A person state detection method and device based on multi-face information

Abstract

The embodiment of the present invention discloses a person state detection method and device based on multi-face information. The method includes: detecting face feature points in the face from the face image; Face model, constructing the target 3D face model corresponding to the person; based on the first eyelid space point, the first lip space point and the preset projection matrix in the target 3D face model, determine the first eyelid space point and the first lip space point The projection point in the face image; based on the first eyelid space point and the corresponding projection point and the corresponding eyelid feature point in the face image, determine the current opening and closing length of the upper and lower eyelids; based on the first lip space point and the corresponding projection Points and the corresponding lip feature points in the face image to determine the current opening and closing degree of the upper and lower lips; based on the current opening and closing degree and the current opening and closing length, determine the current state of the person, so as to improve the accuracy of the detection results of the current state of the target person sex.

Description

technical field [0001] The present invention relates to the technical field of video surveillance, and in particular, to a method and device for detecting a person's state based on multi-face information. Background technique [0002] The current state detection method of the relevant personnel can generally determine the current state of the personnel by detecting the state of the human eye. Specifically, the process of the method for detecting the current state of the person is generally as follows: obtaining a face image collected for the target person, and determining the degree of opening and closing between the upper and lower eyelids of the human eye in the face image to determine the eye level of the target person. state, and further, determine whether the current state of the target person is a fatigue state, wherein when the opening and closing degree is lower than the preset opening and closing threshold, it is determined that the human eye is in a closed state, a...

AI Technical Summary

Problems solved by technology

[0003] However, in the current state detection method of relevant personnel, the current state of the driver is determined only based on the state of the human eye, which is prone to false detection to a certain extent

For example, when the person is a vehicle driver and the vehicle is driven in a strong light environment, the impact of strong light will easily cause the degree of opening and closing of the upper and lower eyelids of the driver's eyes to be lower than the preset opening and closing threshold , and thus prone to false detection results

Images