Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Fu, Ming; Zhong, Qun; Dong, Jixue

doi:10.1155/2022/4887470

Cited by 10 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visual modalities such as RGB and depth are included in these co-learning techniques. Fu et al [16] presented an algorithm to detect sports actions using deep learning methods, specifically the algorithm of clustering extraction. Athletic movements were first detected from deep learning techniques and then fused with sports-centered movements.…”

Section: Literature Reviewmentioning

confidence: 99%

HybridHR-Net: Action Recognition in Video Sequences Using Optimal Deep Learning Fusion Assisted Framework

Naeem Akbar,

Khan,

Umar Farooq

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The combination of spatiotemporal videos and essential features can improve the performance of human action recognition (HAR); however, the individual type of features usually degrades the performance due to similar actions and complex backgrounds. The deep convolutional neural network has improved performance in recent years for several computer vision applications due to its spatial information. This article proposes a new framework called for video surveillance human action recognition dubbed HybridHR-Net. On a few selected datasets, deep transfer learning is used to pre-trained the EfficientNet-b0 deep learning model. Bayesian optimization is employed for the tuning of hyperparameters of the fine-tuned deep model. Instead of fully connected layer features, we considered the average pooling layer features and performed two feature selection techniques-an improved artificial bee colony and an entropy-based approach. Using a serial nature technique, the features that were selected are combined into a single vector, and then the results are categorized by machine learning classifiers. Five publically accessible datasets have been utilized for the experimental approach and obtained notable accuracy of 97%, 98.7%, 100%, 99.7%, and 96.8%, respectively. Additionally, a comparison of the proposed framework with contemporary methods is done to demonstrate the increase in accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

HybridHR-Net: Action Recognition in Video Sequences Using Optimal Deep Learning Fusion Assisted Framework

Naeem Akbar,

Khan,

Umar Farooq

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…This module can realize the rapid import and export of large amounts of data, providing support for the convenience of system data maintenance, the accuracy of decision-making, and the extensive application. The system also includes some other useful functions, including a calculation module for factor determination, cognitive level assessment and expert utilization, and a screen capture module [ 25 ].…”

Section: System Requirements Analysis and Overall Designmentioning

confidence: 99%

Engineering Education Understanding Expert Decision System Research and Application

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Engineering education is based on technical science and aims at training engineers who can transform science and technology into productive forces. In recent years, due to the emergence of new technology revolution, engineering science and production technology have achieved new development, and higher engineering education is also facing new challenges. Engineering education is to cultivate talents in an international environment and update the traditional engineer training model from the aspects of educational philosophy, mode, goal, approach, and means. The author believes that in the process of exploring the new talent training model, we must first change the educational concept and correctly understand and deal with various relationships in engineering education. To solve various decision-making problems in engineering construction, this study introduces the concept of engineering education certification under the background of new infrastructure and engineering education certification, analyzes the current situation and existing problems of engineering education understanding in recent years, and carries out reform and exploration from different aspects. The achievements in engineering education are analyzed. The engineering education project is analyzed and researched using the engineering decision-making scheme. It can be seen from the experimental analysis that the method has a good effect.

show abstract

“…In addition to action recognition, posture estimation algorithms are utilized to determine the spatial orientation and configuration of a person's body within an image or video frame [1]. These algorithms aim to accurately localize key body joints or keypoints, such as the shoulders, elbows, and knees, and estimate the pose or posture based on the relative positions of these keypoints [2].…”

Section: Introductionmentioning

confidence: 99%

Athletes' Action Recognition and Posture Estimation Algorithm Based on Image Processing Technology

Cheng

2024

jes

View full text Add to dashboard Cite

A posture estimation algorithm based on image processing technology involves analyzing images or video frames to determine the position and orientation of human bodies or specific body parts. This process typically begins with detecting key points or landmarks on the body, such as joints or anatomical features. This paper presents a novel approach for athletes' action recognition and posture estimation using image processing technology, specifically focusing on the Contour Mapping Multivariant Recognition and Estimation (CMMRE) algorithm. The primary objective is to develop a robust system capable of accurately identifying human actions and estimating postures from visual data, with potential applications in sports analysis, surveillance, and human-computer interaction. The CMMRE algorithm employs advanced techniques for contour mapping, feature extraction, and prediction, leveraging deep learning methodologies to analyze and interpret visual information effectively. Through a series of experiments and simulations, the algorithm's performance is evaluated, showcasing its ability to achieve high accuracy in action recognition tasks across various scenarios. The results highlight the algorithm's strengths in accurately predicting actions and estimating postures, while also identifying areas for improvement. The algorithm achieved an average accuracy of 95% in recognizing walking and running actions, and 80% in identifying jumping actions. The results highlight the algorithm's strengths in accurately predicting actions and estimating postures, while also identifying areas for improvement.

show abstract

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Cited by 10 publications

References 29 publications

HybridHR-Net: Action Recognition in Video Sequences Using Optimal Deep Learning Fusion Assisted Framework

HybridHR-Net: Action Recognition in Video Sequences Using Optimal Deep Learning Fusion Assisted Framework

Engineering Education Understanding Expert Decision System Research and Application

Athletes' Action Recognition and Posture Estimation Algorithm Based on Image Processing Technology

Contact Info

Product

Resources

About