viso.ai
        • Train

          Develop

          Deploy

          Operate

          Data Collection

          Building Blocks​

          Device Enrollment

          Monitoring Dashboards

          Video Annotation​

          Application Editor​

          Device Management

          Remote Maintenance

          Model Training

          Application Library

          Deployment Manager

          Unified Security Center

          AI Model Library

          Configuration Manager

          IoT Edge Gateway

          Privacy-preserving AI

          Ready to get started?

          Overview
          Whitepaper
          Expert Services
  • Customers
  • Company
Search
Close this search box.

Intel AI Builders Computer Vision Case Study

Swiss Post Innovation Last Mile Delivery
Build, deploy, operate computer vision at scale
  • One platform for all use cases
  • Scale on robust infrastructure
  • Enterprise security
Contents

Artificial Intelligence (AI) vision technology requires the use of highly efficient yet powerful AI hardware. Recently, Intel AI Builders and viso.ai worked together to leverage technologies in a power-constrained environment using the Movidius Vision Processing Unit (VPU).

viso.ai is part of the Intel AI Builders Program to accelerate the development of computer vision solutions for business challenges.

One unified infrastructure to build deploy scale secure

real-world computer vision

 

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.

Viso Suite infrastructure allows for easy integration and scaling of VPU technologies with on-device AI inference applications.

The case runs on Intel Core i3 processors, combined with the Intel Neural Compute Stick 2 and Movidius Myriad X VPU  for Deep Learning inference, in a robust and industrial housing.

Additionally, the Deep Learning models are optimized using the Intel Distribution of OpenVINO Toolkit. This software kit helps developers and data scientists speed up computer vision workloads, streamline deep learning inference and deployments, and enable execution across different Intel hardware.

Read about the joint case study published by Intel AI Builders and viso.ai.

 

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 warns 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. This is according to initial KPI assessments after the first month of system usage. Furthermore, viso.ai confirms that it will integrate further features into the same system to scale enterprise benefits.

According to Arkadiusz Hruszowiec, Intel Business Development Regional Manager, “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 can take video streams, analyze them in a deep-learning model, and draw insights in real time at the edge. This results in real business impact for the end customer.”

 

Viso Suite Infrastructure to manage edge devices for AI inferencing
Viso Suite Infrastructure to manage edge devices for AI inferencing

 

What’s Next?

Computer vision is an imperative aspect of companies using AI software today. If you enjoyed this article, we suggest you read the following articles:

Play Video