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 2019-06-13 13:55
Accuracy Improvement of Depth Estimation from a Single Still Image Using Feature Pyramid Network
Yudai Fukuda, Takuro Oki, Ryusuke Miyamoto (Meiji Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Depth estimation from a single shot image have become accurate drastically after emergence of deep
neural networks that show excellent results in several image recognition tasks. An existing scheme attempts to use
not only local features but global features by a feature pyramid composed of various scales of features obtained
from several convolution layers in order to improve the estimation accuracy. However, there is room for accuracy
improvement because generation of a feature pyramid in the scheme is not sophisticated. This paper tries to apply
the Feature Pyramid Network for improve depth estimation in a single shot image, which was first adopted to object
detection. Experimental results using the KITTI dataset showed that RMSE was improved by about 5% by the
proposed scheme and accuracy became better than state-of-the-art schemes when the threshold was 1.25 3 .r
Keyword (in Japanese) (See Japanese page) 
(in English) depth estimation / a single still image / pyramid feature network / deep learning / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee IEICE-SIS IPSJ-AVM 3DMT  
Conference Date 2019-06-13 - 2019-06-14 
Place (in Japanese) (See Japanese page) 
Place (in English) Fukue Culture Center 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Intelligent Multimedia Systems, Applied Enbedded Systems, Three-Dimensional Image Technology (3DIT), etc. 
Paper Information
Registration To IEICE-SIS 
Conference Code 2019-06-SIS-AVM-3DIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Accuracy Improvement of Depth Estimation from a Single Still Image Using Feature Pyramid Network 
Sub Title (in English)  
Keyword(1) depth estimation  
Keyword(2) a single still image  
Keyword(3) pyramid feature network  
Keyword(4) deep learning  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Yudai Fukuda  
1st Author's Affiliation Meiji University (Meiji Univ.)
2nd Author's Name Takuro Oki  
2nd Author's Affiliation Meiji University (Meiji Univ.)
3rd Author's Name Ryusuke Miyamoto  
3rd Author's Affiliation Meiji University (Meiji Univ.)
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 2019-06-13 13:55:00 
Presentation Time 20 minutes 
Registration for IEICE-SIS 
Paper #  
Volume (vol) vol.43 
Number (no)  
Page  
#Pages  
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]
The Institute of Image Information and Television Engineers (ITE), Japan