Robot monitoring alarm system

Abstract

The invention discloses a robot monitoring alarm system. The robot is equipped with a microphone array, a camera and an infrared thermal imager, and is also equipped with an image processing module; current scenes are recorded through the camera in real time; vibration frequency and vibration amplitude of heads, necks and bodies of persons in the scenes are analyzed through the image processing module so as to acquire the susceptibility degree; when the susceptibility degree of the person analyzed by the image processing module is higher than a predetermined threshold value, the person is recognized as a suspicious person; the camera is driven by the robot to shoot face feature data of the suspicious person from multiple angles, and the face feature data can be analyzed by the image processing module, and the susceptibility degree of the suspicious person is updated; and when the analyzed susceptibility degree of the person is higher than the predetermined threshold value, alarm information is fed back. According to the technical scheme of the invention, multi-level recognition can be realized, and the face feature information of the suspicious person can be shot from different angles, so that the quality level of the face recognition data can be improved.

Description

technical field [0001] The invention belongs to the field of safety monitoring, and in particular relates to a hall robot monitoring and alarm system. Background technique [0002] In the halls of banks, shopping malls, and government agencies, surveillance cameras will be deployed in certain locations. The existing video surveillance equipment in halls and halls can continuously record what is happening in the current scene, and security personnel can view the monitoring remotely. [0003] However, existing technologies on the market have some deficiencies, which make it difficult to meet the requirements of monitoring accuracy. The main problems that exist include: [0004] 1. Through fixed camera monitoring, there will inevitably be blind spots. The suspect avoids the camera monitoring range to commit crimes, and the camera cannot detect it. [0005] 2. Surveillance cameras currently only play the role of recording images. It is necessary to manually judge the current s...

AI Technical Summary

Problems solved by technology

[0004] 1. Through fixed camera monitoring, there will inevitably be blind spots. The suspect avoids the camera monitoring range to commit crimes, and the camera cannot detect it.

[0005] 2. Surveillance cameras currently only play the role of recording pictures. It is necessary to manually judge the current situation of the scene. It cannot intelligently analyze the pictures. When there are many monitoring pictures, the observation will be careless and more omissions will occur.

[0006] 3. Surveillance cameras have no way to capture the changes in facial expressions of people in close range and in detail, and cannot collect high-definition images from various angles

[0007] 4. When the site is not in business hours, when the monitoring is unattended, there is no way to find out the alarm immediately when a crime occurs, and the monitoring video can only play the function of recording

Images