Smart Retail
In-store AI analytics

Computer Vision-based AIoT inventory and customer insights solutions marking a new era in retail business understanding.

The problem.​

For retail businesses, efficient vision-based, embedded machine learning unlocks usable analytics to help enhance the customer experience. Vision-based solutions require software to process real-time data that streams from IoT devices in a variety of expanding markets. AI, machine learning, and deep learning technology provide an opportunity to effectively leverage exponentially increasing data while reducing maintenance costs and downtime.

To capture these opportunities, organizations require a solution that:

In collaboration with:

The solution.

In this Use Case we utilize end-to-end software & services platform to deploy Computer Vision & AI at scale, with Intel® distribution of OpenVINO™ toolkit. is an end-to-end AI software and services platform that supports the full Vision-AI product lifecycle by integrating ML models for any type of object detection together with vision system design, data management and ready-to-use deployment tools for on-device intelligence. OpenVINO™ enables to significantly reduce the required time for porting proprietary machine learning algorithms into Intel® VPUs. Using OpenVino™ and Intel® Myriad X VPUs, Irida has been able to speed up inference performance by up to 55x vs ARM-based CPU, and accelerates full solution development, from algorithmic design to in-store deployment, down to 2 months.

Irida Labs with Intel® distribution of OpenVINO™ toolkit enables high-powered, Computer Vision AIoT solutions for Retail

The advantages.

The proposed application detects people, objects and vehicles, achieving remarkable levels of accuracy and robustness. Our goal is to provide an easily scalable and cost-efficient solution, that can be implemented in a wide variety of real-life scenarios.

0 %
speedup vs. ARM-based CPU
  • Low cost & low power, scalable and versatile system design
  • Integrates to 3rd party systems
  • Privacy preserving – no cloud processing
  • Valuable analytics related to customer behavior and interactions within a retail store
  • Real-time insights based on customer counting and tracking
  • Facilitates conformation to regulations during post-COVID era

The applications.

The future of retail clearly points in the direction of Smart Retail applications. Retail businesses that have a physical presence of people and goods on promises, such as stores, shopping malls, super markets, can benefit from accurate people counting to measure footfall, get insightful smart space analytics and make informed business decisions about cost savings, increased productivity and revenue growth.

Combined with advanced features like personnel analytics or product monitoring, this complete, inventory and customer insights solution is low-cost, energy efficient and easy to install, marking a new era in retail business understanding. 

Download the Presentation


In this presentation with the title “Irida Labs with Intel Technology enables high-powered, vision-based AIoT Solutions” , developed in collaboration with Intel®, you will learn more about the proposed solution components, comparison speed tests and technical details.

    Skip to content