Intelligent analysis system and intelligent analysis method for video monitoring, and system and method for detecting and tracking head and shoulder

Abstract

The invention discloses an intelligent analysis system and an intelligent analysis method for video monitoring, and a system and a method for detecting and tracking head and shoulder. People in the scene can be identified by detecting human head and shoulder and estimating and identifying motions of human head and shoulder, and then intelligent analysis is realized; therefore, the inapplicabilitywhen identifying the people by the whole human body is avoided, and the accuracy of the intelligent analysis is improved due to the improved identification precision of the human body.

Description

technical field [0001] The invention relates to video monitoring technology, in particular to a video monitoring intelligent analysis system, a video monitoring intelligent analysis method, a head and shoulders detection and tracking system, and a head and shoulders detection and tracking method mainly suitable for indoor monitoring. Background technique [0002] There are many application scenarios for video surveillance, such as traffic scenes, open outdoor scenes, crowded indoor scenes such as subways and shopping malls, and indoor scenes with low crowd density such as offices. In these different scenarios, focus on The goals and focus of each are different. [0003] For various indoor scenes, especially indoor scenes with low crowd density, the most concerned target of video surveillance is of course people, and the most concerned content is concentrated on people's movements, such as the gathering of many people, the number of people entering and leaving, and whether th...

AI Technical Summary

Problems solved by technology

However, this method requires the entire human body to be displayed in the image. For some monitoring scenes with a large number of people, such as indoor scenes, indoor people are frequently blocked, and usually only the head and shoulders of the human body can be displayed. Therefore, although the method has high precision, it is difficult to apply

[0006] It can be seen that when the existing technology judges whether a certain target in the monitoring scene is a person by detecting the human body, it is necessary to require the entire human body to be displayed in the image, so although the accuracy is high, it is difficult to apply, so that it cannot improve the performance of intelligent video analysis. accuracy

Images