Motion Fatigue State Detection Based on Neural Networks.

Hu Li,Yabo Wang,Yao Nan,Akshi Kumar

doi:10.1155/2022/9602631

Hu Li, Yabo Wang + Show 2 more

Open Access

https://doi.org/10.1155/2022/9602631

Copy DOI

Abstract

Aiming at the problem of fatigue state detection at the back of sports, a cascade deep learning detection system structure is designed, and a convolutional neural network fatigue state detection model based on multiscale pooling is proposed. Firstly, face detection is carried out by a deep learning model MTCNN to extract eye and mouth regions. Aiming at the problem of eye and mouth state representation and recognition, a multiscale pooling model (MSP) based on RESNET is proposed to train the eye and mouth state. In real-time detection, the state of the eye and mouth region is recognized through the trained convolution neural network model. Finally, the athlete's fatigue is determined based on PERCLOS and the proposed mouth opening and closing frequency (FOM). The experimental results show that in the training process, we set the batch_size = 100 and the initial learning rate = 0.01. When the evaluation index is no longer improved, the learning rate is reduced by 10 times to 0.001, and a total of 50 epochs are trained. The precision and recall of the system are high. Compared with the infrared image simulating the night state, the RGB image taken by the ordinary camera in the daytime has higher precision and recall. It is proven that the neural network has high detection accuracy, meets the real-time requirements, and has high robustness in complex environments.

Highlights

Machine learning is the general name of a class of algorithms
Xintong and others used the AdaBoost algorithm for face detection, combined with the prior knowledge such as the geometric proportion of facial features to locate the coordinates of eyes and mouth, used the gray-scale integral projection method to extract the opening of eyes and the roundness of mouth as fatigue features, and determined fatigue according to the PERCLOS principle [13]
Experimental Results and Analysis is paper constructs a neural network model based on the deep learning framework and uses the framework of multithreaded input data provided by tensor flow to combine the training data and disrupt the data order, which can improve the efficiency of model training

Summary

Introduction

Machine learning is the general name of a class of algorithms It automatically analyzes a large amount of data to obtain new knowledge, accumulate experience, make it continuously improve its own performance, and use these laws to identify existing data for prediction or classification. Support vector machine (SVM) algorithm is used to classify the manually extracted feature vectors so as to identify the eye state. Using neural network algorithms for face detection and keypoint location, constructing convolution neural network to automatically extract athletes’ fatigue features, classify and recognize them, and so on. E other is to automatically extract the fatigue characteristics of athletes by using convolutional neural networks and construct two convolutional neural network models to perform classification tasks for eye and mouth states, respectively, that is, open or closed states [2] Using neural network algorithms for face detection and keypoint location, constructing convolution neural network to automatically extract athletes’ fatigue features, classify and recognize them, and so on. e other is to automatically extract the fatigue characteristics of athletes by using convolutional neural networks and construct two convolutional neural network models to perform classification tasks for eye and mouth states, respectively, that is, open or closed states [2]

Methods

Results

Conclusion