Aircraft damage detection goes hi-tech

Experts in the field of image processing –such as Siemens, Frost & Sullivan, the German Engineering Federation and people from the German Fraunhofer Allianz – all agree that there are very promising trends toward three-dimensional imaging, texture analysis, high-speed cameras, colour recognition and thermography. Looking at the not-so-distant horizon, we will see the greatest amount of innovation in data processing, recognition software and optical resolution performance.

Image processing applications already range from industrial uses and security systems to transportation and medical technology. Industry experts, however, agree that only about 20% of all possible applications have been addressed so far. Siemens’ ‘Pictures of the Future Fall 2006’ stresses that, according to estimates provided by a number of manufacturers, the worldwide market volume for machine-vision systems currently amounts to about €6,5-billion, with annual growth rates extending into the double-digit range.

In the industrial area, image-processing systems are employed for quality control in virtually every sector. They are used to inspect every- thing from computer displays and the surfaces of gearbox components to printed circuit boards for cellphones. Image processing is also useful in metrology, where it is used in visually guided machines and to recognise components, symbolic characters and codes. Cameras can help robots recognise objects, such as the shape and position of workpieces.

In Germany, industrial image processing has been growing faster than other sectors of automation technology for several years and the growth rate was about 9% in 2006.

According to a study by Frost & Sullivan, the market will see increasing growth in sales of gigabit Ethernet cameras that can transmit high-resolution images from a camera to a computer across a distance of several hundred metres. In 2007, three-dimensional vision systems for robots are available together with systems for the inspection of semiconductor components with an accuracy of 4,5 �m.

Starting in 2010, smart cameras with neural networks are expected to have the capability of categorising objects into many different classes – an important feature when it comes to automatic sorting.

Image processing is vitally important in hospitals too. According to Frost & Sullivan market researchers, the key development in that sector is the growing importance of picture archiving and communication systems (PACSes). PACSes make it possible to process, store and manage medical images, and have become accepted as the standard in radiology. By 2010, analysts predict sales in Europe will reach $1,47-billion – compared with $0,47-billion in 2003. An important growth engine here is a reduction in costs, which are declining by about 10% annually. Another trend is the combination of two imaging modalities in a single system, such as high- resolution computed tomography images paired with nuclear medi-cine methods that visualise biochemical processes.

IMAGE PROCESSING FOR AUToMAKERS

In the auto industry too, image processing for driver-assistance systems is gaining in importance, and automakers use not only laser, radar and ultrasonic sensors, but also cameras that can perceive vehicles, lane boundaries, traffic signs and pedestrians faster than the human eye. It is predicted that cameras will expereince the strongest sales growth among all onboard auto- motive sensing systems, for instance, in video-supported systems that sense lane markers and issue a warning when a car strays from its lane, and in parking-assistance systems.

At 44%, North America represents the largest share of this market. In Europe, the UK is driving this trend. As a case in point, the authors of the European Union study ‘UrbanEye’ (www.urbaneye.net) estimate that there are more than four-million private and public survaillance cameras in Europe. About 6 000 cameras of the estimated half-a-million cameras installed throughout London are located in the city’s underground system. In some streets, cameras are mounted only 15 m apart. Privacy advocates have calculated that people in London are recorded by a surveillance camera up to 300 times a day. But most Londoners consider the undeniable successes in fighting crime more important than the potential negative aspects of such monitoring.

In the UrbanEye survey, 90% of London’s inhabitants were in favour of cameras in public places (compared with 25% in Vienna, Austria). In New York, too, cameras are multiplying rapidly. In Manhattan, for instance, there are already 9 000 cameras in public places – about four for each city block.

In the past, such systems used cameras that merely transmitted their images to tape machines and monitors (closed-circuit television).

But now there are more and more digital cameras that transmit data to computers. Presently, four to eight such cameras share one central processing unit (CPU). But in just two to three years, many cameras will have their own CPUs. Conventional videotape will be superfluous. Using intelligent software, the latest smart cameras can even use data comparison to detect unusual behaviour and trigger an alarm.

FUTURE DEVELOPMENTS

By 2008, video cameras will be increasingly combined with access-control solutions. That, in turn, will increase demand for biometric systems, especially those based on face recognition.

Market researchers also see a particularly strong future trend towards totally digital solutions based on the Internet Protocol. Every survaillance camera will then essentially be a webcam.