Adaptative machine vision with microsecond-level accurate perception beyond human retina
Nature Communications · 24.07.2024 · 15 (1)
DOI: 10.1038/s41467-024-50488-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nature Communications, online erschienen am 24.07.2024. Verfasst von Ling Li und 15 weiteren Autor:innen. Beteiligte Einrichtung: School of Semiconductor Science and Technology, South China Normal University, Foshan, 528225, P.R. China. Hauptthemen laut MEDLINE: Retina, Neural Networks, Computer. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Guangdong Province (Guangdong Natural Science Foundation).
Abstract (Originalsprache)
Visual adaptive devices have potential to simplify circuits and algorithms in machine vision systems to adapt and perceive images with varying brightness levels, which is however limited by sluggish adaptation process. Here, the avalanche tuning as feedforward inhibition in bionic two-dimensional (2D) transistor is proposed for fast and high-frequency visual adaptation behavior with microsecond-level accurate perception, the adaptation speed is over 10 4 times faster than that of human retina and reported bionic sensors. As light intensity changes, the bionic transistor spontaneously switches between avalanche and photoconductive effect, varying responsivity in both magnitude and sign (from 7.6 × 10 4 to −1 × 10 3 A/W), thereby achieving ultra-fast scotopic and photopic adaptation process of 108 and 268 μs, respectively. By further combining convolutional neural networks with avalanche-tuned bionic transistor, an adaptative machine vision is achieved with remarkable microsecond-level rapid adaptation capabilities and robust image recognition with over 98% precision in both dim and bright conditions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Semiconductor Science and Technology, South China Normal University, Foshan, 528225, P.R. China.
- School of Electronic Engineering, Chaohu University, Hefei, 238000, China.
- National Key Laboratory of Science and Technology on Reliability Physics and Application of Electronic Component, China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, 510610, Chi…
- College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China.
- Guangdong Provincial Key Laboratory of Chip and Integration Technology, Guangzhou, 510631, P.R. China.
- School of Semiconductor Science and Technology, South China Normal University, Foshan, 528225, P.R. China. njhuo@m.scnu.edu.cn.
ORCID-Profile: Ling Li, Nengjie Huo
Förderung
- Natural Science Foundation of Guangdong Province (Guangdong Natural Science Foundation)
Zitieren
APA
Li, L., Li, S., Wang, W., Zhang, J., Sun, Y., Deng, Q., Zheng, T., Lu, J., Gao, W., Yang, M., Wang, H., Pan, Y., Liu, X., Yang, Y., Li, J., & Huo, N. (2024). Adaptative machine vision with microsecond-level accurate perception beyond human retina. Nature Communications, 15(1). https://doi.org/10.1038/s41467-024-50488-6
Vancouver
Li L, Li S, Wang W, Zhang J, Sun Y, Deng Q, et al. Adaptative machine vision with microsecond-level accurate perception beyond human retina. Nature Communications. 2024;15(1). doi:10.1038/s41467-024-50488-6
BibTeX
@article{Li2024,
author = {Li, Ling and Li, Shasha and Wang, Wenhai and Zhang, Jielian and Sun, Yiming and Deng, Qunrui and Zheng, Tao and Lu, Jianting and Gao, Wei and Yang, Mengmeng and Wang, Hanyu and Pan, Yuan and Liu, Xueting and Yang, Yani and Li, Jingbo and Huo, Nengjie},
title = {Adaptative machine vision with microsecond-level accurate perception beyond human retina},
journal = {Nature Communications},
year = {2024},
volume = {15},
number = {1},
doi = {10.1038/s41467-024-50488-6}
}
EUVIMED