SICK launches 2D vision camera with onboard deep learning

SICK has launched its first vision camera with a pre-installed deep learning app on board to make it simple to create custom quality inspections of complex or irregular-shaped goods, packaging and assemblies, especially where they may have previously defied automation using traditional systems.

The SICK Intelligent Inspection Deep Learning App runs on SICK’s newly launched Inspector P621 2D programmable vision camera. The all-in-one package is said to enable machine builders and end users to set up vision classifications using artificial intelligence in a fraction of the time and cost it would take to program challenging inspections based on recognising the preset rules and patterns of traditional vision systems.

SICK says that automation is therefore now practical and affordable for complex imaging tasks such as sorting fresh fruit and vegetables, checking the orientation of timber profiles by recognising the annual ring structure, checking leather car seats for creases or flaws, or inspecting the integrity of solder in surface-mount assemblies.

“By embedding the Intelligent Inspection App onto SICK’s Inspector P621 deep learning camera, SICK has made it possible for users to purchase a ready-made package that uses artificial intelligence to run complex vision inspections with ease,” said Neil Sandhu, SICK’s UK Product Manager for Imaging, Measurement and Ranging. “Users are guided through an intuitive process that teaches the system how to recognise ‘good and bad’ examples using SICK’s specially optimised neural networks in the cloud.”

Using the SICK Inspector 621’s in-built image capture tool, users begin by collecting example images of their product in realistic production conditions. Guided step by step through the graphic interface, the system prompts them to sort the images into classes. Then, using SICK’s dStudio service, the pre-sorted images are uploaded to the cloud, where the image training process is completed by the neural network. The user can then apply further production images to evaluate and adjust the system. Once the user is satisfied, the custom-trained deep learning solution is downloaded to the SICK Inspector P621 camera, where it can begin to take decisions automatically with no further cloud connection necessary. Results are output to the control system as sensor values and digital I/O.

The image inference is carried out directly on the device, so there is no need for an additional PC. As the system training is done in the cloud, there is also no need for separate training hardware or software, saving on implementation time and cost.

“Because it runs directly on the camera, the SICK Intelligent Inspection app does not require any additional hardware,” Sandhu continued. “So, users can automate complex vision inspections for a much lower cost of ownership. They can now consider automating quality inspections of products or goods that have just proved too difficult previously.

“Even better, the system can be set up in no time at all. Many users will be able to manage this process themselves. However, if needed, SICK is also offering services to support customers through the feasibility, commissioning and neural network training process.”

Users also have access to a large set of traditional machine vision tools installed on the SICK Inspector P621, so they can extend the functionality of their quality inspection further.

The SICK Inspector P621 is an all-in-one 2D CMOS vision sensor with 1.3 MP image resolution.