Bassel Emad, Omar Atef, , Yahya Shams, Ahmed ElKerdany

Publishing Date

5th March 2020


Smart coaching in martial arts is one of the recent research areas in Human Motion Analysis. Numerous moves are performed incorrectly during the performance. In this project we offer a system that will record the Players’ movements using IR (Infrared) camera sensor, store the data in a database, pre-process the data, classify the data using F-DTW (Fast Dynamic Time Warping) and then show the users an accurate report that contains every movement the player had done, their mistakes and how to improve their performance the next time. This approach focuses on the Karate Kata 1 (Hein Shodan) moves. The system has reached an accuracy of 93.65% in classifying the moves and an incorrect version of the moves that involved a common mistake.

1.1 Purpose

This Software Design Document purpose is to present fully detailed description of iKarate System Architecture, and to provide the purpose of implementing this application with full definition of functional requirements and showing the functionality of each component and their interaction together.

1.2 Scope

The scope of the system is to provide Karate coaches and players a system that will help them in the training and judging. For the coaches: the system helps them by providing the progress of their students in a report and the mistakes they made while performing. For the players: the system can be used to train without the coach by providing appropriate feedback that helps them master the movements.

1.3 Overview

The main goal of this project is to capture the moves of the performers in real time, analyse those moves and give them a feedback report to enhance their technique or alert them if they are performing a move or a stance incorrectly. One of the challenges we faced while comparing and analysing the captured motion, is that we should take into consideration that the activities might be performed with different speed, body proportions such as (Limbs length) and initial position of the students. Another challenge is the real-time feedback, giving the users a feedback and a report on their moves whether it was right or not in real-time is essentially important after the move is performed. The report includes tips on how to execute the move correctly the next time.

1.4 Intended audience

Lorem ipsum dolor sit amet, at mei dolore tritani repudiandae. In his nemore temporibus consequuntur, vim ad prima vivendum consetetur. Viderer feugiat at pro.