Infineon integrates computer vision into edge AI tool

Infineon Technologies is enhancing its Deepcraft Studio edge AI development tool by introducing support for computer vision machine learning. This new feature complements the existing capabilities of the tool, which already supports audio, radar, and other time-series data following the acquisition of Imagimob.

Computer vision plays a crucial role in machine learning applications, with popular frameworks like YOLO being utilized for tasks such as real-time visual inspection of components or ensuring safety by detecting human presence near machinery.

As part of the update, Infineon is rebranding the edge AI models and tools from Imagimob, further solidifying its commitment to providing comprehensive solutions for developers. Alexander Samuelsson, Product Manager for Deepcraft Studio, highlights the significance of these enhancements, stating, “These updates to Deepcraft Studio optimize each step in AI model development for vision-based use cases, from data collection to model deployment, offering developers end-to-end support for vision."

A notable feature of the updated Deepcraft Studio is its support for object detection using Ultralytics YOLO models, enabling developers to train custom computer vision frameworks efficiently. This capability not only reduces training time but also maintains high accuracy, facilitating faster and more efficient AI deployment.

Developers can now test their models in real-time using their own computer and camera, ensuring the functionality before deploying it onto hardware. This iterative process accelerates development by allowing for improvements to be made to the model prior to deployment, ultimately enhancing the overall quality of the AI solution.

The enhanced version of Deepcraft Studio, equipped with support for vision-based applications, is set to be released in April through an automatic update. Developers interested in leveraging these advanced features can download the tool to explore its full potential.