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 2023-05-19 15:45
On-Chip Data Reduction and Object Detection for a Feature Extractable CMOS Image Sensor
Yudai Morikaku (Ritsumeikan Univ.), Ryuichi Ujiie, Daisuke Morikawa, Hideki Shima, Kota Yoshida, Shunsuke Okura (Ritsumeikan Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Society 5.0, in which information from sensors in physical space is analyzed by artificial intelligence (AI) in cyberspace and fed back to physical space, has been proposed. Our research group has proposed an image sensor that can extract features suitable for AI. In this paper, we present object recognition accuracy of the feature data with a deep neural network trained. Furthermore, to reduce the power consumption of the image recognition system, we propose a data reduction method using arithmetic filters and bit reduction in the image sensor chip. According to simulation results, object recognition accuracy is 56.6% even though data amount is reduced by 93% compared to the conventional RGB images.
Keyword (in Japanese) (See Japanese page) 
(in English) CMOS image sensor / Feature Extraction / Object Recognition / Data Reduction / / / /  
Reference Info. ITE Tech. Rep., vol. 47, no. 15, IST2023-16, pp. 19-24, May 2023.
Paper # IST2023-16 
Date of Issue 2023-05-11 (IST, ME) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2023-05-18 - 2023-05-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Sansui Hall, Mie University 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To IST 
Conference Code 2023-05-BioX-SIP-IE-IST-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) On-Chip Data Reduction and Object Detection for a Feature Extractable CMOS Image Sensor 
Sub Title (in English)  
Keyword(1) CMOS image sensor  
Keyword(2) Feature Extraction  
Keyword(3) Object Recognition  
Keyword(4) Data Reduction  
1st Author's Name Yudai Morikaku  
1st Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
2nd Author's Name Ryuichi Ujiie  
2nd Author's Affiliation Nisshinbo Micro Devices Inc. (*)
3rd Author's Name Daisuke Morikawa  
3rd Author's Affiliation Nisshinbo Micro Devices Inc. (*)
4th Author's Name Hideki Shima  
4th Author's Affiliation Nisshinbo Micro Devices Inc. (*)
5th Author's Name Kota Yoshida  
5th Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
6th Author's Name Shunsuke Okura  
6th Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
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 2023-05-19 15:45:00 
Presentation Time 30 minutes 
Registration for IST 
Paper # IST2023-16, ME2023-59 
Volume (vol) vol.47 
Number (no) no.15 
Page pp.19-24 
Date of Issue 2023-05-11 (IST, ME) 

[Return to Top Page]

[Return to ITE Web Page]

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