Applied Optics

• Automatic sorting of waste for recycling. Sorting garbage for recycling saves resources, reduces environmental pollution and slows the build-up of landfills. Infrared light is the key to a sorting machine for drink cartons and plastic bottles developed by SINTEF.
• Ice fraction level of superchilled salmon. Superchilling is a process by which the temperature of a food product is lowered to 1-2 ˚C below the initial freezing point of the product. The ice formed on the surface will absorb heat from the interior and will eventually reach equilibrium. A fraction of the water is transformed to ice and is used to protect it from heat impact instead of using surrounding ice. It has been shown that superchilling can increase the shelf life of fish and meat products without the same reduction in quality as seen during normal freezing.
• SMARTIEHS: Smart inspection system for high speed and multifunctional testing of MEMS and MOEMS. SMARTIEHS develops a smart, high-speed, cost effective and flexible inspectionsystem for production of Micro-Opto-Electro-Mechanical Systems (MOEMS).SMARTIEHS will decrease the inspectiontime of a wafer by a factor of 100. It cuts production costs and shorten the time tomarket.
• Road works during night - Recommendations for the visual environment. NordFoU (a cooperation between the road authorities in the Nordic countries) initiated this joint Nordic project to investigate how a good visual environment could be provided for the road works at night time, and as a part of this how to best avoid or reduce the adverse effects of glare for the motorists.
• Fat content measurements in inhomogeneous meat. Nofima and SINTEF, in cooperation with QVision, have investigated the possibility of measuring the fat content of inhomogeneous pork trimmings in large plastic boxes for a Spanish meat company, Frigorificos Andaluces De Conservas De Carnes SA (FACCSA). These boxes are valued based on fat content; the lower the fat content, the higher the purchase value. Customers have different demands in terms of fat content and therefore knowledge of the leanness of each box is advantageous to both supplier and customer.
• Non-contact temperature measurement. Contact-less temperature measurements can be performed by measuring radiated heat. Performing such measurements on aluminium are interesting, but are also particularly difficult.
• Contact free measurement of water content of split cod. Water content estimation is critical in split-cod production. We have developed a contact free transflection probe which has shown even better results than the traditional contact probe.  
• Diffractive Optical Element for spectroscopy. Low-cost near infrared spectrometers have a potentially wide market in material characterization, material sorting, gas monitoring and food quality control. Diffractive optical elements may have a large potential in such applications.
• Probe head for food quality measurement. Within the food and feed industry there is an increasing awareness that optimal production process control is necessary to maintain competitive ability. However, a premise for control is process feedback - in this case measured food quality parameters.
• Water and fat content measurements on French fries. Matforsk and SINTEF have made a feasibility study for McCain to investigate whether water and fat of French fries can be measured during production. Under such conditions measurements must be done contact free and on quickly moving, rather small samples. This favors optical methods.
• Infrared gas sensors with multi-line filters. Selective and sensitive sensors can be made by tailoring infrared filters to fit the absorption pattern of particular gases. SINTEF is developing tunable multi-line filters using micro-optical and MEMS technology. The resulting sensors can be produced at low cost in high numbers.
• Objective measurements of colour in salmon. The over all visual impression and the colour are important parameters for the consumer when buying fish. Different markets have different requirements to the salmon’s redness. SINTEF ICT and Matforsk have together with QVision developed a scanner that classifies the colour of fish fillets based on the same criteria a human observer uses.
• Micro-optical microphones.  Optical microphones have many advantages over conventional condenser or capacitive microphones. They offer immunity toward electromagnetic interference and need only a small membrane, which gives a more compact and robust sensor. Theoretically an optical design will have the same or better dynamical range and sensitivity as capacitive microphones. At SINTEF we have realised two micro-optical microphones with similar performance as the best commercial capacitive microphones available.  The design avoids alignment problems and the sensors can be produced in large numbers by photolithography at a low cost.
• Micro opto-electro-mechanical systems (MOEMS). Micro-opto-electromechanical systems (MOEMS), or optical MEMS as they are also called, are systems involving micromachining of structures in the micro- to millimeter range whose purposes are to manipulate light. Today’s MOEMS devices include waveguides, moving mirrors and diffractive gratings, and are typically made using standard lithography methods giving the advantages of a compact design and fabrication at a low cost.

Image Analysis

• ADABTS (Automatic Detection of Abnormal Behaviour and Threats in Crowded Spaces). ADABTS is a four year EU FP7 project addressing the protection of EU citizens, property and infrastructure against threats of terrorism, crime, and riots, by developing techniques for the automatic detection of abnormal threatening human behaviour, while respecting privacy and civil liberties. The automatic systems will support video surveillance operators during their task performance. More specifically, the support system will help the operator to detect abnormal behaviour and threats in crowded spaces, particularly abnormal or undesirable behaviour of individuals and groups of people in crowded spaces, in the context of large scale events, and critical infrastructure.
• SEAMLESS - Simultaneous navigation and manipulation in complex dynamic scenes. Mobile robot manipulators (mobile robots with one or more attached manipulator arms) will be prevalent in addressing many future industrial and social needs such as contributing to the caring for an aging population, performing autonomous inspection, maintenance and repair operations in onshore and offshore industrial facilities, operating the factories of the future, as well as monitoring environmental pollution and removing contamination. However, in order for such robots to seamlessly navigate and operate in more complex dynamic environments, important challenges regarding real-time 3D mapping and synchronized robot arm and base navigation must be addressed.
• New 3D camera to give robots better view. The TACO EU Project will develop a new type of laser based time-of-flight 3D camera, that will give robots a more “human view of the world”. The project will provide current and future robots with a significantly better overview and understanding of their surroundings. This will open up opportunities for the application of robots to a much greater extent – robots may interact with humans on a daily basis and perform a wide range of different tasks such as cleaning, construction, maintenance, security or personal support.
• 3D Position and Pose Estimation for Random Bin Picking. As manual labor is getting increasingly expensive, the use of robots for automatic handling of parts is becoming more and more important. One challenge that remains to be solved is to automatically pick and place objects that are placed completely unorganized in a container. As a part of the Auto3D project, SINTEF and Tordivel AS have developed versatile and robust algorithms for 3D object localization and pose estimation based on a 3D image of the scene and a CAD model of the object to search for.
• Pinbone removal in pre-rigor salmon. Current systems for automatic processing of salmon are not able to remove all bones from freshly slaughtered salmon. The pin bones are positioned in the thickest part of the fillets. The bones are attached to the flesh by tendons, and the fillet is damaged or the bones broken if the bones are pulled out without “maturing” the fish for several days. The pin bones are removed by pulling in order to keep the fillet “whole”. SINTEF has participated in developing a camera based system for determining the bones positions in the tissue, so that the soft root can be cut with a knife and the bones removed shortly after slaughtering. This allows for production of fresh, filleted salmon, opening up new markets for the salmon industry.
• 3D vision and object recognition for off-shore robot guidance. Norwegian oil company Statoil has developed a new concept for an unmanned oil & gas platform. In order to support research on robotic and instrumentation systems for this platform concept, Statoil has financed a robotic lab facility in Trondheim. One example of a maintenance task that has been demonstrated in the lab is to change the battery of a sensor with a robot. The position and orientation of the battery is found by equipping the robot with a 3D camera and sophisticated 3D object detection algorithms.
• Robot navigation in pipelines using 3D cameras. Robots used for inspection of pipeline systems, such as sewer systems and gas pipelines, are in need of a navigation system. Current pipe inspection robots use stereo cameras or ultrasound for navigation, giving sparse datasets with a high degree of uncertainty. SINTEF is developing a robot navigation system that uses a 3D time-of-flight camera for junction-, bend- and obstacle detection, providing continuous and accurate position estimates.
• Real time fusion of sensor data for dynamic 3D mapping. The Norwegian oil and gas company Statoil has developed a new concept for a remotely operated oil & gas platform located offshore. Robots operating the platform requires multiple sensors to provide the information required for operation planning and execution, and fusing sensor data from different sensors is essential to ensure robust and reliable recognition of environmental shapes, features and properties. To utilize this information, carefully tuned signal processing algorithms are required for combining sensor data. A robust sensor system also requires understanding of the sensors characteristics within when operating in challenging environments, and compensation for any undesired effects.
• Identifying individual fish in videos. Underwater video cameras are commonly used in the fish farming industry for inspecting the health and wellbeing of the fish, monitoring the feeding process, etc. However, for many applications it is desirable to do automatic analysis of the images, for instance for collecting statistical information of the fish size, fish distribution in the cage or fish behavior.
• Automatic 3D inspection for piece-manufacturing industry. Development of a platform (sensors, software and technology concepts) for 3D machine vision, focusing on applications for the piece-manufacturing industry. The technology can be used to e.g. pick 3D objects from an unorganised scene, to perform 100% product inspection in 3D and for adaptive process control.
• Measuring 3D shape of steel shafts during forging. IMEGO (Gøteborg), Mefos (Luleå) and SINTEF in 2005 collaborated in a feasibility study for 3 Swedish steel companies on how the 3D shape of steel shafts can be measured by means of computer vision. The cross section shape and the longitudinal curvature were to be measured during the forging process in order to be able to better control the forging.
• Happier cows through image analysis. Clover leaves are a major source of protein for grazing animals in ecological farming. Maintaining a high proportion of clover in the meadow is therefore vital to keeping the animals healthy and happy. Grass-clover systems are however unstable and difficult to manage. The Norwegian Crop Research Institute is therefore investigating how the proportion of clover in meadows can be kept stable over time. SINTEF has developed an image analysis program that helps evaluate the results of the different growing schemes.
• 3D in-line inspection of car parts. In co-operation with Raufoss Chassis Components AS, SINTEF has developed a tailored, advanced industrial inspection system for the accurate measurement of the shape of wheel suspension arms. The method combines two structured light projection techniques, which results in a robust fast and very accurate in line inspection system, that fulfils the stringent requirements that are set by the automotive industry.
• Visual inspection of split cod/bacalao. SINTEF are together with Norwegian Seafood Federation’s Bacalao Forum and Matforsk developing a system for objective visual inspection of split cod. The features to be detected are the over-all color, liver stains, blood stains, deformation and ruptures/splitting in the cod meat. 
• Automatic weed mapping in cereal fields.In order to reduce weed seedlings and thereby optimise crop production in cereal fields, spraying of herbicides is necessary. By using a camera and image processing the weed-infected areas can be detected and only the infected areas are sprayed.
• Recognising bottles from their shape. The shape of the bottle has always been a main attribute for the recognition of bottles in the Tomra machines. In the Tomra T600 machine introduced in 1997 earlier shape sensing techniques were replaced with a CCD camera and a patented optical system for high contrast contour imaging of the bottle.
• 3D inspection of dental wear. SINTEF has built a measurement device for determining the 3D shape of dental impressions, comparing impressions of the same tooth taken at different times, and determining the wear. The SINTEF solution was chosen ahead of commercial laser scanning instruments because it could readily be adapted to give the micrometer precision that characterises dental wear.
• Cybstickers: Using mobile phones as matrix bar code readers for creating and accessing "digital grafitti". A new kind of personal stickers, CybStickers ®, for connecting an MMS message with a sticker via your mobile phone was created as part of a doctoral work at SINTEF. One of the great challenges of this project was to detect and recognize 2-dimensional matrix bar codes in various settings and with highly varying image quality.
• Matrix bar code reading using mobile phone cameras. SINTEF has developed a system for reading significant amounts of data into the mobile phone automatically. The camera available on newer mobile phones is utilized for this purpose.
• 3D imaging for estimating crate and bottle heights. Tomra Systems ASA has with assistance from SINTEF developed a stereo imaging system for measuring the dimensions of bottles and crates in their reverse vending machines. The height of the crates and the bottles are two important parameters for correct classification and thereby returning the correct refund. By using stereovision a 3-dimensional measurement of the scene is obtained. From this measurement the height of the bottles and the crate is estimated, and in addition the number of bottles within the crate is counted.
• Dimension measurement. We have developed several systems and methods for non-contact high accuracy dimensional measurements in both two and three dimensions.
• High capacity fish counting and weight estimation. When water and fish are "vacuumed" up together out of sea-cages for harvesting, the weights and numbers of the fish are difficult to estimate. But now, a "fish counter" has been developed.
• Reading Braille on aluminum can lids. Reverse vending machines are automated machines that utilize advanced technology to identify, sort, collect and process used beverage containers. Some markets with reverse vending systems have problems with imported used beverage cans from other countries. Tomra Systems ASA has developed a system for reading embossed dot patterns on the can lids for increased reliability of refund calculation. The text or symbols are embossed in the can’s lid when produced. 
• Video security surveillance systems. Video surveillance systems are crucial in protecting areas of vital importance like banks and airports. SINTEF has collaborated since 1992 with Detec (former VideoWeb1) in developing their automatic video surveillance system.
• Model based reading of barcodes from low resolution CCD-images. CCD-cameras have today become a common sensing element in automation, so also in the bottle recycling machines from Tomra Systems ASA. As part of such a development Tomra wanted to investigate the possibilities and limitations in using low cost CCD-cameras for reading the bar code on bottles and beverage cans.
• Intelligent Imaging Sensors.X-ray sensors are used for diagnosing a number of medical conditions. X-ray exposure may however increase the risk of cancer. By using innovative sensor technology combined with realtime image analysis the patient dose may be reduced.
• Inspection of cellular phone display windows. SINTEF has developed an inspection system for the quality control of printed text and mould defects in cellular phone display windows. This enables cost-effective production and reliable quality.

 Data Analysis

• Process deviation detection on robotic oil & gas platform using multiple sensors. The Norwegian oil and gas company Statoil has developed a new concept for a remotely operated oil & gas platform located offshore. One of the great challenges in this project is the analysis of the all sensor data collected by the robot (camera images, sound, vibrations, temperature, gas, etc) in order to automatically identify the normal trends in the process and to detect deviations during automatic inspection rounds.
• ECG analysis for heart diagnostics. Simula Research Laboratory has developed numerical models that can be used to predict the effect on the surface ECG-signals from different ischemia patterns in the hearth.
• Searching for similar shapes. Hydro Aluminium is a major extruder of aluminium profiles world wide. They produce tens of thousands of different shapes, introducing many new shapes every day. All the different shapes are available in 2D cross section CAD drawings, meaning that they have a vast number of historical and current drawings available in their databases. If they could be able to search these databases for earlier products that are similar to for instance a new product or a new customer request, this could have many uses. 
• Multi-Component Trace Gas Monitoring. Ensuring crew safety is a prime concern in spacecrafts and other closed manned habitats. SINTEF has developed equipment for early detection of toxic, harmful or unpleasant gases.
• ASMOD – Adaptive B-spline modeling of observation data. ASMOD is an algorithm for empirical modeling. Empirical modeling deals with the problem of building mathematical models of systems based on observed data. Such models are commonly used in engineering, and application areas include control, optimization, prediction, filtering, and fault detection to mention a few.
• Modelling for de-mining. Mines pose a significant risk for civilians, also after a conflict has ended. Mine removal is difficult, risky and time-consuming. Innovative modeling may speed up the removal process.
• Data fusion determines air-craft’s breaking distance on slippery runways. Data from weather sensors together with the air-craft’s flight information might give the pilot important information about the breaking distance needed to bring the plane to a complete stop when landing.
• Software for analysing and quantifying geoscientific information. The dGB-GDI system is primarily intended for quantifying seismic interpretations in terms of geological and petrophysical probabilities.