On-Chip Data Reduction and Object Detection for a Feature-Extractable CMOS Image Sensor

In order to improve image recognition technologies in an IoT environment, we propose a data reduction scheme for a feature-extractable CMOS image sensor and present simulation results for object recognition using feature data. We evaluated the accuracy of the simulated feature data in object recogni...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2024-11, Vol.13 (21), p.4295
Main Authors: Morikaku, Yudai, Ujiie, Ryuichi, Morikawa, Daisuke, Shima, Hideki, Yoshida, Kota, Okura, Shunsuke
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
CMOS
Color imagery
Complementary metal oxide semiconductors
Datasets
Evaluation
Object recognition
Pharmaceutical industry
Sensors
Signal processing
Transistors
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to improve image recognition technologies in an IoT environment, we propose a data reduction scheme for a feature-extractable CMOS image sensor and present simulation results for object recognition using feature data. We evaluated the accuracy of the simulated feature data in object recognition based on YOLOX trained with a feature dataset. According to our simulation results, the obtained object recognition accuracy was 56.6% with the large-scale COCO dataset, even though the amount of data was reduced by 97.7% compared to conventional RGB color images. When the dataset was replaced with the RAISE RAW image dataset for more accurate simulation, the object recognition accuracy improved to 76.3%. Furthermore, the feature-extractable CMOS image sensor can switch its operation mode between RGB color image mode and feature data mode. When the trigger for switching from feature data mode to RGB color image mode was set to the detection of a large-sized person, the feature data achieved an accuracy of 93.5% with the COCO dataset.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics13214295