In a recent announcement made by Dahua Technology USA, it has been revealed that Movidius’ Myriad 2 Vision Processing Unit (VPU) technology is going to be used to power select Dahua video surveillance cameras. Instead of the basic functions of monitoring and recording, these cameras would offer advanced video analysis features like crowd density monitoring, facial recognition, behaviour analysis, stereoscopic vision, behaviour analysis, people counting and illegal parked vehicle detection.
Intel Movidius offers machine intelligence solutions to make devices more aware, autonomous, and useful. It focuses on delivering class-leading AI performance in ultra-low-power smart devices. Making use of Myriad 2 VPU, Dahua would be able to run cutting edge Deep Neural Networks on the device itself, thereby giving way to natively intelligent cameras that can operate with/without cloud-based compute resources.

Intel Movidius Technology to Bring Artificial Intelligence to Surveillance Cameras (Image Courtesy: Intel)
“The new frontier for AI and machine learning is being able to deploy these technologies in real-world products. This means getting the power demand to a low enough level to be embedded right into the cameras themselves,” said Remi El-Ouazzane, vice president of the Intel New Technology Group and general manager of Movidius, in the Dahua announcement. “The Myriad 2 VPU delivers a tremendous amount of compute for deep neural networks while requiring less than a single watt of power – allowing Dahua to create some of the smartest products to date.”
Intel had acquired Movidius in November 2016 and since then the integration of Intel’s RealSense Technology with Movidius’ leading VPU platform has been serving as an ideal combination for autonomous machines that can see in 3-dimensions, understand their surroundings and navigate accordingly.
Filed Under: News
Questions related to this article?
👉Ask and discuss on Electro-Tech-Online.com and EDAboard.com forums.
Tell Us What You Think!!
You must be logged in to post a comment.