With the help of the IDS NXT lighthouse cloud software, even non-experts with no prior knowledge of artificial intelligence or camera programming can train an AI classifier using their own image data. As it is a web application, all functions and the infrastructure required to create the neural network are immediately available. This means that users do not have to set up their own development environment first, but can start training their own neural network straight away. This involves three main steps: Upload sample images, label the images and then start the fully automatic training. The generated network can then be run directly on the IDS NXT industrial cameras, turning them into inference cameras.

Inference cameras for industrial use
An inference camera can apply the "knowledge" it has acquired through deep learning to new data. This makes it possible to automatically solve tasks that would not be possible at all or only with great effort using rule-based image processing. As IDS NXT industrial cameras have a special AI core, neural networks are executed directly on the devices with hardware acceleration, enabling inference times of just a few milliseconds. With features such as C-mount, robust housing, GigE network connection with RJ45 or M12 connector, RS232 interface and REST web interface, they are also fully-fledged industrial cameras. The IDS NXT rio and rome models are now available as series cameras with different sensors and protection classes.

Get started with the Design-In Kit
The camera specialist also offers an IDS NXT ocean Design-In Kit. It contains all the components a user needs to create, train and run a neural network in their productive environment. In addition to an IDS NXT industrial camera with a 1.6 MP Sony sensor, lens and cable, the package includes six months' access to the AI training software. The company promises that the use of deep learning-based image processing for its own applications can be implemented in a short space of time. as