Contact company icon Add as a preferred source Download PDF version

In order to implement AI vision solutions, specialist knowledge, development effort and investment in computer hardware and storage technology are usually required.

With cloud computing and specialised training services such as IDS NXT lighthouse, the process becomes much easier: neural networks can be trained individually and at the push of a button, without the need to set 978YIDS NXT ocean, the training software helps to make deep learning accessible to everyone. With the release of IDS NXT lighthouse version 1.1, additional functions are now available.

Powerful inference cameras

IDS NXT lighthouse is an easy to use training software for creating neural networks (IDS Imaging Development Systems GmbH) The training of neural networks in the web application requires three basic steps: to upload individual sample images, to label the images (e.g. "good" / "bad") and then to start the fully automatic training.

The generated network can be executed directly on IDS NXT industrial cameras. This turns them into powerful inference cameras that can solve completely new image processing tasks thanks to artificial intelligence. They have learned which image features are important and are able to apply this knowledge to new image data. This is an enormous advantage compared to classical programming, especially in applications with highly varying objects.

Different sensors and protection classes

All components – camera hardware with AI core and different sensors and protection classes, software, infrastructure, knowledge and support – are developed and provided by a single supplier. This holistic approach makes IDS NXT ocean a unique solution in the vision market.

The IDS NXT lighthouse training software for neural networks is now available as version 1.1. The company has further improved both usability and the range of functions, for example by redesigning the detail view or extending filter functions. The next version is already in the works – then, in addition to classification tasks, object detection will also be feasible.

In case you missed it

Responsible AI adoption starts with governance
Responsible AI adoption starts with governance

The eagerness to adopt AI in physical security is increasing as teams want to implement technology solutions for faster, smarter operations. At the same time, the conversations sur...

How AI-enabled cameras are becoming operational sensors that power safety, automation, and business intelligence
How AI-enabled cameras are becoming operational sensors that power safety, automation, and business intelligence

The biggest return on investment from an AI-enabled camera might have nothing to do with security. Organisations are increasingly discovering that the same cameras installed to pro...

Solink's AI agents boost efficiency of existing infrastructure with automation
Solink's AI agents boost efficiency of existing infrastructure with automation

Deploying artificial intelligence (AI) tools should be seen as a business initiative rather than a technology initiative, says Martin Soukup, CTO of Solink, a cloud-based video sec...