Deep learning in sport video analysis: a review

Rangasamy, K S; As’ari, Muhammad Amir; Rahmad, Nur Azmina; Ghazali, Nurul Fathiah; Ismail, Saharudin

doi:10.12928/telkomnika.v18i4.14730

Cited by 32 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Liu G et al concluded by studying deep learning in real-time analysis of basketball sports data that, in today's big data era, a team's completeness, accuracy, and systematization of data collection in basketball games and the results of its analysis will not only make the management mode of basketball data change, but also indirectly affect the level to which basketball games will develop in the future [10]. erefore, the current basketball tournament should first establish the awareness of information technology data management, apply relevant data collection and analysis software, and perfect a data query platform to provide new momentum for the development of basketball [11].…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Real‐Time Analysis of Basketball Sports Data Based on Deep Learning

Peng

2021

Complexity

View full text Add to dashboard Cite

This paper focuses on the theme of the application of deep learning in the field of basketball sports, using research methods such as literature research, video analysis, comparative research, and mathematical statistics to explore deep learning in real-time analysis of basketball sports data. The basketball posture action recognition and analysis system proposed for basketball movement is composed of two parts serially. The first part is based on the bottom-up posture estimation method to locate the joint points and is used to extract the posture sequence of the target in the video. The second part is the analysis and research of the action recognition algorithm based on the convolution of the space-time graph. According to the extracted posture sequence, the basketball action of the set classification is recognized. In order to obtain more accurate and three-dimensional information, a multitraining target method can be used in training; that is, multiple indicators can be detected and feedback is provided at the same time to correct player errors in time; the other is an auxiliary method, which is compared with ordinary training. The method can actively correct technical movements, train players to form muscle memory, and improve their abilities. Through the research of this article, it provides a theoretical basis for promoting the application of deep learning in the field of basketball and also provides a theoretical reference for the wider application of deep learning in the field of sports. At the same time, the designed real-time analysis system of basketball data also provides more actual reference values for coaches and athletes.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Real‐Time Analysis of Basketball Sports Data Based on Deep Learning

Peng

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…In another recent study performed at our institution, we found a negative correlation between resuscitation time and patient severity of injury, implying that more severely injured patients were resuscitated faster than less severely injured patients [ 19 ]. Moreover, Spanjersberg and colleagues [ 20 ] discovered comparable results, with resuscitation times of severely injured patients (Revised Trauma Score (RTS) of < 12) being shorter (35 minutes) than less severely injured patients (RTS 12; 46 minutes). This may imply that the influence of an on-site trauma surgeon during trauma resuscitation on resuscitation time may even be underestimated.…”

Section: Discussionmentioning

confidence: 99%

The effect of an on-site trauma surgeon during resuscitations of severely injured patients

2022

View full text Add to dashboard Cite

Background Although the timely involvement of trauma surgeons is widely accepted as standard care in a trauma center, there is an ongoing debate regarding the value of an on-site attending trauma surgeon compared to an on-call trauma surgeon. The aim of this study was to evaluate the effect of introducing an on-site trauma surgeons and the effect of their presence on the adherence to Advanced Trauma Life Support (ATLS) related tasks and resuscitation pace in the trauma bay. Methods The resuscitations of severely injured (ISS > 15) trauma patients 1 month before and 1 month after the introduction of an on-site trauma surgeon were assessed using video analysis. The primary outcome was total resuscitation time. Second, time from trauma bay admission until tasks were performed, and ATLS adherence were assessed. Results Fifty-eight videos of resuscitations have been analyzed. After the introduction of an on-site trauma surgeon, the mean total resuscitation time was 259 seconds shorter (p = 0.03) and seven ATLS related tasks (breathing assessment, first and second IV access, EKG monitoring and abdominal, pelvic, and long bone examination; were performed significantly earlier during trauma resuscitation (p ≤ 0.05). Further, we found a significant enhancement to the adherence of six ATLS related tasks (Airway assessment, application of a rigid collar, IV access; EKG monitoring, log roll, and pronouncing results of arterial blood gas analysis; p-value ≤0.05). Conclusion Having a trauma surgeon on-site during trauma resuscitations of severely injured patients resulted in improved processes in the trauma bay. This demonstrates the need of direct involvement of trauma surgeons in institutions treating severely injured patients.

show abstract

“…Thus, deep learning methods have been reported in recent years [28,29]. Deep learning is based on a neural network, which is a system that imitates the mechanism of human nerve cells [30].…”

Section: Related Workmentioning

confidence: 99%

“…Sensors 2022, 22, x FOR PEER REVIEW 3 of 15 high-dimensional and contain noise; thus, learning is ineffective in many cases with such machine learning methods [27]. Thus, deep learning methods have been reported in recent years [28,29]. Deep learning is based on a neural network, which is a system that imitates the mechanism of human nerve cells [30].…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Myoelectric Potential Estimation Method for Wheelchair Operation

Aihara

Shibata

Mizukami

et al. 2022

Sensors

View full text Add to dashboard Cite

Wheelchair sports are recognized as an international sport, and research and support are being promoted to increase the competitiveness of wheelchair sports. For example, an electromyogram can observe muscle activity. However, it is generally used under controlled conditions due to the complexity of preparing the measurement equipment and the movement restrictions imposed by cables and measurement equipment. It is difficult to perform measurements in actual competition environments. Therefore, in this study, we developed a method to estimate myoelectric potential that can be used in competitive environments and does not limit physical movement. We developed a deep learning model that outputs surface myoelectric potentials by inputting camera images of wheelchair movements and the measured values of inertial sensors installed on wheelchairs. For seven subjects, we estimated the myoelectric potential during chair work, which is important in wheelchair sports. As a result of creating an in-subject model and comparing the estimated myoelectric potential with the myoelectric potential measured by an electromyogram, we confirmed a correlation (correlation coefficient 0.5 or greater at a significance level of 0.1%). Since this method can estimate the myoelectric potential without limiting the movement of the body, it is considered that it can be applied to the performance evaluation of wheelchair sports.

show abstract

Deep learning in sport video analysis: a review

Cited by 32 publications

References 40 publications

[Retracted] Real‐Time Analysis of Basketball Sports Data Based on Deep Learning

[Retracted] Real‐Time Analysis of Basketball Sports Data Based on Deep Learning

The effect of an on-site trauma surgeon during resuscitations of severely injured patients

Deep Learning-Based Myoelectric Potential Estimation Method for Wheelchair Operation

Contact Info

Product

Resources

About