Create vision applications without any programming knowledge

07-06-2022 | IDS | Design & Manufacture

The current software version 2.6 of IDS NXT for the AI ​​vision system mainly focuses on simplifying the creation of applications. The initial phase of development is often one of the biggest challenges in delivering a project. With the new application wizard in IDS NXT lighthouse, users set up a complete vision application under the guidance in just a few steps, which they can then run directly on an IDS NXT camera. With the block-based editor, which is also new, users can configure their own program sequences with AI image processing functions, such as object recognition or classification, without any programming knowledge. Users build simple sequences in minutes with this visual code editor without any knowledge of the syntax of a specific programming language.

With the Use Case Wizard, the company helps users build Vision App projects. They simply choose the use case that matches their project. With questions and advice, the assistant guides them through the production process of the Vision App project and creates the code, like in an interview. It links existing training projects to the vision application project or creates new training projects and datasets in IDS NXT lighthouse if needed.

With combinable blocks and the intuitive block-based editor user interface, anyone can produce their own projects using AI-based image processing (such as object detection or classification ) as an individual vision application without needing to know the syntax of a specific editor. programming language. Using the predefined code editor blocks, users graphically create their vision application, including processes including loops and conditional statements. How this works is demonstrated, for example, in the IDS Vision Channel. The session “Creating AI vision applications without coding – an exciting new facility” is provided for viewing as a recording.

It is a complete system with multiple workflows and tools to produce users own AI vision applications. Smart cameras can process “OnDevice” tasks and produce image processing results. Camera functions are defined by applications that are downloaded to the cameras and run there. Their functionality can therefore be modified at any time. This is supported by software such as IDS NXT lighthouse, with which users can not only train neural networks, but now also build their own vision applications. The system offers beginners and professionals a huge leeway to create AI vision applications.

Donald E. Patel