ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2023-02-21 15:30
Evaluating The Effectiveness of Data Augmentation for Learning TrackNetV2
Yushan Wang (TMU), Shuhei Tarashima (NTT Com), Norio Tagawa (TMU)
Abstract (in Japanese) (See Japanese page) 
(in English) Data augmentation has been widely used in a variety of deep learning tasks, mostly with a positive impact on the results. Nevertheless, for the shuttlecock detection task, data augmentation has not been applied to state-of-the-art (SOTA) algorithms. In this work we apply data augmentation to a state-of-the-art shuttlecock detection algorithm, TrackNetV2, to evaluate its effectiveness. Data augmentation has usually been applied to a single frame, but in our problem, consecutive frames extracted from a video need to be an input. Therefore, in this work we consider multi-frame data augmentation: Specifically, we apply the same transformation with the same parameters to consecutive frames being fed at the same time in online manner. Experimental results on a public shuttlecock detection dataset demonstrates the effectiveness of our approach: We got improvements with respect to the precision, recall, F1 score and Accuracy from 84.52%, 81.65%, 83.06%, 75.48% to 86.85%, 81.78%, 84.24%, 77.01%.
Keyword (in Japanese) (See Japanese page) 
(in English) Data augmentation / deep learning / shuttlecock detection / / / / /  
Reference Info. ITE Tech. Rep., vol. 47, no. 6, ME2023-36, pp. 81-84, Feb. 2023.
Paper # ME2023-36 
Date of Issue 2023-02-14 (MMS, ME, AIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2023-02-21 - 2023-02-22 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2023-02-MMS-ME-AIT-IE-ITS 
Language English 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Evaluating The Effectiveness of Data Augmentation for Learning TrackNetV2 
Sub Title (in English)  
Keyword(1) Data augmentation  
Keyword(2) deep learning  
Keyword(3) shuttlecock detection  
1st Author's Name Yushan Wang  
1st Author's Affiliation Tokyo Metropolitan University (TMU)
2nd Author's Name Shuhei Tarashima  
2nd Author's Affiliation NTT Communications Corporation (NTT Com)
3rd Author's Name Norio Tagawa  
3rd Author's Affiliation Tokyo Metropolitan University (TMU)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2023-02-21 15:30:00 
Presentation Time 15 minutes 
Registration for ME 
Paper # MMS2023-16, ME2023-36, AIT2023-16 
Volume (vol) vol.47 
Number (no) no.6 
Page pp.81-84 
Date of Issue 2023-02-14 (MMS, ME, AIT) 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan