Electronic Thesis and Dissertation Repository

Degree

Master of Science

Program

Computer Science

Supervisor

Charles X. Ling

Abstract

Most mobile health management applications today require manual input or use sensors like the accelerometer or GPS to record user data. The onboard camera remains underused. We propose an Exercise and Sports Equipment Recognition System (ESRS) that can recognize physical activity equipment from raw image data. This system can be integrated with mobile phones to allow the camera to become a primary input device for recording physical activity. We employ a deep convolutional neural network to train models capable of recognizing 14 different equipment categories. Furthermore, we propose a preprocessing scheme that uses color normalization and denoising techniques to improve recognition accuracy. Our best model is able to achieve a a top-3 accuracy of 83.3% on the test dataset. We demonstrate that our model improves upon GoogLeNet for this dataset, the state-of-the-art network which won the ILSVRC 2014 challenge. Our work is extendable as improving the quality and size of the training dataset can further boost predictive accuracy.


Share

COinS