RETRACTED: Online position recognition and correction method for sports athletes

Wu, Di

doi:10.1016/j.cogsys.2018.07.002

Cited by 14 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The specific process is as follows: first, the training set is forwarded through the neural network, and at the end, one layer gets the output value of the network, then calculates the difference between it and the true value, and propagates the error layer by layer from the last layer to the input layer. In the process of propagating errors, the parameters of this layer can be based on the previous layer, the propagated error is adjusted, and this process is repeated until the error converges to the minimum [ 9 ].…”

Section: Deep Learning and Improved Hmm Training Algorithmmentioning

confidence: 99%

Deep Learning and Improved HMM Training Algorithm and Its Analysis in Facial Expression Recognition of Sports Athletes

Bai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Facial expressions are an auxiliary embodiment of information conveyed in the communication between people. Facial expressions can not only convey the semantic information that people want to express but also convey the emotional state of the speaker at the same time. But for sports athletes in training and competitions, it is usually not convenient to communicate directly. This paper is based on deep learning and an improved HMM training algorithm to study the facial expression recognition of sports athletes. It proposes the construction of deep learning of multilayer neural network, and the rank algorithm is introduced to carry out face recognition experiments with traditional HMM and class-specific HMM methods. The experimental results show that, with the increase of rank value, the class-specific recognition rate is up to 90%, the detection rate is 98% and the time-consuming is 2.5 min, which is better than HMM overall.

show abstract

Section: Deep Learning and Improved Hmm Training Algorithmmentioning

confidence: 99%

Deep Learning and Improved HMM Training Algorithm and Its Analysis in Facial Expression Recognition of Sports Athletes

Bai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The HOG descriptor was first proposed by French researcher Dalal at the CVPR2005 conference and has achieved good results in pedestrian detection [ 19 ]. HOG can be applied to the feature extraction of RGB images and depth images.…”

Section: Human Feature Recognition Based On Deep Learningmentioning

confidence: 99%

Recognition of Human Body Feature Changes in Sports Health Based on Deep Learning

Jiao

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

With the rapid development of social economy and the extensive and in-depth development of national fitness activities, national physical fitness monitoring and research work has achieved rapid development. In recent years, the application of deep learning technology has also achieved research breakthroughs in the field of computer vision. How deep learning technology can effectively capture motion information in sample data and use it to realize the recognition and classification of human actions is currently a research hot spot. Today’s popularization of various shooting devices such as mobile phones and portable action cameras has contributed to the vigorous growth of image data. Therefore, through computer vision technology, image data is widely used in practical application scenarios of human feature recognition. This paper proposes a deep learning network based on the recognition of human body feature changes in sports, improves the recognition method, and compares the recognition accuracy with the original method. The experimental results of this paper show that the result of this paper is 1.68% higher than the original recognition method, the accuracy rate of the improved motion history image is increased by 14.8%, and the overall recognition rate is higher. It can be seen from the above experimental results that this method has achieved good results in human body action recognition.

show abstract

“…Aiming at the problem that athletes' wrong posture cannot be detected and corrected in real time, a position recognition and correction method of swimmers based on depth image bone tracking is proposed, and the image is preprocessed by threshold method. Kalian filter is used to filter the collected image, and surf method is used to filter the edge points and action feature points with low brightness [8]. Pheasant pointed out that subacromial impact is a common condition for high-altitude athletes.…”

Section: Introductionmentioning

confidence: 99%

Application of Virtual Reality Based on Computer Vision in Sports Posture Correction

Zhu

Shao

Zhang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In recent years, with the rise of virtual and sports, people are often injured due to irregular movements during exercise. Based on this, this article takes the basic concept of computer virtual reality as the starting point and analyzes the adoption of computer virtual reality in sports correction. The choice of corrective exercises depends on the daily wrong exercises. If there is an error in any operation, please select the corresponding operation mode for the error operation for corrective training. If there are multiple errors at the same time, we compare and select the error operation that needs to be resolved first and the error operation that needs to be resolved later. In our daily life, the squat action pattern of Tai Chi Half-squat stance ball is closely related to us, and its action pattern can fully reflect the core stability of the subject. In this study, 42 students were selected as the students of a college sports college in Dalian. There are 7 people in each group, divided into 6 groups. The first three groups used exercise correction to assist the traditional teaching method (experimental group). It was found that the performance error rate of the first three groups reached 65%, and the last three groups used the assisted virtual reality teaching method, and the error rate was only 4%. Therefore, we adopted the teaching of virtual reality can reduce the error rate of the movement posture. We trained them for half a year and assessed and scored them once a month. We collect this data and analyze it to reach a conclusion. The experimental results prove that the experimental group has a significant difference before and after the squat test ( P < 0.05 ), and postexperiment there is a remarkable disparity among the experimental group and the comparison group ( P < 0.05 ). Therefore, squatting correction training is effective in improving the wrong squat. It is very effective for problems such as posture movement mode and joint limitation. Therefore, it is a very meaningful thing to explore the exercise correction training based on the virtual reality of computer vision.

show abstract

RETRACTED: Online position recognition and correction method for sports athletes

Cited by 14 publications

References 9 publications

Deep Learning and Improved HMM Training Algorithm and Its Analysis in Facial Expression Recognition of Sports Athletes

Deep Learning and Improved HMM Training Algorithm and Its Analysis in Facial Expression Recognition of Sports Athletes

Recognition of Human Body Feature Changes in Sports Health Based on Deep Learning

Application of Virtual Reality Based on Computer Vision in Sports Posture Correction

Contact Info

Product

Resources

About