AI vision technology requires the use of highly efficient yet powerful AI hardware. Recently, Intel AI Builders and viso.ai published a case study about leveraging technologies in a power constraint environment using the Movidius Vision Processing Unit (VPU).
Scale Intel VPU technology with viso.ai
Movidius VPUs enable computer vision and on-device edge AI workloads at very high efficiency (cost-to-performance). This is achieved by coupling highly parallel programmable computing with workload-specific AI hardware acceleration. VPU technology enables cameras, edge devices (servers), and AI inference with deep neural networks and computer vision based applications. The software platform of viso.ai allows to easily integrate and scale VPU technologies to be part of an on-device AI inference application.
Additionally, the Deep Learning models are optimized using the Intel Distribution of OpenVINO Toolkit, a software kit that helps developers and data scientists speed up computer vision workloads, streamline deep learning inference and deployments, and enable execution across different Intel hardware.
On-Device Deep Learning Inference
The featured solution is based on Edge Computing devices that are mounted inside delivery vehicles. The Movidius Myriad X VPU provides enough power to perform object detection on three input camera streams in real-time at low electrical power consumption. The output is used to warn the driver about potential obstacles. In addition, the Intel Core i3 processor performs geometrical transformation tasks to display the live video streams to the driver inside the delivery van.
Intel AI Builders point out how using the latest, optimized Intel AI technologies has resulted in significant direct cost reduction, according to initial KPI assessments after the first month of system usage. Furthermore, viso.ai confirms that further features are now planned to be integrated into the same system to scale the benefits observed even more.
According to Arkadiusz Hruszowiec, Intel Business Development Manager for the region, “this project is a proof-point that our strategy of enabling AI on edge devices works in practice. By using the Intel Distribution of OpenVINO toolkit and Intel Vision Accelerator Solutions, viso.ai is able to take video streams, analyze them in a deep-learning model and draw insights in real-time at the edge, which results in real business impact for the end customer.”
Computer vision is an imperative aspect of companies using AI today. If you enjoyed this article, we suggest you read the following articles: