Bookmark and Share

"Pilot AI Vision Framework: From Doorbells to Defense," a Presentation from Pilot AI

Register or sign in to access the Embedded Vision Academy's free technical training content.

The training materials provided by the Embedded Vision Academy are offered free of charge to everyone. All we ask in return is that you register, and tell us a little about yourself so that we can understand a bit about our audience. As detailed in our Privacy Policy, we will not share your registration information, nor contact you, except with your consent.

Registration is free and takes less than one minute. Click here to register, and get full access to the Embedded Vision Academy's unique technical training content.

If you've already registered, click here to sign in.

See a sample of this page's content below:


Jonathan Su, CEO of Pilot AI, presents the "Pilot AI Vision Framework: From Doorbells to Defense" tutorial at the May 2018 Embedded Vision Summit.

Pilot AI’s Vision Framework has enabled real-time detection, classification and tracking in thousands of devices, from consumer applications to federal contracts. Though diverse in end-user application, these use cases all share a common disadvantage: they are compute-constrained. Small consumer electronics are compute-constrained as BoM cost limits the amount of silicon that can be integrated, whereas federal use cases are compute-constrained since the problem (seeing from thousands of feet in the sky) requires processing a tremendous amount of data in real-time without reliable network connectivity.

Scaling a single framework to enable the diverse set of hardware platforms these applications represent, from ultra-low power DSPs and microcontrollers to full-size GPUs, is what differentiates Pilot AI’s Vision Framework. Su introduces Pilot AI’s deep learning-based computer vision framework for compute-constrained devices and demonstrates this framework in real-world applications to motivate the drive towards embedded deep learning.