Intelligent System Design for Massive Collection and Recognition of Faces in Integrated Control Centres

Abstract

Intelligent system design for face collection and recognition in integrated control center is presented. Generally, cameras installed for city surveillance monitors wide area. So, it is hard to recognize person by face with those cameras because of lack of image resolution. Our system adopts two cameras, one for normal surveillance and the other for zooming a target face. The system carries out motion detection for candidate of human and detects and recognizes faces based on Microsoft cognitive services. The system utilizes codec’s metadata for motion detection. So, without decoding it can detect the area of motion. As a result, it can handle hundreds of cameras simultaneously in one server. It entrust MS cognitive services with face recognition. It can provide monitoring agents with functionality of searching video in terms of people, which is virtually meaningful to them.

This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No. 2016-0-00109, Development of Video Crowd Sourcing Technology for Citizen Participating-Social Safety Services).