SMU Guildhall Graduate Catalog Spring 2020 — Cohort 28 | Page 80

Adam Riley Software Development « Gameplay Data Extraction for League of Legends Through Computer Vision Game analytics plays an important role esports much easier. This system adds and electronic sports (esports) by getting like football or basketball. in guiding teams in both traditional sports a better understanding of the opponent’s strategies. Unfortunately, not every esport This thesis brings these two worlds collect and analyze the data needed for extract, collect, and analyze gameplay game has a reliable method to extract, team and player analysis. For instance, League of Legends, a popular Multiplayer Online Battle Arena (MOBA) video game, does not provide the ability to track together and presents a methodology to data from League of Legends match videos via an automated computer vision system. gameplay data like players’ position, hit I tracked the positions of players on having to watch and manually encode the Convolutional Neural Networks (CNNs) points and mana within the game without entire match. On the other hand, machine learning is taking the world stage by using object detection to help Artificial Intelligence (AI) learn the features within images to make analysis of various traditional games and 80 various visuals to games watched at home SOFTWARE DEVELOPMENT the minimap using object detection via and encoded them into a data file that can accelerate the work of analysts and will thus lead to more informed and decisive strategies.