This blog will be continued in german language here: blog.md-automation.de.
Vision(s) of the Future
May 31, 2010Top-Line growth despite the recession could be registered during this past year in the so-called non-manufacturing applications of image processing and machine vision. A presentation of the first results – still preliminary – of the annual market study conducted by the EMVA, given by Director of Market Research Andreas Breyer at the business conference of the association in Istanbul this past April, has shown a respectable increase from about 12% to about 19% of total sales of European machine vision by these sectors in 2009. This number, a fifth of the industry´s sales result after all, is even more remarkable considering that the market data is gained predominantly in the area of “industrial” machine vision. Companies being active mainly in areas such as life science, security, surveillance, document management as well as ITS, logistics and military, are not even covered by the EMVA survey. This is based in the historical roots of the association. Both, the European association EMVA as well as the German VDMA sub-group “Industrielle Bildverarbeitung” (Industrial Vision/Machine Vision) have their roots in the “traditional” markets of factory floor quality control automation that started about 20 years ago. These “seeing machines” are today an integral part of modern production technology. Even more: the major part of automated processes for the manufacturing of all kind of products – from toothbrushes up to complete automobiles – would not even be feasible without the vision technologies. The golden days of annual strong double-digit growth, however, have come to an end. The American industry association AIA has forecasted a very moderate growth of 3% for 2010; their European counterparts still expect an increase in turnover at about 11% for this year. Beyond the traditional feeding grounds of machine vision, however, the world moves at a whole different pace. Allow me to hazard the prediction, that we will see imaging technologies in every aspect of our daily life ten years from now. Small airborne robots will be used to automatically visually detect structural damages on buildings from above, guided by robot vision in the first place. Vehicle flow on the main traffic arteries will be steered by individual on-board cameras based on data from the higher-level traffic surveillance camera infrastructure. Our vacation planning will be done at 3D monitors within the augmented reality environment of the trip´s destination having been fully digitized by 3D scanners. Miniaturized cameras regularly circle around inside our body and send out warning messages as soon as they detect something out of the order. Utopia? Maybe so. Maybe it will take ten years instead of twenty, but maybe this vision of the future is not yet even close to what will really evolve. Already today a vacuum cleaner can be obtained at Amazon for a mere 300 Euros that is guided through my place by vision. My cell phone is able to identify my vis-à-vis by face recognition, find him in my address data base and spare me the embarrassment of having to reply to a joyful salutation at the trade show booth with a sheepish “Sorry, what was your name again?”.
Gabriele Jansen
From Healing and Destroying
May 6, 2010It heals eyes and at the same time, it has the energy to cut through metal. It is able to write, to measure, to shape matter, and to transfer information: We are talking about the laser, a tool of contraries. As 50 years ago the U.S.-citizen Theodore Maiman finished the first working laser he probably had his own ideas of its use in the future. Otherwise he would not have spent his free time and threatened his former employer with his dismissal if he had not been allowed to continue his laser project. Not only Maiman, also the public in general was positive about the laser’s usage. The Time Magazine described the laser as “the hottest topic in the field of state physics since the transistor”. But Maiman’s rubin laser did not fulfill the expectations: the laser materials were too impure, the power too little. The researchers were discouraged; the laser was mocked as an invention in search of an application. There were successful experiments, like the one where a laser pierced a steel girder, but the conventional solutions stayed outclassed. One billion US dollar, the laser should achieve ten years later, forecasted the business press with enthusiasm in the year 1962. Turnover figures on which the economy had to wait for a long time. But today the everyday life is not to imagine without the laser technology: The laser beam reads the CD and DVD’s data, supermarket cash points work on the basis of its invention. The laser light is even used for entertainment in so called laser shows.
All the applications known today are possible due to the fact that laser beams are available in all desired wave lengths. For this, just the corresponding laser materials have to be chosen. Furthermore, laser beams can be generated as ultra short pulses. Especially in recent times, the pulses are getting shorter, the laser radiation covers the whole electromagnetic spectrum – from short wavelength X-radiation to long wavelength infrared. And meanwhile, they reach a peak power of some petawatt. But that’s not the end of the laser project which started 50 years ago. At the moment, researchers of the National Ignition Facility (NIF) in Californian Livermore try to realize nuclear fusion reactions with laser radiation.
At this year’s Control show, from May, 4 until May, 7, there were numerous laser applications, mainly in the special show “Contactless Measurement”. Combined with image processing, the laser is able to control the product’s quality contact-free, e.g. with laser scanning sensors.
Let yourself be inspired and sink your teeth into your idea’s realization, like Maiman. I am curious to see on which development we may report in 50 years from now.
Stephanie Nickl
Editor INSPECT
EMVA Conference 2010 in Istanbul
March 3, 2010The 8th EMVA European Machine Vision Conference is getting closer: the conference will take place on April 16 and 17, 2010, in Istanbul, Turkey. Business leaders of the machine vision industry from 20 countries are expected to participate.
We are pleased to present at the conference Mark McGregor, a top-notch speaker offering a session on leadership. In high demand around the globe, Mark has a proven track record of inspiring business executives with his views on motivation, high performance teams, the psychology of winning and many other topics. Since 1999, he has been ranked as one of the top speakers at the St. Gallen Business School and the St. Gallen Management Program. I myself attended one of Marks seminars on leadership and look very much forward to hear him again in Istanbul.
Mark’s approach is unique: His former career as a professional ice hockey player and coach in Canada, Germany and Switzerland enables him to transfer insights from high-performance teams in sports to those in the world of business.
The leadership session is not the only highlight of the conference, however. Once again, the EMVA Conference 2010 focuses on the topics that matter. Here is a quick overview:
Machine Vision in Turkey: Turkey is dynamically developing as a manufacturing base. Top speakers will give overviews of the Turkish economy, the Turkish machine vision industry and machine vision use in Turkey’s rapidly growing manufacturing sector.
Machine Vision Markets: Get the latest updates on machine vision market developments in Europe, North America and Japan.
Research Funding Opportunities in Europe: Find out what is in it for the machine vision industry at our panel discussion.
Technology Trends: Augmented Reality. Service Robotics. Two presentations provide a technology update and identify potentials for the machine vision industry.
I hope this short summary watered your mouths and I will see all of you in Istanbul in April. Of course the networking will be great as always, and the pre-conference reception, the Friday evening event and the sightseeing tour on Saturday afternoon will make for a brilliant framework. More information can be found at www.emva.org.
Gabriele Jansen
Anorexia?
October 6, 200988 pages. That was the size of the September issue of the INSPECT last year. About one third more pages than offered by the September issue of 2009. You surely already noticed that trade journals are significantly thinner this year and that they show a frightening tendency towards anorexia the further the year progresses. Why is that so anyway?
A trade journal is a product, as much as a consumer magazine is, or a book. This product needs to generate an income. That is exactly the same as it is with the products produced by your own company. For a trade journal the main source of income is advertisement, placed by companies who have an interest to communicate with you, the reader of the journal. The amount of advertisement continuously decreases since the beginning of this year and subsequently the income of trade journals abates. Now, one could argue splendidly if it is wise and well to save on market communication especially in economical difficult times, or if it were not even more important now to show a high visibility. On the other hand, one may not be mistaken that for many a company it is no longer a choice where to save.
As a consequence, cost saving has to be done by the publisher of trade journals as well. The first publishing houses announce significant economical imbalance and fight for survival. Others meet the market situation with magazines that rather remind you of a student´s notebook in size and haptics.
Not only in light of this comparison, the 54 pages of the September INSPECT are really good.
Is there no need to save costs for INSPECT as well, you might ask yourself now.
Yes of course there is, but we are lucky to have a very sound basis in more than one aspect: The companies that place their ads in the INSPECT know that in doing so they reach their customers of today and of tomorrow in an optimal way and our readers confirm for them that this choice is the right choice.
Take a close look at the advertisements on the 54 pages of INSPECT 8-9: for those companies it is a priority to be noticed by our readers and to communicate with them. This also shows economical strength, strategic sustainability and faith in their own future. Suddenly these ads have a whole new meaning in addition to featuring a product.
For us they provide the possibility to present with each issue a versatile, comprehensive and independent information package. In German and in English language. In each issue. This is complemented with our online presentation at http://www.inspect-online.com, taking up the topics from the printed issues and enriching them with up-to-date news on a daily basis, again in German and English language. During the summer our portal was given a facelift, that is – as with cars – a technical and optical makeover. Especially the interactive and the multimedia aspects, naturally rather out of reach for a print product, are offered by the website: search engines, webcasts, Buyers Guide database, job search, online polls, to mention but a few. But not only that: also the printed edition features some new components with which we hope to generate value and deliver delight.
Gabriele Jansen
Publishing Director INSPECT
Plea for Software-Benchmarks
July 6, 2009It was in late 2007 when I was met with harsh criticism in the industry. In the course of a panel discussion about vision software I had made the proposal to work on making the performance of vision software comparable for the end user. Along the lines of standard EMVA 1288 for cameras a binding definition of performance criteria and an accurate description of benchmark scenarios could be employed to compare the different software solutions for the different vision tasks. The resulting data could help users in their decision for suitable tools and products for their application.
This proposal was not very well received by some of the software suppliers back then. There was talk of the difficulty to come up with a distinct specification and of the necessity to distinguish oneself from competition especially by the differences in the software and the resulting impossibility to provide a direct comparability.
However, a couple of weeks ago Dr. Wolfgang Eckstein from MVTec delivered a public and concrete proposal on how such a benchmark could be designed and executed. He, as well, suggests to define performance criteria for typical vision applications like barcode identification or pattern matching, to establish a uniform fixed framework for the benchmark, and then to execute the comparison on selected, standardized and well-described image data.
There is a very similar approach already established in other industries, BTW. The British Home Office Security Development Branch (HOSDB), e.g., provides libraries (i-LIDS) with video footage to companies from the video analytics area for a benchmark of their software in applications like people tracking covering several cameras, perimeter surveillance or detection of abandoned luggage. This gives the suppliers the opportunity to test the capabilities of their products in a well-defined scenario and based on relevant input data while the potential customer has the chance to compare the performance of the different software packages.
The challenge, here and there, is of course in the sensible choice of application relevant image data and this gets even more demanding the more complex the vision tasks becomes. May it be even relatively straightforward to decide upon images and testing scenarios for the determination of a barcode identification performance, it ventures into the indefinite complex to do this for a surface inspection.
But there is yet another aspect, not taken care of with a pure performance benchmark of algorithms, for the value rating by the user however at the same level of importance: the usability of the software. How laborious is the parameter set-up of the tool, how transparent is the result extraction, and how coherent are system and result messages and reports? The answer to these questions can determine the success or failure of the application, independent from the performance of the algorithms employed. While following the goal to accomplish transparency and to provide impartial decision criteria to the user, this latter aspect of vision software performance needs to be included in any benchmark.
All aspects considered a benchmark of vision software is by no means a small feat, but definitely one that is worth the effort. One can only hope that Dr. Eckstein´s advance will be taken on by other players in the industry. The real benefit will be achieved only when the definition of the performance criteria and the description of the benchmark scenarios as well as the design of the image data basis are derived from the input, the know-how and the experience of many experts and the procedure and the results will then be supported by many of the suppliers.
Gabriele Jansen
Posted by inspectonline