Ball Tracking Research Articles

Fast moving table tennis ball tracking algorithm based on graph neural network

The key object tracking in sports video scenarios poses a pivotal challenge in the analysis of sports techniques and tactics. In table tennis, due to the small size and rapid motion of the ball, identifying and tracking the table tennis ball through video is a particularly arduous task, where the majority of existing detection and tracking algorithms struggle to meet the practical application requirements in real-world scenarios. To address this issue, this paper proposes a combined technical approach integrating detection and discrimination, tailored to the unique motion characteristics of table tennis. For the detector, we utilize and refine a common video differential detector. As for the discriminator, we introduce GMP (a Graph Max-message Pass Neural Network), which is designed specifically for tracking table tennis balls or similar objects. Furthermore, we enhance an existing dataset for table tennis tracking problems by enriching its scenarios. The results demonstrate that our proposed technical solution performs impressively on both the dataset and the intended real-world environments, showcasing the good scalability of our algorithms and models as well as their potential for application in other scenarios.

Investigating Acceleration and Deceleration Patterns in Elite Youth Football: The Interplay of Ball Possession and Tactical Behavior

The main objective of this study was (1) to analyze the patterns of acceleration (Ac) and deceleration (Dec) during football matches in elite youth football, both within and between different segments of the match; and (2) to investigate the impact of ball possession and various playing positions on these acceleration and deceleration patterns. To provide a broader explanatory context, the influence of tactical space management was assessed in terms of depth and width. A descriptive comparative design was used, and data were collected during two friendly matches. Player and ball tracking data were collected using a local positioning system. In the attack phase, differences were obtained in the average Ac (first half: 0.42 ± 0.06 m·s−2, second half: 0.38 ± 0.07 m·s−2; p = 0.021, d = 0.50) and average Dec (first half: −0.44 ± 0.09 m·s−2, second half: −0.36 ± 0.08 m·s−2; p = 0.001, d = 0.84). Wingers in the attack phase obtained higher values in maximum Ac (1.65 ± 0.65 m·s−2; p = 0.007, η2 = 0.03), and in the total number of both Ac (68.7 ± 45.22; p = 0.001, η2 = 0.10) and Dec (70.6 ± 45.70; p = 0.001, η2 = 0.10). In the defense phase, full-backs obtained higher values in average Ac (0.53 ± 0.17 m·s−2; p = 0.001, η2 = 0.07) and average Dec (−0.49 ± 0.18 m·s−2; p = 0.001, η2 = 0.05) and wingers in the total number of Ac (43.9 ± 27.30; p = 0.001, η2 = 0.11) and Dec (43.8 ± 28.60; p = 0.001, η2 = 0.10). In young football players, Ac and Dec do not follow a decreasing end throughout the match, and their behavior is uneven depending on ball possession and the position assigned to the player, with the highest demands on Ac/Dec in winger and full-back positions.

Defending technology: a normative defence of technologically assisted officiating in binary referee situations

ABSTRACT This article discusses how technological official aids influence sporting competitions in terms of fairness and flow. It addresses the main arguments against technological official aids used to assist refereeing in binary referee situations. First, I argue that the criticism directed at the use of ball tracking devices (‘reconstructed track devices’) is mainly unjustified and that these devices provide the opportunity to make refereeing in certain types of sport fairer. In this regard, I also argue that empirical findings about referees’ decision-making and potential biases must be considered when deciding how technological official aids influence the fairness of sporting competitions. Then I attempt to refute the argument that no situations are more decisive than others in sports with no fixed breaks, such as football. Finally, I scrutinise the argument that human fallibility in refereeing is somehow valuable in itself. Consequently, this article concludes that there are no convincing arguments against the use of technological official aids in binary referee situations.

Ball Tracking Based on Multiscale Feature Enhancement and Cooperative Trajectory Matching

Most existing object tracking research focuses on pedestrians and autonomous driving while ignoring sports scenes. When general object tracking models are used for ball tracking, there are often problems, such as detection omissions due to small object sizes and trajectory loss due to occlusion. To address these challenges, we propose a ball detection and tracking model called HMMATrack based on multiscale feature enhancement and multilevel collaborative matching to improve ball-tracking results from the entire process of sampling, feature extraction, detection, and tracking. It includes a Heuristic Compound Sampling Strategy to deal with tiny sizes and imbalanced data samples; an MNet-based detection module to improve the ball detection accuracy; and a multilevel cooperative matching and automatic trajectory correction tracking algorithm that can quickly and accurately correct the ball’s trajectory. We also hand-annotated SportsTrack, a ball-tracking dataset containing soccer, basketball, and volleyball scenes. Extensive experiments are conducted on the SportsTrack, demonstrating that our proposed HMMATrack model outperforms other representative state-of-the-art models in ball detection and tracking.

A review and reassessment of the aerodynamics of cricket ball swing

This paper reviews 70 years of cricket ball swing literature and reassesses the results in light of new measurements. A comparison of ball tracking data with published experimental results shows that current understanding does not explain the behaviour observed in professional cricket matches. Descriptions of cricket ball boundary layer aerodynamics are updated with new results which show that the seam acts more like a series of vortex generators than a trip and that there is a laminar separation bubble on the seam side of the ball. Previous results for reverse swing are consolidated and compared with new data, showing that different magnitudes of swing occur depending on the condition of both sides of the ball. Variation in pressure and temperature should be included when the Reynolds number, a non-dimensional ball speed, is calculated, while humidity can be neglected. Studies on the effect of wind speed and direction are summarised and results considering the effect of free-stream turbulence are compared with new measurements. Throughout the paper, recommendations for future work are suggested. These include quantitative study of the effect of surface defects and roughness, an assessment of whether atmospheric turbulence can affect swing and investigation into the effect of backspin on swing.

Auditory sensory augmentation to support table tennis games for people with vision loss

People with vision loss often face limitations in regular sports games with standard rules and equipment. For example, in current blind table tennis, conventional rules are modified so that the ball rolls along the table instead of bouncing. In this work, we propose an auditory sensory augmentation system to support traditional table tennis in three dimensions. We capture the trajectory of the table tennis ball using two neuromorphic event cameras and sonify the path of the ball using loudspeakers mounted near the left and right edges of the playing table. The two event cameras capture rapid changes in brightness allowing fast and precise ball tracking. The ball's 3D trajectory is then sonified using four lines of loudspeakers mounted at two different heights near the left and right edges of the playing table. We present a preliminary implementation and investigation of the proposed sensory augmentation system with a focus on the technical and perceptual challenges.

Physical match demands of four LIQUI-MOLY Handball-Bundesliga teams from 2019-2022: effects of season, team, match outcome, playing position, and halftime.

Due to the development in team handball, there is a need to optimize the physical capacities of team handball players for which knowledge of the physical match demands is essential. The aim of this study was to investigate the physical match demands of four LIQUI-MOLY Handball-Bundesliga (HBL) teams across three seasons with respect to the effects of season, team, match outcome, playing position, and halftime. A fixed installed local positioning system (Kinexon) was used, collecting 2D positional and 3D inertial measurement unit data at 20 and 100 Hz, respectively. The physical match demands were operationalized by basic (e.g., distance, speed, and acceleration) and more advanced variables (e.g., jumps, throws, impacts, acceleration load, and metabolic power). A total of 347 matches (213 with an additional ball tracking) were analyzed from four teams (one top, two middle, and one lower ranked) during three consecutive seasons (2019-2022). One-way ANOVAs were calculated to estimate differences between more than two groups (e.g., season, team, match outcome, playing position). Mean differences between halftimes were estimated using Yuen's test for paired samples. Large effects were detected for the season (), team (), and playing position (). Medium effects were found for match outcome () and halftime (). For the first time, we provide a comprehensive analysis of physical match demands in handball players competing in the LIQUI-MOLY Handball-Bundesliga. We found that physical match demands differ on that top-level with up to large effect sizes concerning the season, team, match outcome, playing position, and halftime. Our outcomes can help practitioners and researchers to develop team and player profiles as well as to optimize talent identification, training, regeneration, prevention, and rehabilitation procedures.

Ball tracking and trajectory prediction system for tennis robots

Abstract Recently, as the service robot market has grown, robots have emerged in various fields such as industry, service, and sports. In the field of sports, robots that can play with humans have been developed. We proposed a novel vision system for measuring the trajectory of a tennis ball and predicting its bound position, which can be utilized in the development of tennis robots. In this paper, we introduce a ball detection algorithm using an artificial neural network and a ball trajectory prediction algorithm using stereo vision. Our approach involved the use of a net vision system and a robot vision system to accurately detect and track the ball as it moves across the court. By combining these two systems, we were able to predict the trajectory and bound position of the tennis ball with high accuracy. As a result, the accuracy of the neural network for ball detection in actual tennis images reaches 81.4%. The ball trajectory prediction error in Gazebo simulation is 29.6 cm in the x-axis, 7.2 cm in the y-axis, and 11.7 cm in the z-axis on average.

A multi-view automatic table tennis umpiring framework

This paper presents a low-cost, portable, multi-view table tennis umpiring framework, as a viable alternative to the current expensive systems which are almost exclusively restricted to elite professional sports. Table tennis has been selected as the sport to evaluate this framework primarily because it comprises many different complex match elements, including the service, return and rally elements, which are governed by a strict set of regulations which need to be umpired. The aim is to develop novel methods to analyse and judge the legality of such key match facets, with ball detection and tracking in video frames being integral to reliably and accurately determining the ball’s position and flight path during rallies. While a low-cost option is attractive and offers several benefits, it is a technically challenging problem due to the small number and generally low-resolution cameras that are used. A novel multi-view camera setup and multi-agent system (MAS) framework is presented, which comprises computationally lightweight agents which detect and track the table tennis ball, create a 3D representation of the flight path of the ball, predict the ball’s trajectory, and identify and analyse key facets in a table tennis rally. The MAS correctly detects all state transitions in seven test table tennis sequences with minimal latency and while the processing rate of a standard computer may be unable to analyse long rallies in real time, the potential of running the MAS on a parallel architecture is a propitious alternative. The MAS is also scalable, enabling additional camera pairs to be deployed to achieve enhanced accuracy and coverage. The framework affords the potential to reform the way matches are umpired, especially for amateur players, providing an economic and objective manner of dispute resolution, while the multi-view facility is extendible to other relevant ball-based sports. The ball flight path analysis mechanism can be exploited as a valuable training tool for skill development.

Increasing the Social Interaction of Autism Child using Virtual Reality Intervention (VRI)

Nowadays there is an increase in number of autisms, a neuro-developmental disorder across the world. The level of autism varies with the symptoms such as inattention, interaction, social communication, repetitive behaviors, irritability and the like. Early recovery of a child from autism is necessary to live in a normal socio-communicable life. To measure the inattention of the autism child by enhancing the visual perception through virtual environment. The proposed Virtual Reality Intervention (VRI) enhances visual perception, learning, and social interaction. The proposed method observes the attention level of the autism child through eye tracking or eye movements who interacts with virtual world using eye tracking methodology. As eye tracking is the major component to measure the reduced looking time of objects and subjects which considered being the earliest signs of autism spectrum disorder (ASD). For observing the attention of kids during testing, Eye movements and gestures plays a major role. Using head position and eye pupil direction, attention has been analyzed. Quantitative and Qualitative findings conclude that the inattention of autism child can gradually be reduced by iterating the virtual therapy through eye ball tracking technique. Qualitative finding is done using Aberrant Behavior Checklist (ABC) and quantitative using eye-pupil and head position. Autism affected children can easily recovered from this inattention symptom by continuous iterations on virtual therapy. Similar virtual therapies can also be provided to address other symptoms of autism.

Real-time Ball Detection and Tracking using Raspberry PI

This paper presents a real-time system for ball detection and tracking system which is reliable in any conditions. Images from the webcam are processed by openCV library running on a Raspberry Pi to move the camera pan and tilt servo and two DC motors to drive the robot body using the Arduino Nano microcontroller. The webcam is integrated in a robot prototype to represent the wheel football robot type. The results show that a ball tracking webcam system is obtained with the capability to detect a ball with a diameter of 17cm within a maximum distance of 200 cm, a stable ball reading when the light intensity is at 32 lux and above. Furthermore, the experimental results demonstrated the system’s robustness in detecting and tracking ball in different distance and ligthing conditions.

Ball Detection and Tracking through Image Processing using Python

In this paper, the ball detection and tracking through image processing using python is presented. The Ball Detection and Tracking through Image Processing using Python is a project that aims to identify and track a ball in real-time using computer vision techniques. The project involves the use of a camera to capture the video of the ball, which is then processed by the software using OpenCV library in Python. The project comprises two stages, i.e., ball detection and tracking. In the first stage, the algorithm identifies the ball in the video frame by detecting the circular shape of the ball. The second stage involves tracking the ball's movement by using optical flow techniques. The software is designed to run on a Raspberry Pi or a PC, and it is capable of processing video in real-time. The output of the software is the position of the ball, which is displayed on the screen. The position can also be used to control other devices, such as a robot, to follow the ball's movement. The project has several applications, such as in sports analytics, where it can be used to track the movement of a ball in a game like football or basketball. It can also be used in industrial automation, where it can be used to track the movement of objects on a conveyor belt. Overall, the Ball Detection and Tracking through Image Processing using Python project is an excellent example of the application of computer vision techniques in real-time video processing. It has the potential to revolutionize various industries and open up new possibilities for automation and analytics.

Data Journey: Digitalization Projects Deliver Returns for Operators

Data are the backbone of what Klaus Schwab—the founder and executive chairman of the World Economic Forum—proclaimed to be the Fourth Industrial Revolution. This 21st‑century revolution is one of connectivity, advanced analytics, automation, and manufacturing technology. While the road to this high‑tech revolution started long ago with the use of water and steam to power mechanized production, it was electricity’s ability to power mass production that delivered us from the first to the second industrial revolution. Electronics and information systems necessary to automate production ushered in the third revolution. The data and our abilities to decipher and extract value from these seemingly random and disparate patterns of numbers and letters to create actionable intelligence is rapidly transforming the way business is conducted. Data are everywhere and in everything. But on the grand scale of time, the collection, analysis, and application of digital data is relatively young. Billy Bean and the Major League Baseball team Oakland Athletics, for example, demonstrated the importance of data‑driven decision making in the early 2000s by leveraging the power of data analytics to go from last place contender to chasing the championship in what has become known as Moneyball. Some 20 years later, the power of data and digital continues to evolve, with the bright lights of Qatar’s Lusail Stadium, for example, shining down last month on the final football match of the FIFA World Cup; every movement made by Al Rihla was captured, stored, and analyzed. But Al Rihla was not a player; it was the football created by Adidas and used in each of the more than 60 matches held throughout the tournament with an internal sensor for real‑time ball tracking capabilities. High‑speed cameras and antennas surrounding the football pitch provided additional support, feeding data into FIFA’s enhanced football intelligence service. The data collected during the matches were analyzed on a variety of metrics like possession time, line breaks, pressure on the ball, and forced turnovers, and then shared with teams with the goal of improving the game and its players. Winning the “beautiful game” is not as simple as it looks, as there’s more to kicking the ball into the opposing team’s net to score a goal as many times as possible in 90 minutes. These data offer an inside look into the processes of success or failure. Simple, too, is the production of oil and gas when explained on paper: drill a hole into the ground, route what flows to the surface into a pipeline, and then get paid for the effort invested in delivering that resource to the market when the price is right. It is more complicated than that, and data are playing an important role in delivering production increases and more. Data powered the shale gale that swept across the US oil and gas industry. David Millwee, vice president of drilling performance for Patterson‑UTI Drilling, credits data for helping to deliver the yearly increases in the lateral footage drilled.

A Query Language for Exploratory Analysis of Video-Based Tracking Data in Padel Matches

Recent advances in sensor technologies, in particular video-based human detection, object tracking and pose estimation, have opened new possibilities for the automatic or semi-automatic per-frame annotation of sport videos. In the case of racket sports such as tennis and padel, state-of-the-art deep learning methods allow the robust detection and tracking of the players from a single video, which can be combined with ball tracking and shot recognition techniques to obtain a precise description of the play state at every frame. These data, which might include the court-space position of the players, their speeds, accelerations, shots and ball trajectories, can be exported in tabular format for further analysis. Unfortunately, the limitations of traditional table-based methods for analyzing such sport data are twofold. On the one hand, these methods cannot represent complex spatio-temporal queries in a compact, readable way, usable by sport analysts. On the other hand, traditional data visualization tools often fail to convey all the information available in the video (such as the precise body motion before, during and after the execution of a shot) and resulting plots only show a small portion of the available data. In this paper we address these two limitations by focusing on the analysis of video-based tracking data of padel matches. In particular, we propose a domain-specific query language to facilitate coaches and sport analysts to write queries in a very compact form. Additionally, we enrich the data visualization plots by linking each data item to a specific segment of the video so that analysts have full access to all the details related to the query. We demonstrate the flexibility of our system by collecting and converting into readable queries multiple tips and hypotheses on padel strategies extracted from the literature.

Exploring the effects of head movements and accompanying gaze fixation switch on steady-state visual evoked potential.

In a realistic steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) application like driving a car or controlling a quadrotor, observing the surrounding environment while simultaneously gazing at the stimulus is necessary. This kind of application inevitably could cause head movements and variation of the accompanying gaze fixation point, which might affect the SSVEP and BCI’s performance. However, few papers studied the effects of head movements and gaze fixation switch on SSVEP response, and the corresponding BCI performance. This study aimed to explore these effects by designing a new ball tracking paradigm in a virtual reality (VR) environment with two different moving tasks, i.e., the following and free moving tasks, and three moving patterns, pitch, yaw, and static. Sixteen subjects were recruited to conduct a BCI VR experiment. The offline data analysis showed that head moving patterns [F(2, 30) = 9.369, p = 0.001, effect size = 0.384] resulted in significantly different BCI decoding performance but the moving tasks had no effect on the results [F(1, 15) = 3.484, p = 0.082, effect size = 0.188]. Besides, the canonical correlation analysis (CCA) and filter bank canonical correlation analysis (FBCCA) accuracy were better than the PSDA and MEC methods in all of the conditions. These results implied that head movement could significantly affect the SSVEP performance but it was possible to switch gaze fixation to interact with the surroundings in a realistic BCI application.

Trail Leg Hip Power: Influence On Elbow Varus Torque In Baseball Pitchers

Although excessive elbow varus torque has been reported to contribute to ulnar collateral ligament (UCL) injury in baseball pitchers, contributing factors remain relatively unknown. The lower extremities generate power that is transferred up through the kinetic chain in pitching. Specifically, the trailing hip generates triplanar power during the stride phase. Diminished trailing hip power generation during pitching may necessitate compensatory power generation at the trunk and shoulder, potentially impacting elbow torque. PURPOSE: To determine the relationship between hip power and elbow varus torque during pitching. METHODS: Participants (n = 48) were high-school and collegiate baseball pitchers (17.6 ± 2.5 yrs, 1.85 ± 0.06 m, 84.7 ± 13.4 kg). Reflective markers were placed on the bilateral lower extremities (femoral condyles, malleoli, calcaneus, and distal foot), spine, scapulae and both upper extremities (acromia, humeral epicondyles, styloids of the wrist, and hand). Kinematics and kinetics (instrumented mound) were obtained from the trail limb during 3 maximal effort fastball pitches (36.9 ± 2.5 m/s). Ball velocity (m/s) was measured using an automated ball tracking system. Stride phase was defined as the time between peak stride knee height and stride foot contact. Elbow varus torque and hip power were quantified using inverse dynamics equations and normalized to body weight. Hip power was calculated as the resultant sum of X, Y and Z components expressed in the hip joint coordinate system. Linear regression was used to evaluate the relationship between peak elbow varus torque and hip power, using ball velocity as a covariate. Significance was set to 0.05. RESULTS: Peak hip power was found to be negatively associated with peak elbow varus torque (B = -0.02, p = 0.003, R2 = 11.2%). CONCLUSION: Lower hip power production is associated with higher elbow varus torque during the stride phase of pitching. Greater use of the trail hip during the stride phase may allow pitchers to decrease elbow torque while maintaining ball velocity. Future work should explore intermediate relationships in the pitching kinetic chain to establish a mechanism by which increased hip power may mitigate elbow varus torque in pitching.

VIDEO-BASED TABLE TENNIS TRACKING AND TRAJECTORY PREDICTION USING CONVOLUTIONAL NEURAL NETWORKS

One of the fascinating aspects of sports rivalry is that anything can happen. The significant difficulty is that computer-aided systems must address how to record and analyze many game events, and fractal AI plays an essential role in dealing with complex structures, allowing effective solutions. In table tennis, we primarily concentrate on two issues: ball tracking and trajectory prediction. Based on these two components, we can get ball parameters such as velocity and spin, perform data analysis, and even create a ping-pong robot application based on fractals. However, most existing systems rely on a traditional method based on physical analysis and a non-machine learning tracking algorithm, which can be complex and inflexible. As mentioned earlier, to overcome the problem, we proposed an automatic table tennis-aided system based on fractal AI that allows solving complex issues and high structural complexity of object tracking and trajectory prediction. For object tracking, our proposed algorithm is based on structured output Convolutional Neural Network (CNN) based on deep learning approaches and a trajectory prediction model based on Long Short-Term Memory (LSTM) and Mixture Density Networks (MDN). These models are intuitive and straightforward and can be optimized by training iteratively on a large amount of data. Moreover, we construct a table tennis auxiliary system based on these models currently in practice.

A Markov process approach to untangling intention versus execution in tennis

Abstract Value functions are used in sports to determine the optimal action players should employ. However, most literature implicitly assumes that players can perform the prescribed action with known and fixed probability of success. The effect of varying this probability or, equivalently, “execution error” in implementing an action (e.g., hitting a tennis ball to a specific location on the court) on the design of optimal strategies, has received limited attention. In this paper, we develop a novel modeling framework based on Markov reward processes and Markov decision processes to investigate how execution error impacts a player’s value function and strategy in tennis. We power our models with hundreds of millions of simulated tennis shots with 3D ball and 2D player tracking data. We find that optimal shot selection strategies in tennis become more conservative as execution error grows, and that having perfect execution with the empirical shot selection strategy is roughly equivalent to choosing one or two optimal shots with average execution error. We find that execution error on backhand shots is more costly than on forehand shots, and that optimal shot selection on a serve return is more valuable than on any other shot, over all values of execution error.

Machine Vision-Based Ping Pong Ball Rotation Trajectory Tracking Algorithm.

Because of the overwhelming characteristics of computer vision technology, the trend of intelligent upgrading in sports industry is obvious. Video technical and tactical data extraction, big data analysis, and match assistance systems have caused profound changes to all aspects of the sports industry. One of the important applications is the playback and analysis of sports videos. People can observe the videos and summarize the experience of sports matches, and in this process, people prefer the computers to also interpret and analyze sports matches, which can not only help coaches in postmatch analysis but also design robots to assist in teaching and training. In this paper, we have examined and designed an automatic detection system for ping pong balls, in which the motion trajectory and rotation information of ping pong balls are mainly detected. To achieve this goal, the detection and tracking algorithm of ping pong balls based on deep neural network is used, and better results are achieved on the data set established by ourselves and the actual system test. After obtaining the position of the ping pong ball in the image, the rotation direction and speed of the ping pong ball are calculated next, and the Fourier transform-based speed measurement method and the CNN-based rotation direction detection method are implemented, which achieve better results in the testing of lower speed datasets. Finally, this paper proposes an LSTM-based trajectory prediction algorithm to lay the foundation for the design of table tennis robot by predicting the trajectory of table tennis. Experimental tests show that the proposed system can better handle the ping pong ball tracking and rotation measurement problems.

Capture, analyse, visualise: An exemplar of performance analysis in practice in field hockey.

The goal of performance analysis is to capture the multitude of factors that affect sports strategy, and present them in an informative, interpretable, and accessible format. The aim of this study was to outline a performance analysis process in field hockey that captures, analyses and visualises strategy in layers of detail culminating in the creation of an RStudio Shiny application. Computerised notational analysis systems were developed to capture in-game events and ball tracking data of 74 matches from the Women’s Pro League 2019. Game styles were developed using k-means cluster analysis to reduce detailed in-game events into practical profiles to identify the attack types, game actions and tempo of a team’s strategy. Ball movement profiles were developed to identify the predictability (entropy) and direction (progression rates) of ball movements, and consequent distribution of possession in different attacking zones. The Shiny application, an interactive web-platform, links the information from simple game profiles with detailed game variables to understand each teams’ holistic game plan, how they are different, and how to exploit these differences. The process outlined can be applied to any team invasion sport to understand, develop and communicate successful strategies under different match situations.