Browsing by Author "Huang, Yu-Chuan"

Now showing 1 - 2 of 2

A Study on Multiple Wearable Sensors for Activity Recognition
(2017-01-01)
Huang, Yu-Chuan
;
Yi, Chih-Wei
;
Peng, Wen-Chih
;
Lin, Hsing-Chen
;
Huang, Ching-Yu
In the past few years, human activity recognition is an active area of machine learning. The possible applications include daily activity monitoring for elders, exercise and fitness workout assistant systems, life style analysis, etc. In this work, tri-axial accelerometers were worn at the right wrist, left wrist and waist to collect motion data for activity recognition. Three supervised machine learning algorithms including random forests, decision trees and support vector machines were implemented to classify daily activities into running, walking, standing, sitting and dining from inertial data. The purposes of this study are to understand how good the machine learning algorithms can achieve and how the wearing location and number of sensors impact the recognition accuracy. Our results showed that the multi-sensors achieve the accuracy of 81%, and dominant hand sensor achieves the accuracy of 80%, which is 7% higher than non-dominant hand sensor.
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
(2019-01-01)
Huang, Yu-Chuan
;
Liao, I-No
;
Chen, Ching-Hsuan
;
Ik, Ts I-Ui
;
Peng, Wen-Chih
Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. It is still challenging to recognize and position a high-speed and tiny ball accurately from an ordinary video. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learning network is trained to not only recognize the ball image from a single frame but also learn flying patterns from consecutive frames. The network is evaluated on the video of the men's singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and F1-measure reach 99:7%, 97:3%, and 98:5%, respectively. To prevent overfitting, 9 additional videos are partially labeled together with a subset from the previous dataset to implement 10-fold cross-validation, and the precision, recall, and F1-measure are 95:3%, 75:7%, and 84:3%, respectively.