Team Members:

  1. Habiba Hegazy [ CV ]
  2. Mohammed Abdelsalam [ CV ]
  3. Moustafa Hussien [ CV ]
  4. Seif Elmosalamy [ CV ]

 

Supervisors:

 

  • Dr Ayman Ezzat

Email: ayman@fcih.net

  • Dr Ayman Nabil

Email: ayman.nabil@miuegypt.edu.eg

  • Eng. Youmna Ibrahim

Email: yomna.ibrahim@miuegypt.edu.eg

 
Project Description:

         The main idea of this project (TrainIt) is to help Table Tennis players to achieve the highest accuracy in their plays. TrainIt should provide quick results within real-time and high accuracy to the strokes played by the Table Tennis player. We aim to detect several stroke types in table tennis like forehand/backhand push, forehand/backhand topspin and forehand/backhand drive. We would work in inheriting wearable device with a camera to detect the most accurate and achievable movements made from the movements that had some errors. The mistakes done will be based on the movement of different joints in the body such as the wrist, elbow, shoulders and waist.

Field of Knowledge: Machine Learning, Mobile Application, Augmented Reality, and Artificial Intelligence.

Tools: C# for Kinect SDK and Unity implementation, MySQL for database creation, Android for development of mobile application, Python for Inner server implementation, PHP For connection to database from python and android and Unity for creating the Augmented Reality.

Project Different Phases:

          1. Proposal Document

 

  • Proposal Demo Video:

 

          2. Software Requirements Specification (SRS)

         

          3. Software Requirements Specification (SDD)

 

          4. Final Thesis

Player’s Feedback on the System:

 

Papers submitted and published:

  • Elsevier conference paper, at ANT conference in Poland

Aim: Introduce the idea of the usage of IR depth camera in detecting and classifying table tennis strokes. Also, the first paper to work on different joints in table tennis field and detecting mistakes.

Abstract: Table tennis is a complex sport with a distinctive style of play. Due to the rising interest in this sport in the past years, attempts have been targeted towards enhancing the training experience and quality through various techniques. Technology has been used to support training sessions for table tennis players before, with a focus on players’ performance measures rather than technique. In this paper, we propose a methodology based on an IR depth camera for detecting and classifying the efficiency of strokes performed by players in order to enhance the training experience. Our system is to based on analyzing depth data collected from an IR depth camera and recognized using fastDTW algorithm. The results show an average accuracy of 88% – 100%. This is the first paper to address the usage of IR depth camera on the table tennis player to detect and classify the strokes played.

Publish URL: https://www.sciencedirect.com/science/article/pii/S1877050920305639?via%3Dihub

Paper Draft: ANT_Conference

  • Elsevier conference paper, at MobiSPC conference in Leuven, Belgium

Aim: To extend our dataset (960 strokes) from different players. Also, to examine different algorithms based on User dependent and independent classification experiment’s and apply Analysis of variance (ANOVA) tests on the algorithms.

Abstract: Assisting table tennis coaching using modern technologies is one of the most trending researches in the sports field. In this paper, we present a methodology to identify and recognize the wrong strokes executed by players to improve the training experience by the usage of an IR depth camera. The proposed system focuses mainly on the errors in table tennis player’s strokes and evaluating them efficiently and based on the analysis and classification of the data obtained from an IR depth camera using multiple algorithms. This paper is a continuation of our previous work, focusing more on identifying common wrong strokes in table tennis by utilizing IR depth camera classification algorithms. The classification of the mistakes that took place while playing can be classified based on each player dependently or independently for all players.

Publish URL: https://www.sciencedirect.com/science/article/pii/S1877050920305639?via%3Dihub

Paper Draft: MobiSPC_Conference

  • Journal of Ubiquitous Systems and Pervasive Networks

Aim: To extend our dataset (1500 strokes) from different players. Also, to extend the system by adding a notification system using Augmented Reality and make a usability study on the system made.

Abstract: Table tennis game is based on the speed of the player’s response to different attacks and defence strokes. A way to enhance the player’s performance and technique while training is to update the player with the mistakes in real-time. This paper presents a system that focuses on detecting the correct and wrong strokes within the following stroke types: Forehand drive, backhand drive, and forehand topspin. By the usage of Augmented Reality, the system helps the players to get their results and direction easily using AR-based mobile application when practising real-time. A usability study has been made to measure the learning style of the players by letting the players train on different strokes with the system. Moreover, an experiment has been done to measure the efficiency of the application and compare different algorithms to overview their performance in identifying the strokes based on accuracy and time taken.

Publish URL: 10.5383/JUSPN.13.01.001

Paper Draft: JUSPN_Journal