Google Clips captures and curates life’s meaningful moments autonomously with Intel’s Movidius VPU inside

October 4, 2017

The Myriad 2 by Movidius is a vision processing unit (VPU) that provides low-power, high-performance vision processing solutions across various target applications including embedded deep neural networks, pose estimation, 3D depth-sensing, visual inertial odometry and gesture/eye tracking. (Credit: Intel Corporation)

» Click to download full-size version

Intel announced that the new Google Clips* hands-free camera uses the Movidius™ Myriad™ 2 vision processing unit (VPU) for on-device artificial intelligence (AI) processing.

Google Clips captures and curates motion photos of a person’s family, friends and pets, making them accessible in the Clips app.

Google’s advanced machine learning algorithms run in real time directly on the Clips camera with the ultralow-power Movidius VPU inside. By enabling on-board processing, rather than in the cloud, Google is able to improve upon power consumption and latency and enable offline use.

“To bring our vision for Clips to life, we’ve been working on integrating Intel’s Movidius technology within Clips to give people many of the benefits of machine learning directly on their device,” said Google Clips product lead Juston Payne. “On-device processing gives people a lengthy battery life, speedy access to their clips, and the ability to use the camera without an internet connection. We can’t wait for parents and pet lovers to start effortlessly capturing spontaneous moments, while getting to stay in the moment.”

“In our collaboration with the Clips team, it has been remarkable to see how much intelligence Google has been able to put right into a small device like Clips,” said Remi El-Ouazzane, vice president and general manager of Movidius, Intel New Technology Group. “This intelligent camera truly represents the level of onboard intelligence we dreamed of when developing our Myriad VPU technology.”

Movidius VPU technology delivers a unique approach to low-power, high-performance computer vision intelligence that is enabling new classes of intelligent and autonomous devices.

“Our partnership with Movidius has meant that we can port some of the most ambitious algorithms to a production device years before we could have with alternative silicon offerings,” said Blaise Agüera y Arcas, director of Machine Intelligence at Google. “With Clips, we are enabling people to capture and share their moments naturally and seamlessly, and Movidius technology has significantly accelerated this initiative.”