Scalable distributed biometric video monitoring and face tracking system

Scalable distributed biometric video monitoring and face tracking system

by from Moscow, Russia

Design

Tech

Usability

Creativity

Content

Type: Software
Client from United States
Category: Information technology
Style: Realistic
Color: Red

Highlights 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\\r\\nsingle frame·       Fast face search in real time·      \\r\\nEvent\\r\\nconsumers (including access control systems) integration·      \\r\\nWeb portal\\r\\nand on-prem agent for the system monitoring and managementThe challenge The customer needed to develop a video monitoring system for use in\\r\\nsolving automated biometric access control tasks.On the one hand, as an automated video monitoring system, it had to be\\r\\nable to work with IP cameras, track people on their video streams in real time,\\r\\nand identify them by database. On the other hand, it had to have two external\\r\\nintegration loops: one for using the existing biometric database, the other for\\r\\ncommunicating with the access control system, transmitting events to it.In addition to this, there were requirements for collecting a historical\\r\\naudit, providing it to both users on the web portal and external integration\\r\\nsystems via the API.Moreover, the system was supposed to be distributed (including geo),\\r\\nscalable and multi-tenant.The solutionThe contractor, taking\\r\\ninto account the uncertainties of requirements for various parameters, as well\\r\\nas seeing the possibilities for generalizing the solution, designed the most\\r\\nflexible system, without relying on its application directly only in the field\\r\\nof access control.The system consists of\\r\\nseveral modules divided into 2 groups:• On-prem group,\\r\\nmodules that are deployed directly to the consumer, include a video server\\r\\n(Video Server), processing video streams from surveillance cameras, its database\\r\\n(Database) and management agent (Management Agent).• Cloud group, the\\r\\nmodules that are deployed in the cloud include a cloud server (Cloud Server)\\r\\nfor managing on-prem groups, its database (Database) and web portal (Web\\r\\nPortal).Integrations with\\r\\nexisting systems (providers of events, event consumers, consumers of historical\\r\\ndata) are maximally generalized, and do not know anything about the specifics\\r\\nof the application (access control systems, or anything else).The resultsThe system was successfully implemented at the\\r\\nend customer and allowed to execute ACS scenarios in a contactless mode in a\\r\\npandemic 2020.