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 2019-12-05 13:55
An Circular Road Signs Extraction Method for Accelerating Object Detection System
Fang Yin, Kentaro Katayama, Eiji Yoshida (Fujitsu Lab)
Abstract (in Japanese) (See Japanese page) 
(in English) Cyber-physical system (CPS) becomes realistic with the development of sensing technology and pattern recognition technology. There is a typical example that dynamic map could display the traffic information dynamically. In dynamic map construction, objects are recognized based on the information from each vehicle’s camera and sensor, and recognition results from each vehicle are aggregated and mapped dynamically. Since objects recognition requires a large amount of computing resources, there is a problem that memory capacity and processing capability are insufficient while performing all processing by edge device such as in-vehicle computer. Furthermore, low bandwidth is also a problem while transmitting a large amount of data in the data transfer architecture from in-vehicle to cloud. Therefore, our research efforts focus on the architecture which extracts the shape of objects by edge device, and recognize objects by cloud to reduce network bandwidth. This paper reports the results of proposed fast circular road signs extraction method by the edge device. We extract a candidate region by color filter in HSV space, and detect the center of a circle by only 4 lines input buffer. The experimental result shows our proposed method is 11.5 times faster than the conventional one.
Keyword (in Japanese) (See Japanese page) 
(in English) Cyber-Physical System / Edge Computing / Image Processing / Artificial Intelligence / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2019-12-05 - 2019-12-06 
Place (in Japanese) (See Japanese page) 
Place (in English) Aiina Center 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image coding, Communications and streaming technologies, etc. 
Paper Information
Registration To IEICE-IE 
Conference Code 2019-12-IE-CS-AVM-BCT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) An Circular Road Signs Extraction Method for Accelerating Object Detection System 
Sub Title (in English)  
Keyword(1) Cyber-Physical System  
Keyword(2) Edge Computing  
Keyword(3) Image Processing  
Keyword(4) Artificial Intelligence  
1st Author's Name Fang Yin  
1st Author's Affiliation Fujitsu Laboratories LTD (Fujitsu Lab)
2nd Author's Name Kentaro Katayama  
2nd Author's Affiliation Fujitsu Laboratories LTD (Fujitsu Lab)
3rd Author's Name Eiji Yoshida  
3rd Author's Affiliation Fujitsu Laboratories LTD (Fujitsu Lab)
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 ()
Date Time 2019-12-05 13:55:00 
Presentation Time 25 
Registration for IEICE-IE 
Paper #  
Volume (vol) ITE-43 
Number (no)  
#Pages ITE- 
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]

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