Method and system for detecting human face risk in monitoring video

Abstract

The invention discloses a method and a system for detecting a human face risk in a monitoring video. The method comprises the following steps: the monitoring device determines a user to be analyzed; calculating a time interval between the first moment and the second moment, calculating to obtain a first concave-convex degree matching value of the human face in each grid region and a second concave-convex degree matching value of the human face in each grid region; or the time interval is greater than the preset time threshold; or sequentially judging whether the first concave-convex degree matching value of the human face in each grid region conforms to a preset threshold range or not; obtaining N1 matching results, m1 matching results representing that the first concave-convex degree matching value of the human face in the grid area does not conform to a preset threshold range are obtained from the N1 matching results, if the ratio of M1 to N1 is larger than a preset threshold value or the ratio of M2 to N2 is larger than the preset threshold value, a first comparison result is generated, and it is determined that a preset risk exists.

Description

technical field [0001] The invention relates to the field of video surveillance, in particular to a face risk detection method and system in surveillance video. Background technique [0002] Existing automatic teller machines (Automatic Teller Machine, referred to as ATM) are generally arranged in self-service banks, and after inserting a bank card on the ATM, bank counter services such as withdrawal, deposit, and transfer can be performed on the ATM. Due to the openness, convenience and environmental particularity of self-service banks and automatic teller machines. Criminal activity targeting self-service banks and ATMs has increased in recent years. [0003] However, the traditional ATM video surveillance system is mainly to record the video. After the event occurs, the recorded video is used to obtain evidence afterwards, so as to eliminate disputes and solve the case. However, such a mechanism can only provide evidence collection after the event, and cannot achieve Re...

AI Technical Summary

Problems solved by technology

[0003] However, the traditional ATM video surveillance system is mainly to record the video. After the event occurs, the recorded video is used to obtain evidence afterwards, so as to eliminate disputes and solve the case. However, such a mechanism can only provide evidence collection after the event, and cannot achieve Real-time or early warning

Images