DOCSLIB.ORG

Tracknet: a Deep Learning Network for Tracking High-Speed and Tiny Objects in Sports Applications

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Tracknet: a Deep Learning Network for Tracking High-Speed and Tiny Objects in Sports Applications TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications Yu-Chuan Huang I-No Liao Ching-Hsuan Chen Ts`ı-U´ı Ik˙ ∗ Wen-Chih Peng Department of Computer Science, College of Computer Science National Chiao Tung University 1001 University Road, Hsinchu City 30010, Taiwan ∗Email: [email protected] Abstract—Ball trajectory data are one of the most topic in the areas of image processing and deep fundamental and useful information in the evaluation of learning. In the applications of sports analyzing and players’ performance and analysis of game strategies. athletes training, videos are helpful in the post-game Although vision-based object tracking techniques have review and tactical analysis. In professional sports, been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed high-end cameras have been used to record high and tiny ball accurately. In this paper, we develop a deep resolution and high frame rate videos and combined learning network, called TrackNet, to track the tennis with image processing for referee assistance or data ball from broadcast videos in which the ball images are collection. However, this solution requires enormous small, blurry, and sometimes with afterimage tracks or resources and is not affordable for individuals or even invisible. The proposed heatmap-based deep learning amateurs. Developing a low-cost solution for data network is trained to not only recognize the ball image from a single frame but also learn flying patterns from acquisition from broadcast videos will be significant consecutive frames. TrackNet takes images with the size for massive sports data collection. of 640 × 360 to generate a detection heatmap from either Ball trajectory data are one of the most funda- a single frame or several consecutive frames to position mental and useful information for game analysis. the ball and can achieve high precision even on public However, for some sports such as tennis, badminton, domain videos. The network is evaluated on the video of baseball, etc., the ball is not only small but also may the men’s singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and fly as fast as several hundred kilometers per hour, F1-measure of TrackNet reach 99:7%, 97:3%, and 98:5%, resulting in tiny and blurry images. That makes the respectively. To prevent overfitting, 9 additional videos ball tracking task becomes more challenging than are partially labeled together with a subset from the other sports. In this paper, we design a heatmap- previous dataset to implement 10-fold cross validation, and based deep learning network, called TrackNet, to the precision, recall, and F1-measure are 95:3%, 75:7%, precisely position ball of tennis and badminton on arXiv:1907.03698v1 [cs.LG] 8 Jul 2019 and 84:3%, respectively. A conventional image processing broadcast videos or videos recorded by consumer’s algorithm is also implemented to compare with TrackNet. Our experiments indicate that TrackNet outperforms con- devices such as smartphones. TrackNet overcomes ventional method by a big margin and achieves exceptional the issues of blurry and remnant images and can ball tracking performance. The dataset and demo video are even detect occluded ball by learning its trajectory available at https://nol.cs.nctu.edu.tw/ndo3je6av9/. patterns. The proposed network can be applied to Index Terms—Deep Learning, neural networks, tiny other ball-based sports and help both amateurs and object tracking, heatmap, tennis, badminton professional teams collect data with a moderate budget. I. INTRODUCTION Conventional image recognition is usually based Video considered as logs of visual sensors con- on the object’s appearance features such as shape, tains a large amount of information. Information color, size, etc., or statistical features such as HOG, extraction from videos has become a hot research SIFT, etc. Due to a relatively long shutter time of consumer or prosumer cameras, images of high- detection. At last, the position of our target object speed objects are prone to suffer from afterimage is calculated based on the heatmap generated by the or blur issues, resulting in poor image recognition deep learning network. To meet the characteristics accuracy. The performance of ball tracking can be of tennis and badminton games, our calculation and improved by pairing candidates from frame to frame evaluation are based on the assumption that there is according to trajectory models to find the most at most one ball on the court. possible one [1]. In addition, a classical technique in image processing to improve image quality is To evaluate the proposed network, we have la- by fusing multiple low-quality images. Based on beled 20; 844 frames from the broadcast of men’s the above observations, instead of using the rule- singles final at the 2017 Summer Universiade. To based techniques, we propose to adopt deep learning assess the performance of the proposed consecu- network to recognize the shape of the ball and tive input frames technique, both single-frame and learn the trajectory patterns by applying multiple multiple-frame versions of TrackNet are imple- consecutive frames to solve the mentioned issues. mented. Along with the conventional image recog- Object classification and detection are two of the nition algorithm [1], a comprehensive comparison earliest studies in deep learning. VGG-16 [2] is among different models is performed. Experiments one of the most popular networks for feature map indicate that the proposed TrackNet outperforms the encoding. To detect and classify multiple objects in conventional image recognition algorithm and effec- an image, the R-CNN family [3] [4] [5] structurally tively locates fast-moving tennis ball from broadcast examine the picture in two stages. It firstly selects sport competition videos. Moreover, to prevent the many areas that may contain interesting objects, notorious overfitting issue that happens frequently called Region of Interests (RoIs), and then applies in deep learning solutions, additional data from object detection and classification techniques on 9 tennis games on different courts are added to these regions. However, its performance cannot ful- the training dataset, including grass court, red clay fill the needs of real-time applications. To speed up, court, hard court, etc. Additionally, to explore the the YOLO family [6] develops a one-stage end-to- model extensibility, badminton tracking by Track- end approach to detect objects in a limited search Net is evaluated. We have labeled 18; 242 frames space, significantly reducing the computing time. from the video of 2018 Indonesia Open Final - TAI The streamlined version of Tiny YOLO can even run Tzu Ying vs CHEN YuFei. Although badminton on the Raspberry Pi. Compared to the block-based travels much faster than tennis, our experimental algorithms, Fully Convolutional Networks (FCN) results exhibit a decent performance. proceeds pixel-wise classification. To compensate for the size reduction of the feature map during the The critical contribution of TrackNet comes from encoding process, upsampling and DeconvNet [7] its capability of precisely tracking fast-moving and are often used to decode the feature map, generating tiny objects by learning the dynamic behavior of the an original size of the data array. trajectory. In the tennis tracking application, 10-fold In this paper, a deep learning network, called cross validation results in an outstanding perfor- TrackNet, is proposed to realize a precise trajec- mance of 95:3% precision, 75:7% recall, and 84:3% tory tracking network. Firstly, VGG-16 is adopted F1-measure. Such capability shows great potential to generate the feature map. Different from other in expanding the variety of computer vision applica- deep learning networks, TrackNet can take multiple tions. The rest of the paper is organized as follows. consecutive frames as input. In this way, TrackNet Section II provides an introduction to the relevant learns not only the features of the ball but also the researches and the convolutional neural network. characteristics of ball trajectories to enhance its ca- Section III introduces the datasets used in this paper. pability of object recognition and positioning. Since Section IV elaborates the proposed deep learning images are downsampled and encoded by pooling network and Gaussian heatmap techniques. Section layers, the network follows the upsampling mech- V provides experimental results and performance anism of FCN to generate the heatmap for object evaluation. At last, Section VI concludes this paper. 2 II. RELATED WORKS sampling, and deconvolution/up-sampling. A soft- max layer is usually used as the output layer. In recent years, the analysis of player perfor- For example, the widely used VGG-16 [2] mainly mance and game tactics based on the trajectory consists of convolutional, maximum pooling, and data of balls and players has received more and ReLU layers. Conceptually, front-end layers learn more attention [8] [9] [10] [11]. Many tracking to identify simple geometric features, and back-end algorithms and systems have been developed to layers are trained to identify object features. compute and collect the trajectory data. Current In CNNs, each layer is a W × H × D data array. commercial solutions mainly rely on high resolution W , H, and D denote the width, height, and depth and high frame rate video, resulting in high hard- of the data array, respectively. The convolution ware investment. For example, the Hawk-Eye sys- operation is a filter with a kernel of size w × h × D tem [12] has been extensively used in professional across the W × H range with the stride parameter competitions to calculate ball trajectories and assist s being set as 1 in many applications. To avoid the referee in clarifying controversial calls through information loss near the boundary or maintain the 3D visual depictions. Nonetheless, the system has to size of the output data array, columns and rows of deploy high-end cameras with dedicated operators the data array can be padded with zero by setting the at selected locations and angles.
Load more

Recommended publications
  • How the Court Surface Is Affecting the Serve-And-Volley Tristan Barnett
    How the court surface is affecting the serve-and-volley Tristan Barnett Strategic Games www.strategicgames.com.au 1. Introduction The modern version of the game (official name of Lawn Tennis) as we recognize it today was designed and patented by Major Walter Clopton Wingfield in 1873. Two years later in 1875, the official rules of the game were drawn up by Marylebone Cricket Club, and two years later in 1877, Wimbledon began on a grass surface as the first official championships. All four grand slam events have been played on a grass surface. Wimbledon is the only grand slam event played on a grass court today and has always been played on a grass court surface. The French Open began in 1891 on a grass surface and remained on grass until 1928 when the surface was changed to clay. The US Open began in 1881 on a grass surface; until it was changed to clay from 1975-1977 and from 1978 has been played on a hard court surface. Finally, the Australian Open began in 1905 on a grass surface and remained on grass until 1988 when the surface was changed to a hard court. There has been a change in the proportion of tournaments played on different court surfaces from 1877 to 2010. Firstly, for the first 14 years of the game, all tournaments (grand slam and non grand slam) were played on grass. Secondly, for the first 101 years of the game all tournaments were played on the natural surfaces of grass and clay. Thirdly, according to the ITF, until the early 1970’s, the majority of tournaments were played on grass including three out of the four grand slams.
    [Show full text]
  • Characterisation of Ball Degradation Events in Professional Tennis
    Sports Eng DOI 10.1007/s12283-017-0228-z ORIGINAL ARTICLE Characterisation of ball degradation events in professional tennis 1,2,3 1 3 1 Ben Lane • Paul Sherratt • Xiao Hu • Andy Harland Ó The Author(s) 2017. This article is published with open access at Springerlink.com Abstract Tennis balls are acknowledged to degrade with appears to influence the distribution of ball speed on impact use and are replaced at regular intervals during professional with the surface or racket, suggesting a surface-specific matches to maintain consistency and uniformity in per- degradation test may be beneficial. As a result of these formance, such that the game is not adversely affected. findings a new test protocol has been proposed, utilising the Balls are subject to the international tennis federation’s in-play data, to define the frequency of impacts and impact (ITF) ball approval process, which includes a degradation conditions to equate to nine games of professional tennis test to ensure a minimum standard of performance. The across the different surfaces. aim of this investigation was to establish if the ITF degradation test can assess ball longevity and rate of Keywords Tennis Á Ball Á Impact Á Hawk-Eye Á Surface Á degradation and determine if there is a need for a new Speed Á Angle Á Degradation degradation test that is more representative of in-play conditions. Ball tracking data from four different profes- sional events, spanning the three major court surfaces, 1 Introduction including both men’s and women’s matches were analysed. The frequency of first serves, second serves, racket impacts Approximately 360 million tennis balls are manufactured and surface impacts were assessed and the corresponding each year [1], with wholesale sales figures in the region of distribution of ball speed and (for surface impacts) impact $92 million in the United States alone in 2015 [2].
    [Show full text]
  • The Tennis Court
    M. ROSS ARCH. 422 • A RACQUET CLUB FOR LUBBOCK, TEXAS. A Racquet Club for Lubbock, Texas A Thesis Program in Partial Fulfillment of Requirements for the Bachelor of Architecture degree. Design Option Presented by Michael David Ross Texas Tech University Spring 1978 1, INTRODUCTION 2, THE CLIENT 3, FINANCING 4, THE SITE 11 S> FACILITIES 24 ^, RESTRICTIONS 40 7, APPENDIX 54 CONTENTS INTRODUCTION THE NATURE AND SCOPE OF THE PROJECT The nature of this thesis program is the development of the most precise and complete collection of data concerning my topic, A Racquet Club for Lubbock, Texas. Some of the questions this program will answer are: What is a Racquet Club? Who this Racquet Club is for? Where is this Racquet Club located? What goes on in this club? The elements composing the physical make-up of the facility are: 1. Clubhouse A) offices B) lounge and dining C) pro-shop D) lockers and dressing facilities E) indoor tennis and racquet ball courts 2. Outdoor tennis courts This facility not only will enhance the city of Lubbock but also provide its members a com­ plex that enables them to play the game as it should be played and to savor the deepest pleas­ ure the game has to offer. HISTORY OF THE PROJECT The name and the game came from the ancient net and racquet sport known in France where it was invented, as Jeu de Paume. This sport had its origins in the Middle Ages. It is mentioned in twelfth and thirteenth century manuscripts. In the sixteenth century the game was known to be exclusively an aristo­ cratic game because of the high cost of building courts.
    [Show full text]
  • Applied Sciences
    applied sciences Article Analysis of Serve and Serve-Return Strategies in Elite Male and Female Padel Bernardino J Sánchez-Alcaraz 1, Diego Muñoz 2,* , Francisco Pradas 3 , Jesús Ramón-Llin 4 , Jerónimo Cañas 5 and Alejandro Sánchez-Pay 1 1 Department of Physical Activity and Sport, Faculty of Sport Sciences, University of Murcia, C/Argentina, s/n, 30720 San Javier, Murcia, Spain; [email protected] (B.J.S.-A.); [email protected] (A.S.-P.) 2 Department of Didactic of Musical, Plastic and Corporal Expression, Faculty of Sports Science, University of Extremadura, Avda de la Universidad, s/n, 10003 Cáceres, Spain 3 Department of Musical, Plastic and Corporal Expression, Faculty of Human Sciences and Education, University of Zaragoza, C/Pedro Cerbuna, 12, 50009 Zaragoza, Spain; [email protected] 4 Department of Musical, Plastic and Corporal Expression, Faculty of Education, University of Valencia, Av. Dels Tarongers, 4, 46022 Valencia, Spain; [email protected] 5 Department of Physical Education and Sport, Faculty of Sport Sciences, University of Granada, Carretera de Alfacar, 21, 18071 Granada, Spain; [email protected] * Correspondence: [email protected]; Tel.: +34-927-257-460 Received: 22 August 2020; Accepted: 22 September 2020; Published: 24 September 2020 Abstract: This aim of this study was to analyze serve and return statistics in elite padel players regarding courtside and gender. The sample contained 668 serves and 600 returns of serves from 14 matches (7 male and 7 female) of the 2019 Masters Finals World Padel Tour. Variables pertaining to serve (number, direction, court side and effectiveness), return of serve (direction, height, stroke type and effectiveness) and point outcome were registered through systematic observation.
    [Show full text]
  • Tennis Courts: a Construction and Maintenance Manual
    DOCUMENT RESUME ED 433 677 EF 005 376 TITLE Tennis Courts: A Construction and Maintenance Manual. INSTITUTION United States Tennis Court & Track Builders Association.; United States Tennis Association. PUB DATE 1998-00-00 NOTE 246p.; Colored photographs may not reproduce clearly. AVAILABLE FROM U.S. Tennis Court & Track Builders Association, 3525 Ellicott Mills Dr., Suite N., Ellicott City, MD 21043-4547. Tel: 410-418-4800; Fax: 410-418-4805; Web site: <http://www.ustctba.com>. PUB TYPE Guides - Non-Classroom (055) -- Reports Descriptive (141) EDRS PRICE MF01/PC10 Plus Postage. DESCRIPTORS *Construction (Process); *Facility Guidelines; Facility Improvement; Facility Planning; *Maintenance; *Tennis IDENTIFIERS *Athletic Facilities ABSTRACT This manual addresses court design and planning; the construction process; court surface selection; accessories and amenities; indoor tennis court design and renovation; care and maintenance tips; and court repair, reconstruction, and renovation. General and membership information is provided on the U.S. Tennis Court and Track Builders Association and the U.S. Tennis Association, along with lists of certified tennis court builders and award winning tennis courts from past years. Numerous design and layout drawings are also included, along with Tennis Industry Magazine's maintenance planner. Sources of information and a glossary of terms conclude the manual. (GR) ******************************************************************************** Reproductions supplied by EDRS are the best that can be made
    [Show full text]
  • The Real Sport of Kings When Our Family Moved from Notting Hill Gate
    The Real Sport of Kings When our family moved from Notting Hill Gate to larger quarters on Brook Green I realized it was a ten-minute bike ride to The Queen’s Club. A mecca of lawn tennis, with grass courts, Queen’s was known for the Invitational that preceded Wimbledon. As a youth, spurred by my father whose passion was tennis, I played a lot, at times as many as eight hours a day. The game was so bound with Southampton’s lifestyle that even the houses, with their white- painted frames and green shutters, could seem a reverse echo of the grass courts on which we played. It is hard to imagine a Long Island village where we played only three months a year competing with Florida and California, but the town boasted a Wimbledon winner and several national champions. The two grandsons of Dwight Davis who had given the eponymous cup were daily opponents, and the Meadow Club Invitational (now the U.S. Amateur Championship) reigned as the longest continuing tournament on the grass court circuit. This tournament, which brought the great “bums,” as they were known, roaring in on their jalopies was the social high point of the Southampton summer, crowned by a dance and massive silver trophies that begged to be melted down. We put them up in our houses and the money I made ball-boying more than paid for all the presents I bought my parents. For much of my youth I aspired to that kind of athletic career. I wanted to travel to fabled venues: Wimbledon, Rome, Monte Carlo, Paris, Rapallo, Gstaad.
    [Show full text]
  • Data Visualization and Analysis of Playing Styles in Tennis
    https://doi.org/10.2352/ISSN.2470-1173.2021.1.VDA-319 © 2021, Society for Imaging Science and Technology Data Visualization and Analysis of Playing Styles in Tennis Shiraj Pokharel and Ying Zhu Department of Computer Science and Creative Media Industries Institute, Georgia State University Atlanta - 30303, USA Email: [email protected], [email protected] Abstract are used to show the ”fingerprint” of a player’s pattern of play. Sports data analysis and visualization are useful for gaining The analysis presented in this paper is based on micro-level insights into the games. In this paper, we present a new visual an- performance data from professional tennis matches. Although we alytics technique called Tennis Fingerprinting to analyze tennis focus on tennis in this paper, this idea can be extended to the players’ tactical patterns and styles of play. Tennis is a compli- analysis of other sports (including Esports), if micro-level per- cated game, with a variety of styles, tactics, and strategies. Tennis formance data is available. experts and fans are often interested in discussing and analyzing tennis players’ different styles. In tennis, style is a complicated Related Works and often abstract concept that cannot be easily described or ana- Traditional tennis analytics focuses on analyzing high-level lyzed. The proposed visualization method is an attempt to provide statistics, such as serve percentages, serve winning percentages, a concrete and visual representation of a tennis player’s style. We etc. These statistics mostly deal with the outcome of points, demonstrate the usefulness of our method by analyzing matches games, and matches, not how the points are played.
    [Show full text]
  • The Plantar Pressure Analysis of Open Stance Forehand in Female Tennis Players
    Chen, C, et al. (2019). The Plantar Pressure Analysis of Open Stance Forehand in Female Tennis Players. Physical Activity and Health, 3(1), pp. 63–70. DOI: https://doi.org/10.5334/paah.37 RESEARCH The Plantar Pressure Analysis of Open Stance Forehand in Female Tennis Players Chaoyi Chen, Zhiqiang Liang and Shudong Li Faculty of Sports Science, Ningbo University, CN Corresponding author: Chaoyi Chen ([email protected]) Purpose: The aim of this study was to analyze plantar pressure during the open stance forehand (OSF) in female tennis players. Methods: Seven female players executed the tennis forehand technique with open stance in the biomechanical laboratory. A portable pressure insole system was adopted to collect mean pressure (MP), peak pressure (PP), force (F), pressure-time integral (PTI) and contact area (CA) in 7 regions of the feet. Independent sample T-test was used to analyze the difference among these parameters. Results: F, PP in the first phalangeal region (BT) and the remaining four toe regions (OT) of the right foot (RF) were both larger than the left foot (LF); F in the fourth and fifth metatarsophalangeal joint (M4-5), the middle foot region (MF), hind foot region（HF）and PP in M4-5 of LF were significantly greater than the same region in RF; MP in BT and OT of RF showed significantly higher pressure than LF. While MP among areas of M4-5 and HF of LF was significantly greater than RF; PTI, CA in OT, M4-5 and MF of RF were significantly higher than LF while M1, M2-3, M4-5 and MF of LF showed significant smaller.
    [Show full text]
  • Artificial Surfaces for Recreation Bulletin Number 37
    Artificial Surfaces for Recreation Bulletin Number 37 A report of the proceedings of a Block Course held at Lincoln College, Canterbury, May 11-1 4 1 981. The course was designed to study and evaluate the range of artificial surfacing material·currently available for indoor and outdoor recreational facilities. Edited by J. O. Taylor I~I Sponsored by The N.Z. Institute of Park and Recreation Administration (Inc) GRJ.~I in association with .-.. • The Department of Horticulture, Landscape and Parks, ~I' Lincoln College, Canterbury. January 1982. FOREWORD In opening the Block Course on Artificial Surfaces for Recreation, Mr Lance Cross, C.B.E., Chairman, New Zealand Council for Recreation and Sport, quoted from a U.N.E.S.C.O. Survey that over the next 25 years the major problem facing the world as a whole, will be the effective use of leisure time. He went on to develop the theme that maximum use must be made of facilities already existing before expensive new recreation and sports arenas were developed. On a population basis, New Zealand needs only four standard Olympic pools, but many lido-type pools are still required. Local Authorities are faced with ever rising costs for the provision and maintenance of play grounds, sports grounds and recreational facilities, but the trick of how to reduce these costs, let alone maintain costs, eludes most experts today. The aim of the Block Course was to study the range of methods and materials available for the construction of artificial surfaces used in recreation and to come up with some positive ideas on what can best be used inside and outside to provide more effectively for the requirements of our recreating communities.
    [Show full text]
  • 2021 Confirmed Calendar 1
    2021 confirmed calendar Tournament Divisions Start Date End Date USTA Level City State Surface Host Tournament Director USTA National Mixed 50, 60, 70, 75, & 80 Hard Court Championships X50, X60, X70, X75, X80 TBD TBD Level 1 Palm Desert CA Hard Desert Tennis Events Caerwyn Evans USTA National Same Gender Couples Doubles Hard Court Championships Same Gender Op, 80, 100, 120, 140 3/6/2021 3/7/2021 Level 1 Rancho Mirage CA Hard Mission Hills Country Club (SGE) Nabil Najjar Tennis Channel USTA National Husband Wife Combined Age Grass Court Championships HW 100, HW120, HW 140 3/7/2021 3/13/2021 Level 1 Rancho Mirage CA Grass Mission Hills Country Club Mas Kimball / Steve Solomon USTA National Women's 40, 50, 60, 70, 80 Clay Court Championships W40, W50, W60, W70, W80 Sgls & Dbls 3/16/2021 3/20/2021 Level 1 Palm Beach Gardens FL Clay City of Palm Beach Gardens William McDermott / Trish Faulkner Tennis Channel & Crabel Capital USTA National Men's 65 Hard Court Championship $10,000 Prize Money M65 Sgls & Dbls 3/21/2021 3/27/2021 Level 1 Palm Springs CA Hard Tennis Events Mas Kimball / Steve Solomon USTA National Men's 40, 45, & Mixed 45 Clay Court Championships M40, M45 Sgls & Dbls X45 4/8/2021 4/13/2021 Level 1 Ft Lauderdale FL Clay Lauderdale Tennis Club Frank Hughes USTA National Women's 35, 45, 55, 65, 75, 85 & 90 Clay Court Championships W35, W45, W55, W65, W75, W85, W90 Sgls & Dbls 4/12/2021 4/18/2021 Level 1 Houston TX Clay Houston Racquet Club Susan Bramlette USTA National Men's 45 Hard Court Championships M45 Sgls & Dbls 4/26/2021 5/2/2021
    [Show full text]
  • Tennis-Point
    Tennis for Beginners Getting Ready to Hit the Court Midwest Sports Table of Contents Tennis: An Introduction ........................................................................................ i Section 1: The Basics ................................................................................................. 3 Chapter 1:Tennis Terms to Know .......................................................... 4 Chapter 2: The Ins and Outs of Tennis Scoring .................................... 8 Chapter 3: Finding the Perfect Beginners’ Racquet and Equipment . 11 Chapter 4: Outfitting Yourself for the Court ...................................... 17 Section 2: The Essential Elements of Play .................................................. 21 Chapter 5: The Grip............................................................................... 22 Chapter 6: The Serve ............................................................................. 25 Chapter 7: The Forehand ...................................................................... 28 Chapter 8: The Backhand ...................................................................... 31 Chapter 9: Volleys .................................................................................. 34 Conclusion .................................................................................................................. 36 Sources ............................................................................................................. 37 i ii TENNIS FOR BEGINNERS Tennis: An Introduction Have
    [Show full text]
  • Facts and Statistics Indicate Fixing at the Very Top of Men's Tennis
    Facts and statistics indicate fixing at the very top of men’s tennis by Katarina Pijetlovic, LL.B, LL.M, LL.Lic. LL.D cand. [email protected] EU and sports law academic Facts and statistics strongly indicate that draws at the Grand Slam tournaments 2008-2011 might have been fixed at the very top of men's tennis. Namely, in 12 out of 12 Grand Slam tournaments played on hard and grass courts between 2008-2011, Federer and Djokovic were always drawn to the same half of the draw, while Nadal and Murray were drawn to the other half. In addition, in five of those 12 tournaments Murray was not among the first four seeded players, so his draw was conducted separately five times. Thus, the statistics are as follows: to get the same result 12 out of 12 times, probability is 1 in 4096. For the case of Murray's separate draws which produced the same result 5 out of 5 times, it is 1 in 32. THEREFORE, THE PROBABILITY TO OBTAIN DRAW RESULTS AS OBTAINED AT THE 12 GRAND SLAM TOURNAMENTS IS 131072 TO 1 (4096 x 32 = 131072). Combined with the study conducted by ESPN on the draws of unseeded players at US Open it reaches 1 in many BILLIONS. FACEBOOK PAGE ON THIS ISSUE WITH MORE DETAILS AVAILABLE AT http://www.facebook.com/pages/Tennis‐ biggest‐public‐secret/284730451547505?sk=wall DRAWING PROCEDURE In general, at the Grand Slam tournaments players are entered in the draw sheet based on their current standing on the ATP rank list.
    [Show full text]