Presenter(s)
Yousef Idris Yousef Mohamad
Files
Download Project (1.5 MB)
Description
Automatic event recognition based on human action is both interesting and valuable research topic in the field of computer vision and deep learning. With the rapid increase and the explosive spread of data which is being captured momentarily, the need of fast and precise access to the right information has become challenging task with considerable importance for multiple practical applications, e.g., image and video search, sport data analysis, healthcare monitoring applications, monitoring and surveillance systems for indoor and outdoor activities, and video captioning. This research, part of my master’s thesis, develops an adaptive content-aware convolution neural network with the capability of analyzing, recognizing and interpreting the sport event in the Olympic games based on human action. 20 of the 33 sports scheduled for inclusion in the Olympic Games Tokyo 2020 will be included in the collected data set to evaluate the proposed method. This method combines convolutional neural network (CNN) and transfer learning (fine-tuning method) to potentially achieve best performance with high accuracy and precision of the event recognition.
Publication Date
4-22-2020
Project Designation
Course Project
Primary Advisor
Van Tam Nguyen
Primary Advisor's Department
Computer Science
Keywords
Stander Symposium project, College of Arts and Sciences
Recommended Citation
"Olympic Games Event Recognition via Adaptive Convolutional Neural Networks" (2020). Stander Symposium Projects. 1929.
https://ecommons.udayton.edu/stander_posters/1929
![Olympic Games Event Recognition via Adaptive Convolutional Neural Networks](https://ecommons.udayton.edu/stander_posters/2929/thumbnail.jpg)
Comments
This project reflects research conducted as part of a course project designed to give students experience in the research process. Course: CPS 595 01