METHOD, DEVICE AND SYSTEM FOR PROCESSING CCTV IMAGE INSTALLED IN PUBLIC PLACE BASED ON ARTIFICIAL INTELLIGENCE

摘要

According to one embodiment, in the method of processing an image of a CCTV installed in a public place based on artificial intelligence, performed by a device, when the first area is photographed through the first CCTV camera, the obtaining image information generated by shooting of the first area from a first CCTV camera; setting, as first image information, image information captured at a first point in the image information for the first zone; generating a first input signal by encoding the first image information; inputting the first input signal to an artificial neural network, and obtaining a first output signal based on a result of the input of the artificial neural network; detecting whether an event has occurred in the first region based on the first output signal; detecting a type of event occurring in the first region based on the first output signal when it is detected that an event has occurred in the first region; acquiring first meta data set as meta data of the first event when the event occurring in the first area is detected as a first event; and matching the first image information and the first meta data, and storing the first image information in a database.