Privacy protection method based on monitoring video multi-target tracking and face recognition

Abstract

The invention belongs to the field of video privacy protection technology and discloses a privacy protection method based on monitoring video multi-target tracking and face recognition. The method comprises the steps that a background model is established and updated according to a real-time monitoring video, and the new background model is adopted to divide a foreground target region; pedestrian detection and face recognition are performed based on the foreground target region, and continuous tracking and identity recognition of community internal personnel and community foreign personnel in a community monitoring video are realized through combination of a Kalman filtering technology and a Hungary algorithm; and video information of the community internal personnel is protected by means of information hiding. According to the method, privacy information of users in a community is protected through face recognition and target tracking technologies, foreign strangers are also monitored, and balance is achieved between maintenance of community safety and protection of user privacy; and the video information of specific users is subjected to privacy protection in combination with target detection, target recognition and multi-target tracking technologies while monitoring system availability is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of video privacy protection, and in particular relates to a privacy protection method based on surveillance video multi-target tracking and face recognition. Background technique [0002] In recent years, with the continuous improvement of personal privacy security requirements, the protection of personal privacy in public surveillance systems has received widespread attention. The monitoring system must first meet the needs of maintaining the security of the area under its jurisdiction. However, for the monitoring system installed in areas with fixed personnel, such as communities, while maintaining security, it also leaks the private information of community insiders who basically have no security threats. Therefore, ensuring the security function of the monitoring system while not disclosing the private information of the insiders in the community is a hot issue in current research. Due to its high acade...

AI Technical Summary

Problems solved by technology

[0003] To sum up, the problems existing in the existing technology are: the security monitoring in the community deviates more seriously from user privacy protection, basically at the expense of user privacy to ensure the norma

Images