A CCTV Camera

Loss Prevention Retail Reference Implementation

Loss Prevention Retail Reference Implementation provides:

  • High-quality testable ingredients needed to create a solution to prevent thefts at stores.

  • Building blocks needed to enable the use case with solid performance numbers.

  • Hardware requirements to support the workloads and scale the solution.




The Loss Prevention Reference Implementation provides critical components to build and deploy solutions to prevent store theft. This reference implementation focuses on theft at shopping aisles and checkout stations. This reference implementation provides pre-configured loss prevention pipelines optimized for Intel® hardware.


To build the Intel® Loss Prevention Reference Implementation, you need:

  • Ubuntu* LTS Boot Device
  • Docker*
  • Git*

To know about the supported platforms, see the list of platforms

Learning Objectives

Using this reference implementation, you can:

  • Identify optimized middleware and frameworks relevant for checkout use cases from Intel.
  • Utilize services developed for the self-checkout reference implementation.
  • Use the core checkout services to build the loss prevention reference modules.
  • Identify the required hardware for the intended workloads.

Features and Benefits

With this reference implementation, the retail stores can:

  • Monitor persons of interest
  • Track products that customers might hide (Recognize suspicious customer activity).
  • Identify price switching.
  • Keep track of the items skipped in the basket and shopping cart.

How it Works

This reference implementation identifies video streams projected by various types of cameras, such as the overhead cameras at the isles, shelf monitoring cameras, and cameras in the self-checkout area. Different AI models with varying resolutions and precisions drive this reference implementation.   

Loss Prevention - Functional Diagram

You can sign up to know about the upcoming releases.

The loss prevention reference design complements features in the automated self-checkout reference implementation. Together, they address critical data and software code that can be readily verified and used when building complete solutions.


The reference implementation includes:

  • Source code
    • Microservices
    • Benchmark scripts
    • Pre-trained models
  • Documentation
  • Learning videos (will be available in the forthcoming releases)
  • Hardware recommendation
  • Tools and libraries
  • Operating system support
  • Support for Intel architecture-based platforms

Get Started on GitHub

Performance Results

Find the latest performance results by choice of Intel® processors for the vision-enabled workloads.

View Performance Results

Report Issue or Submit Feedback

You can open an issue on GitHub to report a problem related to the reference implementation or give feedback.