Sports Video Research Articles

A real-time basketball referee gesture recognition system based on multi-scale spatio-temporal features

Abstract In this paper, the multi-scale spatio-temporal convolution module and the channel attention mechanism of global information synchronization have excellent performance in the field of sports gesture action recognition; therefore, combining the multi-scale spatio-temporal convolution and the channel attention mechanism to construct the dynamic gesture recognition model. The trained, dynamic gesture recognition model is deployed to cell phones and web pages through Java computational programming language, and the application scenarios of the basketball referee gesture recognition system are explained in detail. The real-time basketball referee gesture recognition system processes are analyzed using simulation analysis after determining the dataset. The basketball referee gesture recognition system’s video cropping frame analysis has an accuracy of 87.64% and 71.25%, with a loss value of 6.24 and 5.59, as shown in the results. When compared to the single-resolution features on the basketball referee gesture recognition system, the fused features exhibit some improvement, and the average recognition rate is 92.20%. This study is applicable to the referee gesture tracking method in complex basketball sports scenarios and lays the foundation for higher semantic level research in the field of sports video analytics, such as action recognition, event detection, and content understanding.

Retracted: Combining AI Techniques for Recognizing Aerobics Sport Videos.

[This retracts the article DOI: 10.1155/2022/2293122.].

Learning group interaction for sports video understanding from a perspective of athlete

Learning group interaction for sports video understanding from a perspective of athlete

Sports video summarization using acoustic symmetric ternary codes and SVM

Broadcasters produce and transmit a vast number of sports videos in cyberspace due to immense viewership and potential commercial benefits. The analysis and processing of such a huge amount of video content are very challenging. This situation demands the development of effective and efficient summarization methods to manage the massive sports video repository while keeping the viewer’s interest along with potential storage and transmission benefits. This paper presents an automated summarization framework based on excitement detection for sports videos i.e., cricket, soccer, etc. The audio stream of the sports video is analyzed to capture the significant events that are then used to produce the concise video. For effective representation of audio signals, we proposed an acoustic feature descriptor symmetric ternary codes and used them to train a binary Support Vector Machine classifier for excitement detection. Each audio frame is labeled as either an excited audio frame or a non-excited audio frame. The video frames corresponding to the excited audio frames represent the key-events in the sports videos and are marked as the key-frames. Each key-frame is appended with the neighboring frames to produce video skims for each key-event based on the user’s required summary length. Finally, these video skims are sequentially arranged to produce the user-driven video summary. We evaluated our highlights generation method on our own diverse YouTube dataset of cricket and soccer videos, and a largescale SoccerNet corpus of soccer videos. The average accuracy of 97.7% and 91.23% on both datasets confirms the reliability of our method in terms of key-event detection for sports highlight generation.

Adherence and perceptions of a home sports video gaming program in persons with spinal cord injuries: A pilot study

Objective Sports video-gaming can facilitate increased activity levels in persons with limited exercise options. Understanding how persons with spinal cord injuries (SCI) participate in home-based video-gaming and its potential impact on maintaining or enhancing physical function remains largely unexplored. The purpose of this study was to evaluate adherence, perceptions, and potential physical effects of a home sports video-game program for persons with chronic SCI. Participants Fourteen individuals with chronic SCI (9 tetraplegia, 5 paraplegia). Design This was a prospective study. Wii video-gaming systems that included four sports games were provided to participants for home use. Participants were instructed to play for 8 weeks 3–4 days/week. The video consoles recorded the time and number of sessions played. Outcome measures At baseline and at the conclusion of the program, measurements were made of upper extremity strength, perceived exertion, active heart rate, pain, balance, and a functional upper extremity (UE) test. The total time and number of sessions were compared to the prescribed game play as a measure of adherence. Scores from a self-reported survey were used to gauge participants’ satisfaction and perceptions of their gaming experience. Results Overall mean gaming adherence was 85% during the first 4 weeks and 69% for the second 4 weeks. There were no significant changes in upper extremity strength, active heart rate, balance, pain, or functional UE test for either group. All of the participants rated video gaming as enjoyable and 85.7% perceived that it could be used as a form of exercise. Conclusion The Wii sports home video-gaming intervention elicited overall high adherence rates and was well received by study participants indicating that it may have value as an adjunctive tool for increasing physical activity for individuals with SCI.

Augmented reality experience: An examination of viewer responses to sports videos

AbstractAugmented reality (AR) offers a transforming user experience and has been increasingly integrated into entertainment and service contexts. Drawing on experience economy theory and employing a mixed‐methods approach, this research evaluates the antecedents and consequences of four realms of viewer experiences: entertainment, educational, aesthetic, and escapist experiences, in AR‐infused sports videos. A qualitative study of semi‐structured interviews highlights three critical AR features in sports videos (i.e., novelty, vividness, and informativeness) in shaping viewer experiences. Subsequently, a research model is formulated to elucidate the relationships among AR features, four realms of viewer experiences, and behavioral intentions. A quantitative analysis based on survey data reveals that AR features exert varying effects on viewers' entertainment, educational, and aesthetic experiences, yet none significantly affects escapist experience, which is relatively trivial in viewers' overall experience. Entertainment, educational, aesthetic, and escapist experiences have various influences on viewers' intentions to watch again, to recommend, and to pay, except that entertainment and educational experiences do not significantly affect intention to pay. This research stresses the importance of understanding multiple aspects of user experiences in AR research and provides useful guidelines for AR features and viewer experience design in sports videos.

The Birth and Development of Sports Video Games From the 1950s to the Early 1980s

This article provides an overview of the origins and early development of sports video games. The first generation of sports video games were developed by scientists in laboratories for academic purposes. Together with the rise of microcomputers and the widespread adoption of television (TV) sets, commercial video games began to emerge in the early 1970s. Like their laboratory predecessors, most of the first-generation commercial games were sports-themed and primarily designed as a platform for competition between players. In the second half of the 1970s, ball-and-paddle-based games began to be replaced by more sophisticated games adopting the rules and actions of real-life sports. By the late 1970s and early 1980s, intense competition between video game companies gave birth to many innovative titles, with various sports disciplines adapted into games. Most of the sports games created in this period were based on competitive sports including American football, basketball, baseball, soccer, and tennis, as well as recreational sports like bowling, pool, and darts, many of them long popular in Western Europe and North America, some with a huge fan base in Japan. They were clearly produced to cater to the needs of gamers and sports fans in the world’s three major TV, personal computer, video game, and sports markets at the time.

Video Shot Boundary Detection and Sports Video Classification Algorithm Based on Particle Filter

INTRODUCTION: Sports video is a very important information resource. The classification of sports video with high accuracy can effectively improve the browsing and query effect of users. This project intends to study a motion video classification algorithm based on deep learning particle filter to solve the problems of strong subjectivity and low accuracy of existing motion video classification algorithms. A key box extraction method based on similarity is proposed. The moving video classification algorithm based on deep learning coding model is studied. Examples of various types of sports videos are analyzed. The overall performance of the motion video classification algorithm proposed in this paper is much better than other existing motion video classification algorithms. This algorithm can greatly improve the classification performance of motion video.

Sports Video Object Tracking Algorithm Based on Optimized Particle Filter

INTRODUCTION: Particle filter based human motion video target tracking technology has become a trend. This project intends to apply particle filters to image processing of human activities. Firstly, an improved particle filter model is used to track moving video objects. The purpose is to further improve the tracking effect and increase the tracking accuracy. HSV distribution model was used to establish target observation model. The algorithm is combined with the weight reduction algorithm to realize the human motion trajectory detection in the target observation mode. The model was then confirmed by an examination of sports player videos. Experiments show that this method can be used to track people in moving images of sports. Compared with other methods, this method has higher computational accuracy and speed.

Effects of Virtual Reality Pilates Training on Duration of Posture Maintenance and Flow in Young, Healthy Individuals: Randomized Crossover Trial.

This study explored the use of virtual reality (VR) technology to enhance the effectiveness and duration of low-intensity movements and postures in Pilates-derived exercises. We postulate that by leveraging the flow state in VR, individuals can engage in these exercises for longer periods while maintaining a high level of flow. The purpose of this study was to compare differences in posture maintenance and flow between VR Pilates training and conventional Pilates training, and the correlation between the 2 factors. The 18 participants in each group received either VR training or conventional training and were switched to the other training type after a 2-day wash-out period. Each group performed Pilates movements in a VR environment and a conventional environment, divided into 4 types. After training sessions, participants were evaluated for flow using a self-report questionnaire. In addition, a sports video analysis program was used to measure the duration of posture maintenance in 2 video-recorded sessions. Repeated-measures ANOVA and correlation analysis were performed on the measured duration of posture maintenance and flow scores. In all cases, the statistical significance level was set at P<.05. Results for the duration of posture maintenance verification by type showed that simple behavior (F1,16=17.631; P<.001), upper body-arm coordination behavior (F1,16=6.083; P=.04), upper body-leg coordination behavior (F1,16=8.359; P<.001), and whole-body coordination behavior (F1,16=8.426; P<.001) all showed an interaction effect at P<.05. Flow (F1,16=15.250; P<.001) also showed an interaction effect. In addition, significant correlations were determined between duration of all types of posture maintenance and flow in the VR training group at P<.05. Our results indicate that VR Pilates training may be more useful than conventional Pilates training in improving the duration of posture maintenance and that it promotes a significantly higher degree of flow when compared with conventional Pilates training.

Sports video retrieval and classification using focus u-net based squeeze excitation and residual mapping deep learning model

Sports videos are widely used by athletes and coaches for training and match analysis purposes outside the mainstream audience. Sports videos should be effectively classified into different genres to easily retrieve and index them from large video datasets. Manual labelling classification methods may cause errors and have low accuracy. Classification based on video content analysis is challenging for computer vision-based techniques. This work introduces an improved focus-net deep learning (DL) model called the Convolutional squeeze U-Net based encoder-decoder for sports video retrieval and classification. First, the keyframes are extracted from the input sports video using a clustering and optical flow analysis method. In the next stage, the frames are pre-processed using a smoothed shock filtering technique to remove the noise. The process of image segmentation is carried out using a Convolutional squeeze U-Net based encoder-decoder model. Finally, the sports video can be classified using the softmax classifier. A CNN (convolutional neural network) is utilized at the encoder section for extracting the features and fed to the decoder for video classification. The experiments are performed in the UCF101 dataset, and the proposed model achieved an overall accuracy of 99.68%. Hence, it is proven that the proposed focus-net model can be efficiently utilized in sports video classification.

The effect of acute high-intensity interval training and Tabata training on inhibitory control and cortical activation in young adults.

Physical exercise not only benefits peoples' health, but also improves their cognitive function. Although growing evidence suggests that high-intensity interval training (HIIT) is a time-efficient exercise regime that can improve inhibitory control performance by enhancing cortical activation in the prefrontal cortex, less is known about how Tabata training, a subset of HIIT that requires no equipment or facilities to perform, affects inhibitory control and cortical activation in young adults. Therefore, we aimed to reveal the effect of an acute bout of HIIT and Tabata training on inhibitory control and attempted to identify its potential neural substrates. Forty-two young adults (mean age: 19.36 ± 1.36 years; 21 females) performed the Stroop task and Simon task before and after acute HIIT, Tabata training, or a control session, and cortical hemodynamic changes in the prefrontal area were monitored by functional near-infrared spectroscopy (fNIRS) during the tasks. Both HIIT and Tabata interventions lasted for a total of 12 min. The HIIT participants performed ergometer cycling at their 80% maximal aerobic power at 90-100 rpm, and the Tabata participants performed a total of 8 intense activities, such as jumping jacks, high knees, and butt kickers, without using equipment or facilities, keeping the heart rate at 80-95% of their maximum heart rate. Participants in the control group watched a sport video while sedentary. Cognitive tasks data and fNIRS data were analyzed by repeated-measures three-way ANOVA. Our results indicated that both the HIIT and Tabata groups exhibited reduced reaction times after the intervention, and there were alterations in activation patterns in the dorsolateral and ventrolateral prefrontal cortices.

OTRN-DCN: An optimized transformer-based residual network with deep convolutional network for action recognition and multi-object tracking of adaptive segmentation using soccer sports video

In today’s era, video analysis is immensely involved in recognizing the sport-related movement that has become a significant part of human’s life. The intent of this approach is to know about the player’s activities with prior information of tracking objects. It also analyzes the player potential or capacity to lead the winning team. When the player frequently changes their location, object tracking and action recognition will become a quite challenging task. Over the game, various athletes or different objects are considered to assist the system to easily recognize the respective actions of the player. Most of the previous models have been implemented, yet, it faces such consequences to provide promising performance. To meet the pre-requisite, a new multi-athlete tracking model for action recognition in soccer sports is designed with deep learning approaches. Initially, the multi-object tracking video is offered as the input to pre-processing phase. Here, occlusion and background clutter removal and contrast enhancement techniques are utilized to perform pre-processing in the videos. Then, the pre-processed video is offered to the multi-object tracking phase, where the jersey number is observed during multi-object tracking to avoid the identity switch problem. Then, effective multi-object tracking is performed by adaptive YOLOv5. The parameters presented in the improved adaptive YOLOv5 are tuned by proposing a new algorithm as the Random-based Cheetah Red Deer Algorithm (RCRDA). Next, in the action recognition phase, the tracked object from the video is taken based on the Region of Interest (ROI) that is subjected to an action recognition model named Optimized Transformer-based Residual Network with Deep Convolutional Network (OTRN-DCN). At first, ROI is offered as the input to TRN for attaining the feature vectors. Then, the optimal weighted vector extraction is performed, where the weight is tuned by the developed RCRDA. Finally, the attained optimally weighted vectors are given to the DCN phase for attaining recognized action as output. Hence, the developed multi-object tracking and action recognition model will secure an improved recognition rate than the traditional framework.

Retracted: Deep Learning-Based Multitarget Motion Shadow Rejection and Accurate Tracking for Sports Video

Retracted: Deep Learning-Based Multitarget Motion Shadow Rejection and Accurate Tracking for Sports Video

Retracted: Semantic Analysis of Multimodal Sports Video Based on the Support Vector Machine and Mobile Edge Computing

Retracted: Semantic Analysis of Multimodal Sports Video Based on the Support Vector Machine and Mobile Edge Computing

The Meanings Behind Camera Movements of Live Sport Events

The development of technology has had a very extraordinary impact on human civilization, such as the example of the development of the digital era in the world of videography. The focus of this study is analyzing the structure constructed by the camera movement of sport live events. The authors used semiotic analysis in this study to describe the live sports video of the event. The author then relates to the meaning of the visual signs of several scenes in each video, in order to understand the phenomena being studied, such as behavior, perception, and action in the form of words. Using Roland Barthes’ analysis method, there are three meanings of visual messages in the camera movement sport live event, namely denotative, connotative, and mythical meanings.&#x0D; Keywords: structure, camera movement, sport live action

A novel multi-modal neural network approach for dynamic and generic sports video summarization

Video Summarization is a video compression/compaction technique to create a shorter yet informative version of original video. Video summarization has offered solutions to plenty of media, user and engineering applications. Though sports video summarization has been an active research topic for some time; there still exists a void for multi-modal, dynamic, generic and domain knowledge based approach for Cricket Sport video summarization. This paper presents a multi-modal video summarization approach to summarize Cricket sport videos. This work captures the domain knowledge acquired from multi-modal (audio-visual) cues. A dual neural network architecture pipeline is proposed to dynamically segment and dynamically summarize Cricket videos for generic target audience. The former Neural Network is grounded on Cricket bowling activity (visual feature) for dynamic video segmentation of Cricket videos. The segments are then forwarded to the latter Neural Network for identification of key segments. The key segment detection module relies on Audio analysis of Cricket video stream to identify exciting, content representative and informative segments as per Cricket domain. Experimental analysis on two novel proposed benchmark datasets, i.e. DPCS (Delivery Play Cricket Sport) image dataset and EXINP (Excited Interval Normal Play) Cricket Dataset (audio based) shows promising results. The results indicate that the proposed multi-modal approach generates exciting, content representative, informative, generic and dynamic summary incorporating domain knowledge of the sport.

A Four-Point Camera Calibration Method for Sport Videos

The main objective of camera calibration is to estimate the homography between a sports field template and the corresponding field in a video frame. State-of-the-art approaches exploit deep-learning technologies to achieve this aim. However, the lack of large training datasets leads to unreliable results. Search-based approaches deliver better accuracy but at the expense of a very high computational cost. In this paper, a four-point camera calibration method is proposed to address these challenges. It consists of four stages: first, a conditional generative adversarial network (cGAN) is used to generate meaningfully segmented video frames. This cGAN is a general image-to-image translation technique which has robust performance even for small training datasets. The aim is to eliminate foreground objects that greatly impede accurate estimation of four suitable points for the subsequent stage. Then, a regression network which can estimate four points from a single segmented video frame is introduced. In this stage we aim at keeping the low computational cost. In the next processing stage, the estimated four points and the original selected four points are used to calculate the homography. In this third stage a Direct Linear Transformation (DLT) algorithm is applied. In the last processing stage, the accuracy of the estimated homography is refined by running an Enhanced Correlation Coefficient (ECC) module. The proposed method is extensively evaluated using a standard 2014 World Cup dataset. The obtained results are compared to the state-of-the-art approaches and its variations based on U-net, VGG-16, ResNet-50. The obtained results show that the proposed method is superior in terms of accuracy and computational efficiency. To demonstrate the effectiveness and robustness of the proposed method, it is also validated on National Basketball, 2018 World Cup and cross dataset. In these diverse environments, the proposed method still maintains the competitive performance.

The effect of playing e-sports games on young people's desire to engage in physical activity: Mediating effects of social presence perception and virtual sports experience.

E-sports game experiences can help enhance young peoples' willingness to participate in sports and fitness. However, e-sports game studies have mostly focused on users' violent tendencies and aggressive behaviors, and less attention has been paid to the positive effects on young peoples' sports health. The purpose of this study is to provide reasonable guidance young people away from sedentary, addictive and other negative behaviors and to promote active sports and healthy exercise and development. Following the random sampling criteria, questionnaires were distributed to Chinese young people aged 14 to 24 through gaming communities as well as social media platforms, and 1608 valid questionnaires were obtained after eliminating invalid ones. The influence mechanism of e-sports game experience on young peoples' intention to participate in sports and fitness was examined empirically by using factor analysis and structural equation modeling. The e-gaming scenes (β = 0.399, p<0.01), virtual sports experience (β = 0.257, p<0.01), and social presence (β = 0.258 p<0.01) each had a significant positive effect on young peoples' intention to participate in sports and fitness; virtual sports experience [OR]0.099, 95%: CI 0.077-0.121 and social presence[OR]0.052, 95%: CI 0.035-0.071, were known to have mediating utility in the e-gaming scenario's influence on young peoples' intention to participate in sports and fitness. Using the significant features of sports video games such as entertainment and simulation to awaken the interest and willingness to participate in young people sports is an innovative way to accelerate the development of mass sports.

Emotional Cues and the Demand for Televised Sports: Evidence from the UEFA Champions League

This study provides first evidence on how belief dynamics are driving entertainment utility and consequently the demand for sports across markets by analyzing minute-by-minute audience data of UEFA Champions League (UCL) games televised in the UK and the Spanish market during a full (pre-COVID) cycle of broadcasting rights. Overall, we find that suspense and surprise are the main drivers of demand in both markets while shock only has marginal effects in the Spanish market. Interestingly, we find a combined impact of suspense and surprise in the UK market that is of similar magnitude as reported in a previous study for English Premier League matches in the UK. In the Spanish market, however, the combined impact is considerably larger.