Deep learning-based visual algorithms for identity and action recognition in engineering practical courses

Engineering practice is an important component of engineering education. In this teaching scenario, students are frequently moving around, making the identification of their identities and actions using computer vision methods a prominent and ongoing research challenge. This is a challenge for AI-based identity recognition algorithms. Some facial recognition algorithms and person re-identification algorithms have attempted to solve the problem of identity recognition, but they all face difficulties in recognizing angles and low recognition accuracy. Some action recognition algorithms, such as the optical flow estimation, still face characteristics such as a lack of practical teaching scenarios, a lack of action training sets, complex networks, and complex operations. This paper introduces an identity recognition algorithm based on facial recognition algorithm and person re-identification algorithm, which improves the accuracy and effectiveness of recognition by introducing dynamic feature caching. And based on the target classification algorithm of torso and limb recognition, achieve action recognition. Finally, we validated the effectiveness and accuracy of the algorithm in practical engineering courses and conducted comparative experimental analysis.