Abstract: A video analysis system is a system in which a video is analyzed through an edge device installed in each site to generate a security event, and when the edge device continuously generates erroneous security events, the video is analyzed through another edge device or a cloud server in parallel, and then a deep learning model enabling the edge device not to generate an erroneous security event is found to change the edge device, thereby maintaining high video analysis quality.

Abstract: An event detection system with adaptively changeable event detection conditions according to an aspect of the present invention includes an edge device that analyzes a captured video in real time and detects a defined event on the basis of set detection conditions, and a control server that verifies an event detection result transmitted by the edge device, collects statistical information on a result of the verification, and then controls the edge device to adjust and change the detection conditions on the basis of the statistical information.

Abstract: Provided is a system for detecting an event using a multimodal generative artificial intelligence (AI) model, the system including an edge device that analyzes videos, which are recorded by one or more cameras installed in a space to be monitored, in real time through one or more AI model parts and detects an event, and a server device that verifies an event detection result of the edge device on the basis of the event detection result transmitted by the edge device and preset specification information of the AI model parts, analyzes a response acquired through the multimodal generative AI model using a prompt that requests additional information for event detection in accordance with a verification result, and controls operations of the AI model parts of the edge device.

Abstract: Provided is an intelligent image analysis system metaverse system for analyzing an object by intelligently processing camera images of a plurality of spatial zones in each of which at least one camera is installed. The intelligent image analysis system includes body shape encoders configured to detect an object in a camera image of each spatial zone and encode the object into a shape identifier (ID) on the basis of features of a body shape, a spatial-zone-specific identification manager configured to manage the shape ID together with camera information and time information, an identical shape ID extractor configured to extract identical shape IDs from different spatial zones on the basis of a list of shape IDs which are encoded according to each spatial zone, and an identical object determiner configured to determine a shape ID related to the same object using a distance between two spatial zones and imaging time information.

Abstract: Provided is an intelligent security system, which generates a more specific query about a situation in which video is captured and query to generative AI to be able to reduce ambiguity in result analysis different from intent, thereby more accurately identifying a security event.

Abstract: Provided is an intelligent image analysis system metaverse system for analyzing an object by intelligently processing camera images of a plurality of spatial zones in each of which at least one camera is installed. The intelligent image analysis system includes body shape encoders configured to detect an object in a camera image of each spatial zone and encode the object into a shape identifier (ID) on the basis of features of a body shape, a spatial-zone-specific identification manager configured to manage the shape ID together with camera information and time information, an identical shape ID extractor configured to extract identical shape IDs from different spatial zones on the basis of a list of shape IDs which are encoded according to each spatial zone, and an identical object determiner configured to determine a shape ID related to the same object using a distance between two spatial zones and imaging time information.

Abstract: Provided is a metaverse system. The metaverse system for providing metaverse content virtualizes a target space as a digital twin but statistically applies attributes and action patterns of objects in the target space to virtual objects in a virtual space, thereby reproducing the environment, atmosphere, and the like of the target space without accurately copying the attributes and action patterns of objects.

Abstract: A video analysis system is a system in which a video is analyzed through an edge device installed in each site to generate a security event, and when the edge device continuously generates erroneous security events, the video is analyzed through another edge device or a cloud server in parallel, and then a deep learning model enabling the edge device not to generate an erroneous security event is found to change the edge device, thereby maintaining high video analysis quality.