As technology progresses, people start engaging in sedentary behaviour more and could raise the risk of getting health deficits such as cardiovascular diseases, cancer, and type-2 diabetes. Recent studies on how to prevent sedentary behaviour is to incorporate physical activity through exergaming. While many exergames have been on health aspects and how to design exergames, not much has been on the impact of certain game designs and game rules. Our paper will research how to design and create a fun 2Dplatform exergame and keep or increase the total movement as the player gets better at the game. The exergame used some normal game design and some known design strategies from experienced exergame designers. The data were then taken from the authors playing the exergame and the results showed a positive increase in total movement when they had a higher score. In-game components such as durational power ups had some higher and lower total movement per second than without, but in general the total movement increased the more power ups were picked up. We believe picking up power ups and power ups that motivates the player to move more, yields in more total movement

The world's population has grown sedentary during the past one to two decades, with increased time spent sitting and laying down both during work hours and free time spent at home. For people that find normal exercise boring, exergames can be an attractive alternative. Using their body to play the game the player can have fun while exercising or even just to get some blood flowing. In this research project we implemented a game of a successful genre but we changed input from a controller to the body of the player. We set out to find out how to design a game as an exergame, how exhausted players get when playing and whether the players find it uncomfortable or not to play the game. Our testing showed that the implemented game might not have been as responsive as we would have hoped. When it comes to the exhaustion perceived by the play-testers they reported that they considered the game exercise, but also that most of them did not find it too intense during the playtest.

The world is quickly moving to a more and more digital world, everything is online and computerized. This is convenient but also increases the amount of time spent in front of various types of devices and displays, not getting the exercise we as humans need. Gaming or the act of playing video games is very much a part of this and is traditionally thought of as a sedentary activity. However, there is a type of video games that does not fall into this category, that is exergames. Exergames distinguish themselves from sedentary games in that they use the human body for control, leading to their use to combat the lack of exercise. This thesis describes the implementation and testing of one such exergame that is a part of a larger project at Linköping University that aims to create a library of games to be used in organizations where sitting for long periods is common. The game is implemented using the game engine Godot and an ML solution called MediaPipe for movement tracking and recognition. The goal was to create an easy to playgame providing moderate to high physical activity. Testing showed that the game provided the desired physical exertion within a few consecutive rounds and exertion remained on roughly the same level even if the user was experienced.

Hand and finger movements are underrepresented in biomechanical studies, primarily due to the challenge of tracking the hands and fingers. Several limitations are associated with marker-based motion capture, including interference with natural movement, and require the tedious, time-consuming application of numerous markers. Advancements in computer vision have led to the development of markerless motion capture systems yet validation of markerless systems for the upper extremities is limited, especially the hand and fingers. The purpose of this study was to develop and assess a markerless motion capture system capable of tracking hand and finger kinematics. A markerless system using four synchronized webcams was developed. Camera pairs were organized in different angles Centre90° (C/90°), Left45°/Right45° (L45°/R45°), and Centre/Left45° (C/L45°). Motion capture was performed with both marker-based and markerless systems. Twenty healthy participants performed five dynamic hand tasks with and without markers. Three-dimensional joint positions were defined using a musculoskeletal model in OpenSim. No significant differences were observed between C/90° and C/L45° markerless camera pairs and the marker-based system. The L45°/R45° camera pair differed significantly from other markerless pairs in several tasks but agreed with the marker-based system for the index finger during flexion. For most of the fingers, no significant differences were found across the different camera pairs. Correlations and error for the concurrent finger flexion task revealed high consistency among all the camera pairs, with R² above 0.90 and RMSD below 10°, the thumb showed greater variability. The R² and RMSD varied depending on the camera comparison and finger for each task. Markerless motion capture for the hands and fingers is possible with little difference to marker-based systems and is dependent on the camera orientation used. / Thesis / Master of Science in Kinesiology

В области компьютерного зрения оценка позы человека приобретает все большее значение. Это одна из самых привлекательных областей исследований, и она вызывает большой интерес благодаря своей полезности и гибкости в самых разных областях, включая здравоохранение, игры, дополненную реальность, виртуальные тренировки и спорт. На ряду с этим люди все чаще начинают заниматься спортом. А в спорте травмы неизбежны. В данной статье предлагается приложение для оценки выполнения фитнес-упражнений, которое контролирует правильность техники и дает обратную связь по ее исправлению, что помогает уменьшить травматизм при занятиях. Предварительно обученная модель MediaPipe использовалась для оценки поз, по результатам которой вычисляются углы между конкретными суставами. / In the field of computer vision, human pose estimation is becoming increasingly important. This is one of the most attractive areas of research, and it is of great interest due to its usefulness and flexibility in a wide variety of fields, including healthcare, games, augmented reality, virtual training, and sports. Along with this, people are increasingly starting to do sports. And in sports, injuries are inevitable. This article offers an application for evaluating the performance of fitness exercises, which monitors the correctness of the technique and gives feedback on its correction, which helps to reduce injuries during classes. A pre-trained MediaPipe model was used to evaluate poses, based on the results of which the angles between specific joints are calculated.

One major issue that office workers face in their daily lives is a large amount of sedentary behavior. To help alleviate this, researchers at Linköping University are developing a collection of motion games to create natural and motivating active breaks named Liopep. This thesis presents the development and evaluation of one new game being added to Liopep called BoatSim. In BoatSim, the player makes real rowing motions in front of a web-camera to row a virtual boat between various islands, where they can grow crops, raise cows, etc. BoatSim was created in the game engine Godot, with a motion controller powered by Mediapipe Pose. The game was evaluated by repeated playtesting where data was gathered to determine how much movement was achieved by a player interacting with the various different parts of the game, and comparing these to each other.

This thesis aims to create an easy to play exergame that can be used by office workers in theirday-to-day work to battle the long-term consequences of a sedentary lifestyle. A sedentarylifestyle can lead to serious health risks such as obesity and diabetes. This gives exergames anopportunity to be implemented in the daily life of the affected. Exergames have evolved frombeing solely playable from their own console such as Wii or Xbox Kinect to only needing a webcamera, making it accessible and portable for office workers and others all around the globe. Theonly thing left is the actual exergames themselves. The goal of this thesis is to expand an existinglibrary of exergames with a unique boxing game. The research questions are as follows, 1: Howshould the game be designed to incite large body movements? 2: How will achieving higherscores impact the players' movement? Answering research question one will involve a lot of trialand error and creative thinking to come up with a solution that answers the question but alsofeels good to play. Research question two will require user data collected during the gameplay tobe analyzed to see relations between the total movement and the total score. Tracking elbows todetect whether a cube is hit as well as having cubes always spawn on opposite sides is anefficient way to incite large body movements as the player needs to rotate the entire upper bodyand reach further than tracking the wrists would have required. The analyzed user data showedthat there was a linear relation between achieving a higher score and the total movementexercised during the game. Gaps between the right-hand elbow and left-hand elbows’ totalmovement were also found.

Background: A sedentary lifestyle is becoming more common as our society is shift-ing away from physical labour. Many workplaces offer work from home arrangements,schools offer tutoring over the internet and children’s playgrounds, once full of life, aremostly empty. The availability of gaming devices, smartphones and social media havemade a big impact on the way we choose to live. With that comes the challenges of neg-ative health effects on a population level. Gaming has traditionally been thought of as asedentary activity in front of a desk and screen, but the development of exergames andthe rise of gamification has changed our perception of gaming and in some cases beenshown to be directly beneficial for our health. Objectives: A gamification project led byErik Berglund at the department of Computer and Information Sciences at Linköping Uni-versity is investigating if exergames can be enjoyed, give users a feeling of control, andlead to heightened exertion levels. With this in mind, we set out to develop a 2D racingexergame, PhysiKart, controlled by a face-tracking machine algorithm from Google’s Me-diaPipe library. Method: 14 participants tested the game 3-5 times where each sessionlasted 2 minutes. The participants filled out the Exergame Enjoyment Questionnaire andrated their exertion levels on the RPE scale. Results: Most participants found the gameresponsive to the control system and that the scoring system motivated them to continueplaying. However, the users perceived the immersion of the game to be lower than desiredand is believed to be a consequence of the slow pacing and the short rounds of the game. Conclusions: Through the survey it was confirmed that using face-tracking software foran exergame is suitable to achieve low levels of exertion. By changing the control motionsof the game it would be possible to increase the exertion while still utilizing face-tracking.

<p> Body Posture provides enough information regarding the current state of mind of a person. This idea is used to implement a system that provides feedback to lecturers on how engaging the class has been by identifying the attentive levels of students. This is carried out using the posture information extracted with the help of Mediapipe. A novel method of extracting features are from the key points returned by Mediapipe is proposed. Geometric moments aided features classification performs better than the general distances and angles features classification. In order to extend the single person pose classification to multi person pose classification object detection is implemented. Feedback is generated regarding the entire lecture and provided as the output of the system. </p>

The wrist is a body part that can be used during repetitive movements in many work environments. There is a need to measure these movements in order to notice harmful repetitive movements in advance. There are many different ways to measure these movements, such as with the use of a depth camera. The goal of this study is to determine if this can be done with high precision compared to other technologies. In order to determine this, an application was created that used several different technologies and libraries to track and pinpoint the hand’s and forearm’s location in each frame. With these locations, together with timestamps from the frames, the angular velocity of the wrist could be calculated. The recordings were made in several different test cases with factors such as background, clothes and lighting changing in each test. In order to compare the depth cameras values, a golden standard had to be set. The depth camera’s recorded values were compared to the golden standard’s recorded values by displaying the values on a graph and by calculating the root mean squared error as well as the mean absolute error. The results indicated that a depth camera can be used to measure wrist movements relatively accurately, even with more advanced movements relative to this study. The result also showed that the depth camera had problems in some test cases. / Handleden är en kroppsdel som kan användas under repetitiva rörelser i många arbetsmiljöer. Det finns ett behov av att mäta dessa rörelser för att upptäcka skadliga repetitiva rörelser i förväg. Det finns många olika sätt att mäta dessa rörelser, till exempel med hjälp av en djupkamera. Målet med denna studie är att avgöra om detta kan göras med hög precision jämfört med andra teknologier. För att avgöra detta skapades en applikation som använder flera olika teknologier och bibliotek för att spåra och lokalisera handens och underarmens position i varje bildruta. Med hjälp av dessa positioner, tillsammans med tidsstämplar från bildrutorna, kunde vinkelhastigheten för handleden beräknas. Inspelningarna gjordes i flera olika testfall där faktorer som bakgrund, kläder och belysning ändrades i varje test. För att kunna jämföra djupkamerans värden behövdes en referensstandard fastställas. Djupkamerans inspelade värden jämfördes med referensstandardens inspelade värden genom att visa värdena på en graf och beräkna rotmedelkvadratfelet samt medelabsolutfelet. Resultaten indikerade att en djupkamera kan användas för att mäta handledsrörelser relativt noggrant, även med mer avancerade rörelser i förhållande till denna studie. Resultatet visade även att djupkameran hade problem i vissa testfall.