A person state detection method and device based on eyelid feature information

Abstract

The embodiment of the present invention discloses a person state detection method and device based on eyelid feature information. The method includes: obtaining a face image including a face of a target person; detecting two-dimensional position information of face feature points from the face image; Combining with the preset 3D face model, construct the target 3D face model; then combine the projection matrix to determine the projection position information of the eyelid space point at the specified position in the face image; based on the position corresponding to the specified position in the face image The two-dimensional position information of the eyelid feature point, the three-dimensional position information of the eyelid space point at the specified position, and the projection position information determine the current opening and closing length of the upper and lower eyelids; based on the current opening and closing length, determine the current state of the target person to Realize the determination of the eyelid feature information of the human eye, use the eyelid feature information to improve the accuracy of the detection result of the opening and closing state of the human eye, and improve the accuracy of the detection result of the current state of the person.

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 eyelid feature information. Background technique [0002] In the state of fatigue, personnel are prone to operating errors. For example, drivers are prone to car accidents when driving fatigued. In order to reduce the occurrence of dangerous situations caused by personnel fatigue to a certain extent, the current state of the personnel can be detected. 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. The model detects the face image, and detects the open and closed state of the target person's eyes, that is, to detect whether the target person's eyes are in the closed state; according to the detection result, determine whether the target person is fatigued. If the eyes are closed, it is...

AI Technical Summary

Problems solved by technology

[0003] In the process of detecting the current state of the above-mentioned personnel, before training the model, when labeling the sample images, the labeling standards for the closed and open states of the eyes in the sample images cannot be unified. For example, some labels for half-open eyes People are marked as open, and some are marked as closed, which leads to the blurred detection boundary between the closed state and open state of the human eye in the image by the pre-trained human eye state detection model, which leads to inaccurate detection results

Images