logo CenterVision


Industrial video analytics system


CenterVision uses neural networks for object recognition. The system recognizes objects with an accuracy of 98%, track production process in real time, transmit   automatic notification to the situation center, prepare   reports on security violations.

The system consists of video surveillance cameras, rangefinders, lasers, notification and information systems, software (model training, business logic, scenario adaptation), systems for integration with external scenarios (API), and a user interface.

The response time of 2.4 seconds allows the system to learn about security violations; objects are detected at large distances, regardless of rain, snow or fog, recognition of small objects from a long distance (50-70 m) makes it possible to use fewer cameras for monitoring.

logo CenterVision
242Latest update:08.17.2020

Unless otherwise stated, the content is available under Creative Commons BY 4.0 license

Supported by the Moscow Government