Scalable distributed biometric video monitoring and face tracking system

Alexander Solovey
Jun 26 · 3 min read

Face Tracking System is a scalable distributed biometric video monitoring software. It is designed to detect, track and identify people by faces in live video streams, generates events in real time, accumulates historical data, provides access to them through the API and web portal.

Image for post
Image for post


· Distributed video monitoring and tracking system

· Hybrid scalable architecture: on-prem and cloud

· IP-cameras connectivity and configuration

· Biometry/Faces providers integration

· Real time faces detection up to 20 in the single frame

· Fast face search in real time

· Event consumers (including access control systems) integration

· Web portal and on-prem agent for the system monitoring and management

Image for post
Image for post

The challenge

The customer needed to develop a video monitoring system for use in solving automated biometric access control tasks.

On the one hand, as an automated video monitoring system, it had to be able to work with IP cameras, track people on their video streams in real time, and identify them by database. On the other hand, it had to have two external integration loops: one for using the existing biometric database, the other for communicating with the access control system, transmitting events to it.

In addition to this, there were requirements for collecting a historical audit, providing it to both users on the web portal and external integration systems via the API.

Moreover, the system was supposed to be distributed (including geo), scalable and multi-tenant.

Image for post
Image for post

The solution

The contractor, taking into account the uncertainties of requirements for various parameters, as well as seeing the possibilities for generalizing the solution, designed the most flexible system, without relying on its application directly only in the field of access control.

The system consists of several modules divided into 2 groups:

• On-prem group, modules that are deployed directly to the consumer, include a video server (Video Server), processing video streams from surveillance cameras, its database (Database) and management agent (Management Agent).

• Cloud group, the modules that are deployed in the cloud include a cloud server (Cloud Server) for managing on-prem groups, its database (Database) and web portal (Web Portal).

Integrations with existing systems (providers of events, event consumers, consumers of historical data) are maximally generalized, and do not know anything about the specifics of the application (access control systems, or anything else).

Image for post
Image for post

The results

The system was successfully implemented at the end customer and allowed to execute ACS scenarios in a contactless mode in a pandemic 2020.

Image for post
Image for post

ITA Labs, High load identification and management systems. Architecture design and custom development.

ITA Labs

High load identification and management systems.

Medium is an open platform where 170 million readers come to find insightful and dynamic thinking. Here, expert and undiscovered voices alike dive into the heart of any topic and bring new ideas to the surface. Learn more

Follow the writers, publications, and topics that matter to you, and you’ll see them on your homepage and in your inbox. Explore

If you have a story to tell, knowledge to share, or a perspective to offer — welcome home. It’s easy and free to post your thinking on any topic. Write on Medium

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store