This short video showcases an early experiment using the Voyager SDK and Metis AIPU to run Fast Segment Anything (FastSAM). It is based on YOLOv8-seg generating masks and CLIP to link the text prompt with visual masks in the video stream.
What’s exciting is the flexibility—no need for retraining on specific classes. Just change the text prompt and it finds the object. This is still a test setup, but I thought it might spark a few ideas and show what’s becoming possible on the edge with Metis. Keen to hear what you guys think, or how you’d use this!
That’s something else AI would be better at...
. With the question where to use it the first answer is security systems. This security officer input to share other security guys that the target with danger item have Pokemon uniform or targeted car has logo with some specific text. It can safe the lives sometimes quick reaction and many details, where people can forgot what the car colour was or logo. Not only that. Logistics to recognise exact containers. Flood to rescue some people or animals. Medical to help pharmacies. Hospitals to help nurses and doctors. Car industry to help with the processes. Components manufacturing to help with references. Do you need more ???. Simple things can be developed very fast and generate massive profits for the business not only Axelera but more important for others. 
