Intel Demonstration of Running Mixed Deep Learning Workloads on CPU-plus-Movidius VPU Devices

Akshatha Kini, Product Application Engineer at Intel, demonstrates the company's latest embedded vision technologies and products at the 2019 Embedded Vision Summit. Specifically, Kini demonstrates running multiple deep learning-based computer vision applications in parallel.

The first application shows face detection and face recognition, along with age and gender identification. The second application is running face detection and face blurring. Next, there are two traffic monitoring applications which show Illegal parking detection and illegal turn detection.

The deep learning workloads are being distributed in real time between the CPU and an accelerator card based on eight Movidius VPUs. Face detection, for example, is running on the CPU while the face recognition and face blurring applications are running on the VPUs. Using OpenVINO enables developers to divide the workloads in real time between different Intel hardware architectures.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top