Sound controls

Researchers develop technology to accurately classify sound in CCTV blind spots

[Gettyimages Bank]

SEOUL — South Korea’s state research body has developed a situation recognition solution that can accurately classify sound generated in CCTV blind spots using artificial intelligence. Within three seconds of the sound signal, the combined sound objects can be classified with up to 91% accuracy to monitor crimes and emergencies.

The Korea Photonics Technology Institute (KOPTI) said its research team developed the solution with the aim of detecting all kinds of mixed sounds. It can recognize a total of 76 sounds, including screams, moans, fire alarms, footprints, dog sounds, door sounds, children’s cries, and foreign languages.

Closed circuit television (CCTV) cameras are widely used in South Korea. Smart CCTVs have been demonstrated in various parts of South Korea, equipped with super-fast internet networks. However, violent crime and security accidents have been reported occasionally in blind spots and restrooms where it is difficult to install CCTVs.

The institute said a new security convergence market can be created by applying sound recognition technology to integrated crime and emergency control. “We will actively cooperate with companies in various physical security sectors to strengthen social safety nets by accelerating the development of artificial intelligence technologies that use multiple information such as video and sound,” said Lee Kwang-hoon. , principal researcher at KOPTI.

© Aju Business Daily & Copyright: Nothing on this site may be reproduced, distributed, transmitted, displayed, published or broadcast without the permission of Aju News Corporation.