Creating vision apps with no programming knowledge

07-06-2022 | IDS | Design & Manufacture

IDS NXT's current software release 2.6 for the AI vision system focuses mainly on simplifying app creation. The initial phase in the development is frequently one of the most significant challenges in realising a project. With the new Application Assistant in IDS NXT lighthouse, users configure an entire vision app under guidance in only a few steps, which they can then run straight on an IDS NXT camera. With the Block-based Editor, which is also new, users may configure their own program sequences with AI image processing functions, such as object recognition or classification, with no programming knowledge. Users construct simple sequences in a few minutes with this visual code editor with no knowledge of the syntax of a specific programming language.

With the Use Case Assistant, the company supports users in constructing Vision App projects. They simply choose the use case that fits their project. With queries and tips, the assistant guides them through the process of producing the Vision App project and creates the code, just like in an interview. It links existing training projects with the vision app project or creates new training projects and data sets in IDS NXT lighthouse if needed.

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


It is a comprehensive system with multiple workflows and tools for producing users' own AI vision applications. The intelligent cameras can process tasks 'OnDevice' and produce image processing results. The functions of the cameras are defined by apps that are uploaded to the cameras and executed there. Their functionality can therefore be modified at any time. This is supported by software such as IDS NXT lighthouse, with which users may not only train neural networks but now also construct their own vision apps. The system provides beginners and professionals with enormous scope for creating AI vision apps.

By Natasha Shek