Head attitude angle detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a head attitude angle detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a face area of a target person in a to-be-detected image; performing feature extraction on the face region by using a pre-trained deep learning model to obtain global features and key point thermodynamic diagram features of the face region; splicing the global features and the key point thermodynamic diagram features by using a deep learning model to obtain attitude angle prediction features; and analyzing the attitude angle prediction features by using a deep learning model to obtain a head attitude angle corresponding to the face area. On the basis of considering the key points of the face, the global features of the face are also considered, so that the detection precision of the head attitude angle can be improved when the key points are not accurately positioned; under the condition that key points drift when a target person turns the head substantially and lowers the head, the detection precision of the head posture angle is improved, and the method is suitable for the condition that the target person wears a mask.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a method, a device, an electronic device and a storage medium for detecting a head posture angle. Background technique [0002] With the development of computer vision technology, intelligent traffic based on surveillance video becomes possible. In order to better supervise and regulate the behavior of drivers and reduce traffic accidents caused by driver distraction, driver monitoring has received more and more attention. A core function in driver monitoring is to detect the driver's distraction state, that is, to determine whether the driver is distracted by detecting the driver's head attitude angle. [0003] In the related art, when the driver's head attitude angle is detected, firstly, computer vision technology is used to detect the key points of the face on the image containing the detected driver's face to obtain the key points of the face, and the...

AI Technical Summary

Problems solved by technology

[0004] However, using the above method relies too much on the positioning accuracy of key points. For example, when turning the head or bowing the head significantly, the key points are prone to drift, and inaccurate key point detection will seriously affect the detection accuracy of the head attitude angle, especially When the driver wears a mask, the accuracy of key point detection may be low or even impossible to detect key points, resulting in the near failure of head attitude angle detection

Images