Pose estimation is the problem of detecting poses of people in images, multiperson pose estimation is the problem of detecting poses of multiple persons in images. This thesis investigates multi-person pose estimation by applying the associative embedding method on images from soccer videos. Three models are compared, first a pre-trained model, second a fine-tuned model and third a model extended to handle image sequences. The pre-trained method performed well on soccer images and the fine-tuned model performed better then the pre-trained model. The image sequence model performed equally as the fine-tuned model but not better. This thesis concludes that the associative embedding model is a feasible option for pose estimation in soccer videos and should be further researched.

Due to rugby's increasing level of professionalism, rugby union performance analysis is in a rapid state of evolution. Coaches, media, administrators and players are demanding greater access to more detailed analysis of team and player performance. Owing to the dynamic nature of the game and high frequency of events, nobody can adequately recall all aspects of the game; therefore performance analysts are playing an increasingly important role in rugby. The ability of analysts to meet this demand is being enhanced by technological advancements world wide, including the integrated capabilities of digital video, computer systems and video analysis software. Most analyses are conducted post-match by reviewing video footage and coding events of interest. Sound methodological approaches exist to develop performance indicators, which, if appropriately collated, can be used to create performance profiles indicative of player and/or team abilities. Sufficient data should be collected to ensure valid profiles, which can then be compared against population norms for more objective interpretation. Rugby research has focused on a range of performance indicators related to game structures and tactical aspects, including lineout tactics, differences between winning and losing performances, which side of the field try scoring predominates, and the number of passes per try. Research has included analysis of the world's top teams to assess the effect of law changes on the game and rates of foul play across different competitions. Despite the range of detailed analysis in the literature, there is a need for a structured account of all logical units of play, defined and quantified in accordance with coaching language and concepts. Player interactions, and off the ball player formations, also present future research potential.

Due to rugby's increasing level of professionalism, rugby union performance analysis is in a rapid state of evolution. Coaches, media, administrators and players are demanding greater access to more detailed analysis of team and player performance. Owing to the dynamic nature of the game and high frequency of events, nobody can adequately recall all aspects of the game; therefore performance analysts are playing an increasingly important role in rugby. The ability of analysts to meet this demand is being enhanced by technological advancements world wide, including the integrated capabilities of digital video, computer systems and video analysis software. Most analyses are conducted post-match by reviewing video footage and coding events of interest. Sound methodological approaches exist to develop performance indicators, which, if appropriately collated, can be used to create performance profiles indicative of player and/or team abilities. Sufficient data should be collected to ensure valid profiles, which can then be compared against population norms for more objective interpretation. Rugby research has focused on a range of performance indicators related to game structures and tactical aspects, including lineout tactics, differences between winning and losing performances, which side of the field try scoring predominates, and the number of passes per try. Research has included analysis of the world's top teams to assess the effect of law changes on the game and rates of foul play across different competitions. Despite the range of detailed analysis in the literature, there is a need for a structured account of all logical units of play, defined and quantified in accordance with coaching language and concepts. Player interactions, and off the ball player formations, also present future research potential.

Tennis är en sport som ständigt förändras. Nya data som analytikern Craig O'Shannessy tagit fram visar att en klar majoritet av alla poäng är korta, det vill säga poäng som innehåller fyra eller färre slag. Den spelare som vinner flest av dessa tenderar även att stå som segrare i slutet av matchen. Målet med det här arbetet är att undersöka WTA-turneringen Sydney International 2018 för att se om samma mönster går att hitta där och, om så är fallet undersöka om det finns några skillnader mellan hur olika grupper presterar. Ett par exempel på grupper är matchvinnare mot förlorare och seedade mot oseedade spelare. Det visade sig att poänglängderna nästan var identiska med O'Shannessys resultat och de hade påverkan på utgången av matcherna. Vidare så låg matchvinnarna högre i de flesta kategorierna som exempelvis andelen servar och returer in och andelen vunna. Gällande serve+1 så höll de en jämn nivå både på forehand- och backhandsidan, jämfört med de förlorande spelarna som hade problem med backhanden. Däremot gick det inte att se några tydliga skillnader i serve- och returmönster, bortsett från andraservar till deuce court. Utifrån resultaten så verkar kvaliteten på slagen vara mer avgörande än var i banan som de landar. / Tennis is an everchanging sport. New data from tennis analyst Craig O'Shannessy show that a vast majority of points are short, i.e. points decided in four or fewer shots. The player who wins most of them also tends to be the winner. The purpose of this paper is to examine the WTA tournament Sydney International 2018 to see if the same pattern occurs there and if that is the case investigate if there is any difference between how different groups are performing. A few examples of groups are match-winners against losers and seeded against unseeded players. It turns out that the lengths of the points were almost identical to O'Shannessy’s results and they influenced the matches outcome. Furthermore, match winners performed better in most categories, for example, the ratio of serves and returns in play and won. Regarding serve+1 they were able to keep an even level on both forehand and backhand side, while the losing players had some problems with their backhands. With that said, there were no clear differences in serve and return patterns, apart from second serves to the deuce court. From the results, it seems like the quality of the shots is more important than where they are landing.

Prestationsmätning och analys används inom sporter för att förbättra en spelares resultat relaterade till sin respektive sport. För analys finns labb och/eller dyr utrustning vilket gör den svårtillgänglig för icke-professionella utövare. Att minska kostnaden för mätverktyg bidrar till mer jämlika förutsättningar för spelare oavsett inkomst eller ålder. Den här studien syftar till att undersöka om en smartphone eller surfplatta kan användas för mätning och sportanalys. För att utforska detta utvecklades en applikation med fokus på projektilsporter som fotboll, tennis och golf. Applikationen testar visualisering av ett objekts parabel, mätning av dess hastighet och visualisering av dess träff i ett vertikalt plan. Applikationen utvecklades för iOS och testades på en iPad 12 pro. Tester för att validera applikationens noggrannhet utfördes med en fotboll, en tennisboll och en golfboll. Testresultaten för visualisering av parabel gav resultat för fotboll och tennisboll men kunde inte hantera golfbollens mindre storlek. Hastighet kunde mätas för alla tre bollar med en genomsnittlig procentuell avvikelse på 76% för fotboll, 21% för tennisboll och 43% för golfboll. Testresultaten för visualisering av ett objekts träff i ett målplan visade resultat för fotboll och tennisboll, men inte för en golfboll. Den genomsnittliga procentuella avvikelsen var 89% för fotboll respektive 23% för tennisboll. / Measuring and analyzing player performance within sports helps to improve a players results in regards to their respective sport. Specialized labs and or expensive equipment are used for analysis but are difficult to access for the average player. Decreasing the cost of measurement tools would help equalize the playing field for players regardless of age or economic background. This study evaluates if a smartphone or tablet can be used to perform the same task. To achieve this an application was developed with a focus on projectile sports such as soccer, tennis, or golf. The application will visualize a parabola, measure speed, and visualize the point where an object hits a vertical plane. The application was developed for iOS and was tested on an iPad 12 pro. The tests were performed with a soccer ball, tennis ball and golf ball. Tests for visualizing a parabola produced results for the soccer ball and the tennis ball but could not handle the golf balls smaller size. Speed was measured for all three balls with an average percentual offset of 76% for the soccer ball, 21% for the tennis ball and 43% for the golf ball. Hit on a vertical plan produced results for the soccer ball and tennis ball with an average percentual offset of 89% for the soccer ball and 23% for the tennis ball.