On-chip data reduction and object detection for a feature extractable CMOS image sensor

Yudai Morikaku; Ryuichi Ujiie; Daisuke Morikawa; Hideki Shima; Kota Yoshida; Shunsuke Okura

doi:10.1117/12.3018344

2 May 2024 On-chip data reduction and object detection for a feature extractable CMOS image sensor

Yudai Morikaku, Ryuichi Ujiie, Daisuke Morikawa, Hideki Shima, Kota Yoshida, Shunsuke Okura

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 1316413 (2024) https://doi.org/10.1117/12.3018344
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

Toward the image recognition in IoT society, we propose data reduction scheme of the feature data extracted in a CMOS image sensor and present simulation results of object recognition of the feature data. We evaluated object recognition accuracy of the feature data based a YOLOX trained with simulated feature dataset. According to simulation results, object recognition accuracy was 56.6% even though data amount is reduced by 97.7% compared to the conventional RGB color images.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yudai Morikaku, Ryuichi Ujiie, Daisuke Morikawa, Hideki Shima, Kota Yoshida, and Shunsuke Okura "On-chip data reduction and object detection for a feature extractable CMOS image sensor", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 1316413 (2 May 2024); https://doi.org/10.1117/12.3018344

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available