An intelligent directing method and system for indoor networked video surveillance

Abstract

The invention discloses an intelligent directing method and system for indoor networked video surveillance. The system includes: a video acquisition module, which is used for pulling video streams from networked surveillance cameras set up indoors, and in the form of offline videos with a fixed duration Save; the time analysis module is used to use offline video to create a timestamp data set, and image recognition is performed at the corresponding monitoring time position of each frame of the video to obtain the time stamp corresponding to each frame of the video; the spatial analysis module is used to determine the coordinates of the detection frame. The global physical space position of the target; the spatial position determination module of the target, which is used to obtain the spatial position of the target and generate the target motion trajectory; the guide module is used to decide whether to switch the camera and the corresponding camera to be switched according to the guide rules; the video playback synchronization module, Used for video playback synchronization control. The present invention enables the user to conveniently and continuously observe the target through the directing control and the multi-channel video picture synchronization mechanism, thereby improving the look and feel.

Description

technical field [0001] The invention relates to a networked monitoring video analysis technology, in particular to an intelligent directing method and system for indoor networked video monitoring. Background technique [0002] The network monitoring system is an important link in the informatization construction of indoor public places, which provides a strong guarantee for the safety of indoor public places. This paper designs and implements a set of intelligent directing system for indoor networked video surveillance. It can provide users with real-time monitoring images about the target of interest, and present the images of the target of interest under different cameras to the customized user in a real-time broadcast mode with the movement of the target of interest, so that the user can conveniently and continuously observe the sense of Interested target, know the real-time status of the target. However, due to frequent occlusions in the indoor environment, inconsisten...

AI Technical Summary

Problems solved by technology

However, due to problems such as frequent occlusions in indoor environments, inconsistent color performance caused by different light sources, and large differences in the resolution of target detection frame pictures, the reliability of target matching solely relying on pedestrian re-identification technology is not enough.

And due to reasons such as busy IO or network congestion, the saved offline videos may have the same duration but inconsistent start times, and there may be a large difference between the frame rate of each video and the video playback frame rate set by the program

Images