Infineon adds computer vision to edge AI tool
Cette publication existe aussi en Français
Infineon Technologies is adding support for computer vision machine learning to its Deepcraft Studio edge AI development tool.
This builds on existing support for audio, radar and other time-series data in the tool that was acquired with Imagimob.
Computer vision has been a key technology for machine learning, with frameworks such as YOLO used for real-time visual inspection of parts or to shut down machinery in the presence of a human.
Infineon opens up Apple ‘find my’ network with secure wireless chips, microcontrollers
“These updates to Deepcraft Studio optimize each step in AI model development for vision-based use cases, starting with data collection and preprocessing and all the way through model deployment,” says Alexander Samuelsson, Product Manager for Deepcraft Studio. “This means we are offering developers truly end-to-end support for vision. With this support paired with Infineon’s PSOC Edge high performance machine learning MCUs, Infineon’s customers are well-equipped to add top-of-the-line Edge AI features to their products.”
A demonstration with object detection using Ultralytics YOLO models enables developers to train custom computer vision frameworks using the tool. This significantly reduces training time while maintaining high accuracy, making AI deployment faster and more efficient.
Developers can run their model in real-time using their own computer and camera, making sure it works as intended before deploying onto hardware. This speeds up development, as improvements can be made to the model before it is deployed.
The version of Deepcraft Studio with support for vision will be released in April with an automatic update, and the tool can be downloaded here.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
