NeuroCheck, Stuttgart, Germany, and
Director, Industrial Vision Systems, Kingston Bagpuize, UK

Then and now: 20 years of machine-vision system integration

David Dechow, aptúra Machine Vision Solutions, on the changing role of the machine-vision system integrator

Within the context of a machine-vision application, integration quite simply is where someone has to actually make things work. With that definition, the role of the machine-vision integrator has changed little from “ancient times,” when we interfaced vidicon cameras with plodding computers to check the presence of an object based on 32 levels of gray. With scant few exceptions, today’s machine-vision devices do not yet arrive from the manufacturer shrink-wrapped, fully configured, ready to plug in, turn on, and perform an inspection. Machine-vision technology is a combination of diverse components that must be correctly selected based upon the needs of the application, competently installed, programmed, or configured to provide a robust result, then tested to ensure reliability that will withstand a production environment. Bottom line: a machine-vision application still must be “integrated”; someone has to “make it work.”

What is new is that machine vision has become a technology that today is significantly more accessible to the plant engineer than it was even several years ago. Yet the need and demand for the machine-vision system integrator is as strong as ever. What has changed ever so slightly is the perceived ROI or value of the integration partner. At one time the machine-vision system integrator was absolutely required even to consider an inspection project. The prevailing perception now is that the inspection task could be successfully done “in-house”; but it is more efficient and effective to use an outside integration resource for machine vision. A parallel situation occurred in the maturation of the PLC integration market, where today it is very common for a company to hire contractors to develop and maintain machine logic rather than have a team of company experts.

Looking ahead, the machine-vision integrator likely will continue to be an engineering resource for end users, machine builders, and other integrators, providing services on a contract or time-and-materials basis. Integrators will be called upon to execute more complicated inspection systems and will need to maintain relatively higher levels of machine-vision expertise. The barriers to entry into the vision integrator marketplace remain low, but the name of the game is efficiency and profitability, and the machine vision integration entity will increasingly need to find economies of scale that will sustain the business model.

Working with a machine-vision-system integrator

A discussion with John Nagle, Nagle Research

VSD: What sort of systems or services does Nagle Research provide?
Nagle: While many companies are involved with 2-D machine vision...

VSD: What sort of systems or services does Nagle Research provide?

Nagle: While many companies are involved with 2-D machine vision, we have decided to devote ourselves almost exclusively to 3-D machine-vision development. We think this has allowed us to build an expertise and body of experience with 3-D technology that is second to none in the industry. Nagle Research is a SICK (Minneapolis, MN, USA; www.sick.com) vision integrator. We are entirely brand loyal to SICK|IVP vision products, most often using the Ranger series of cameras. We started the company in June 2003.

My business partner, Andy Thyssen, is also a software engineer, and he is the chief technology officer of the company. Our first project and what is generally regarded as our “claim to fame” is the Aurora automated high-speed railroad track-inspection system. In our past lives, we spent more than a decade making video games for Nintendo, Playstation, and others. That experience has been immeasurably valuable in keeping the performance of our systems on the leading edge.

VSD: What sort of questions should be asked when considering the services of a machine-vision system integrator?

Nagle: Suffice it to say, it is impossible to engineer a solution without a thorough understanding of the problem. But to truly know the problem, you have to get past the superficial goals and get to the meat of the challenges that any solution will have to face. There can be many gremlins hiding just below the surface of what seems like an “easy” project.

For example, a candy factory needs a vision system that can count jellybeans moving down a conveyor belt. That’s the superficial goal. Obviously this is a very straightforward task for a vision system to accomplish. To be able to intelligently plan a solution, however, requires much more information. What should the system do with the count? Does it need to trigger a signal when a certain count is reached? Does it need to communicate with a PLC? What if a jellybean is malformed, does it count? And how does the system determine what is a “good” jellybean? How fast are the jellybeans moving? Do we need to count the individual colors? What are the space considerations for the vision system? This is very “goal-oriented” fact-finding research, and so this sort of questionand- answer probing can be done even by nontechnical people. Once all of the major and minor goals are known, then it is straightforward to isolate the specific disciplines and skill sets required to make the project a success.

VSD: So what can be done in-house by a company?

Nagle: Evaluating one’s own capabilities or the capabilities of company staff members is the next step in deciding how much, if any, of the project can be done in-house. If the project can be accomplished with off-the-shelf vision solutions or relatively simple smart cameras and only minor external connectivity is required, then the chances of being able to do this are good. If complicated record keeping, PLC connectivity, or advanced image-processing algorithms are required, it is almost certain that a third-party vision-system integrator with software-development capability will be necessary.

Different skills are required to integrate vision systems of varying degrees of complexity. Even a good list of necessary skills cannot be comprehensive and should be treated only as a guideline or rule of thumb.

VSD: What are the implications of working with a 2-D vs. 3-D system?

Nagle: Most people who have experience with vision are likely to have worked only with 2-D systems. Far less common are those who have worked with 3-D. Twodimensional systems deal with color and contrast; three-dimensional systems deal with materials and geometry. The share a lot of the same concepts, but, in general, 3- D is more difficult to implement. This is because now we are not just dealing with a light and a camera, we have to deal with laser light frequency; beam spread angle and thickness; laser power requirements based on material properties and stand-off distance; ranging algorithms; angular orientation of camera/subject/laser to obtain required accuracy; safety issues related to working with the laser; and coping with less than ideal material properties.

Integrating a SICK-IVC-3D or a Ruler product can mitigate some of these issues, in that the camera lens, laser type, and orientation are fixed at the factory (which also limits to some degree their applicability.) Ranging algorithms and material properties must still be dealt with in any case.

VSD: Is a vision software-development kit difficult to learn?

Nagle: In any nonsmart camera system, the integrator must have a thorough knowledge of the vision hardware SDK (software development kit), including the SDK for the frame grabber if applicable. Speaking in general terms, these are highly nontrivial software toolkits and a deep-rooted foundation in C++ and software development is essential. Even with the requisite C++ experience, the SDK itself—like any complex system—has a learning curve. If the project can absorb the extra time and cost associated with becoming proficient with the SDK, then it is very feasible.

VSD: What are the benefits of third-party integration?

Nagle: Any competent vision integrator should be able to integrate vision in simple to moderately complex projects. Many vision integrators do not have great depth in software and electrical engineering, and so for many the more complicated vision projects are beyond them. When choosing vision integrators do not have great depth in software and electrical engineering, and so for many the more complicated vision projects are beyond them. When choosing an integrator, it becomes very important to match the skills they bring to the table with the skills that will be required. Dealing with an integrator can save an enormous amount of time and development effort. In many cases, experienced integrators have saved companies from spending hundreds of thousands of dollars on inappropriate equipment and software.

For example, we were asked by a railroad-equipment manufacturer to provide consultation as to what camera would be required for a 2-D high-speed-railroad-inspection system. The company had already spent many thousands of dollars on image-processing software to locate defects in crossties using 2-D imaging techniques. The problem was that their approach had not accounted for surface stains, sealant, and debris confusing the analysis software. We ultimately concluded that a 3-D solution was more appropriate for this application and developed a Ranger-based solution that handles these material properties nicely.

VSD: When working with a system integrator, what are you paying for?

Nagle: Speaking only for Nagle Research, in most cases vision projects are quoted on a flat fee basis. Usually the process is phone conference to discuss the challenges and goals; if possible, samples are sent for testing and proof-of-concept; and if the project proves solvable, we submit a proposal.

With projects whose goals are a moving target--for example, additional defects to detect or additional accuracy requiring more cameras--there will most likely be proposed a flat fee for a defined scope of work and a standard hourly fee for work that is out of scope. The proposal will include time for travel, but the travel expenses are billed separately.

For our fee, the client receives our professional consultation, software and electrical engineering resources, and, in the end, a solution that meets their requirements. In most cases, unless specifically agreed to, the client does not get source code to the final solution. In some arrangements we will relinquish source code for the application, for example, their user interface and project-specific algorithms. Our proprietary Javelin Vision Engine, however, remains closed source. Javelin is the 3-D technology infrastructure to help us in developing more robust vision systems

VSD: What are the fundamental questions to ask before calling an integrator?

Nagle: The basic questions that need to be answered before an integrator is called are • Is the project outside the scope of in-house capabilities? • Is the company open to using third-party integrators? • What is the price of failure or delays arising from lack of internal experience? • Is there a budget for vision that includes third-party integration? • Is there likelihood that given a workable solution within budget, the project would proceed?

If the answer to all of these is “yes,” then most any integrator would be willing to take the challenge. A competent vision integrator is the key to successfully deploying a machine-vision system. Whether or not that expertise comes from within or from a third party is a decision the client ultimately will have to make. The most important thing to keep in mind is that in any event, a broad skill set and expertise in a variety of disparate disciplines will be required to complete the project on time and on budget.