Non-contact learning state monitoring system and learning state detection method

Abstract

The invention discloses a non-contact learning state monitoring system and a learning state detection method. The monitoring system comprises a data acquisition module, a feature detection module anda visual interface module. The detection method comprises the following steps: carrying out face detection through image processing, and identifying and storing face key point data; obtaining a head posture through calculation according to point pairs of a plurality of spatial 3D points and image 2D points and the existing head 3D model, calculating the aspect ratio of eyes and the mouth through existing face key point data, carrying out blinking and yawing detection, determining a face region of interest according to face key points, and carrying out real-time heart rate estimation accordingto the principle of photoplethysmography. According to the invention, interference on learners is small, and real-time performance is good; the ground fatigue degree and attention degree of the learner can be accurately described; a convenient way is provided for a manager and learners to know the current learning condition, and the problem of monitoring and feedback of the learning state of the learners in the learning support service system is solved.

Description

technical field [0001] The invention relates to the field of online learning support services and emotional computing, in particular to a non-contact learning state monitoring system and a non-contact learning state detection method. Background technique [0002] Since the establishment of Massive Open Online Courses (MOOCs) by many top universities in the United States in 2012, online learning platforms have developed vigorously. Since then, the rise of the three major course providers, Coursera, Udacity, and edX, has injected many free and excellent courses into the development of online learning platforms. This makes higher education accessible only to top schools, freeing learning from the constraints of geography, time, and identity. But today, there is still a lack of a mature MOOC learning support service system to meet the needs of learners, teachers and administrators. Therefore, the monitoring and feedback of learners' learning status in the construction of learn...

AI Technical Summary

Problems solved by technology

However, the current research only uses traditional knowledge (such as contour rules, symmetry rules, etc.) and geometric features (such as YCbCr, feature points, etc.) to capture the learner's face. The influence of the learner's body posture cannot meet the needs of real-time monitoring

Images