Machine vision trends – what we can expect in 2019

Over the past year, unparalleled levels of developments have occurred in artificial intelligence (AI), big data, 3D imaging, and robotic process automation – none more so than on the factory floor. Industrial Vision Systems Ltd (IVS), a supplier of vision inspection solutions to industries such as medical devices, pharmaceuticals, food & drink, automotive, and printing & packaging, provides vision systems for quality control and robotic vision. This is a particular trend, amongst four others, which IVS believes will be prevalent in 2019.

3D Imaging and Bin Picking

Automation is driving factories to be smart and to reduce the workforce in operations where industrial automation can replace a person. Machine vision has been used for some time for the final quality control inspection, but new markets are opening up with the advent of 3D sensors and integrated solutions for bin picking. Random objects are picked by a robot gripper irrespective of the position and orientation of the part. 3D vision systems can recognise randomly placed parts in large scanning volumes, such as a tote and part boxes. The picking of complex objects in different orientations and stacks is possible thanks to dynamic robot handling. Combining Artificial Intelligence (AI) with bin picking operations allows autonomous part selection, increasing productivity and cycle time, reducing the need for human interaction in the process.

Deep Learning in the Cloud

The coming of 5G data networks for autonomous vehicles provides the ability to perform cloud-based machine vision computation. Massive Machine Type Communications (mMTC) allows large amounts of data to be processed in the cloud for machine vision applications. Deep learning algorithms using Convolutional Neural Network classifiers allows image classification, object detection and segmentation at speed. Development of these new AI and deep learning system will increase over the coming year.

Robotics

2018 was a record year for robot sales according to the International Federation of Robotics with industrial robot sales increasing by 31 per cent. Trends such as human collaborative robots, simplification of use and process learning have helped propel the use of robots in industrial automation. In the future industrial robots will be easier and quicker to program using intuitive interfaces. The human-robot collaboration will support the flexible production of small quantity production with high complexity. The reduction in complexity of use allows the widespread use of robots and vision systems in the mid to long term.

Hyperspectral Imaging

Next generation modular hyperspectral imaging systems provide chemical material properties analysis in industrial environments. Chemical Colour Imaging visualises the molecular structure of materials by different colouring in the resulting images. This allows the chemical composition to be analysed in standard machine vision software. Typical applications include plastic detection in meat production, detection of different recyclable materials and blister pill inspection quality control. The main barrier for such systems is the amount of data and speed required for processing, but the development of faster processes, better algorithms and on camera calibration still make this a hot topic for 2019.
Thermal Imaging Industrial Inspection

Thermal imaging cameras have traditionally been used for defence, security and public safety with far-ranging uses of thermal images for detection. For many industrial applications, such as the production of parts and components for the automotive or electronics industry, thermal data is critical. While machine vision can see a production problem, it cannot detect thermal irregularities. Thermal imagery combined with machine vision is a growing area, allowing manufacturers to spot problems which can’t be seen by eye or standard camera systems. Thermal imaging provides non-contact precision temperature measurement and non-destructive testing – an area of machine vision and automation control set to grow.

Earl Yardley, Industrial Vision Systems Director, comments: “Industry 4.0-related technologies are driving much of the changes that are currently taking place in manufacturing. This applies in all sectors, but it is particularly important in high-specification and highly regulated industries like food & drink, pharmaceutical and medical device manufacturing. There are many reasons for companies moving towards Factory Automation technologies including making production lines more efficient, making more effective use of resources, and improving productivity. I fully expect to see growing demand in this area across many sectors in 2019.”


Recent news articles