Method for splitting and indexing surveillance videos

Abstract

The invention discloses a method for splitting and indexing surveillance videos, in particular to a method for splitting the surveillance videos through the human face detection and tracking and the movement track cluster analysis for crowd detection and for carrying out association degree analysis on surveillance video fragments according to the position information of surveillance setting points so as to improve the indexing speed and the intelligibility of videos. The method can be widely applied to residential property monitoring, commercial center exhibition hall monitoring, subway traffic monitoring and other application occasions.

Description

technical field [0001] The present invention relates to a monitoring video segmentation and indexing method, in particular to a monitoring video segmentation realized by face detection and tracking, moving track clustering analysis and crowd detection, and the monitoring video clips are associated according to the location information of monitoring setting points It can be widely used in residential property monitoring, shopping mall exhibition hall monitoring, subway traffic monitoring and other application scenarios, and belongs to the field of video monitoring data retrieval technology. Background technique [0002] Video surveillance is an important content and technical means in the field of surveillance. In recent years, with the rapid development of microelectronics technology, video compression processing technology, and network technology, the cost of video surveillance is decreasing day by day, and the application scenarios are increasing. It is widely used in defen...

AI Technical Summary

Problems solved by technology

[0010] However, in practical applications, complex situations often occur in surveillance video scenes, such as the situation of multiple people and vehicles, and there are targets moving in multiple directions at the same time. , indexing brings technical difficulties

[0011] The Chinese patent "Video Analysis, Archive and Alarm Method and Equipment for Video Surveillance System" (patent number: ZL 200510106772.4) discloses a method for managing video tracks, and the managed video tracks include independent human beings, vehicles and other objects. The function of the method is complex and comprehensive, and it is mainly used to detect the situation of real-time video surveillance analysts. However, in general monitoring application scenarios, emergencies are rare after all, and most of them are traced back after the event. Therefore, more appropriate storage and retrieval methods are needed.

Images