Concentration degree analysis method and device, electronic equipment and computer storage medium

Abstract

The invention relates to an artificial intelligence technology, and discloses a concentration degree analysis method, which comprises the steps of obtaining a to-be-detected image, and performing facedetection on the to-be-detected image by utilizing a face detection network to obtain an initial detection image; performing head detection on the initial detection image by using a pre-trained headdetection model to obtain a detection result graph; cutting the to-be-detected image according to the detection result graph to obtain a plurality of head region graphs; analyzing the plurality of head region graphs by using a pre-trained head posture estimation network to obtain a plurality of head posture angles; and calculating and outputting concentration scores of the plurality of head attitude angles according to a preset score formula. The invention further provides a concentration degree analysis device and equipment and a computer readable storage medium. In addition, the invention also relates to a blockchain technology, and the to-be-detected image can be stored in the blockchain node. According to the method, the accuracy of concentration analysis can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a concentration analysis method, device, electronic equipment and computer-readable storage medium. Background technique [0002] A meeting is an important way to discuss and deal with affairs. It requires all participants to be highly focused to achieve results. There are many participants, and it is necessary to identify and analyze the concentration of the participants. [0003] At present, there are two main ways to identify personnel concentration: one is to calculate the face attitude angle (pitch angle) based on 2D image face key points to determine personnel concentration; the other is to calculate based on 3D face reconstruction Face posture angle to determine the concentration of personnel. However, the first method relies too much on face detection. When the face pose angle is large and the face is occluded, it is easy to fail to detect the fac...

AI Technical Summary

Problems solved by technology

However, the first method relies too much on face detection. When the face pose angle is large and the face is occluded, it is easy to fail to detect the face. The attitude angle of the face is inaccurate, and the concentration of the person cannot be correctly analyzed; the second method will introduce errors in the process of reconstructing the 3D face at a large attitude angle, resulting in low detection accuracy

Images