A real-time identification method for judging someone intruding into a room

Abstract

The invention provides an identification method for judging home invasion in real time, belonging to the security field of video surveillance. The method comprises the steps of: collecting a real-time surveillance video or image and preprocessing the video or the image; and identifying the invasion time, number, body figures and threatening degree of the invaders in the surveillance region by zoning and segmentation processing. According to the method, the problems that the current video or image surveillance system is only used for static forensics and cannot identify a warning condition or give an alarm without the assistance of other sensors are solved; and specific information of the warning condition such as the number, body height, body width and threatening degree of the invaders can be analyzed by the method according to the surveillance video or image, and the surveillance effect and the alarming effect for the surveillance region can be greatly improved.

Description

technical field [0001] The invention relates to an identification method for real-time judging that someone has invaded a room, and belongs to the field of information technology, especially the field of indoor video monitoring. Background technique [0002] An important monitoring object of the security engineering system is the office space of the unit, including public internal places and various office areas. Important security units and departments often install video surveillance systems for security precautions during daily working hours, off-duty or holidays. Especially after get off work or holidays, when the staff are resting, the importance of the monitoring system is self-evident. [0003] Currently common patents or methods for indoor monitoring systems mainly contain five categories. The first category is the basic physical anti-theft method, which is often to modify the anti-theft door and add a sensor or switch (eg: ZL201210164854.4). The second type is a ...

AI Technical Summary

Problems solved by technology

The fifth category is to only install a video surveillance system, relying on the on-duty staff to manually check the video images to find out whether someone has invaded the room

However, these systems cannot perform image matching on holidays, nights or situations where people’s faces are blocked, and occasions with average video effects, and cannot recognize real-time alarm situations, so they cannot achieve good monitoring results.

Images