EUVIMEDEUVIMED entdecken
Open Access

Color and orientation feature-attention sensors for efficient recognition

Hongzhao Wu iD, Xiangwei Su, Cheng Zhang, Tianjiao Zhang, Yiqi Chen, Zheng Bian, Xinlong Zeng, Chaokai Zhu, Maoxin Tian iD, Jialei Miao, Caijing Liang, Yang Xu iD und 3 weitere

Science Advances · 31.07.2026 · 12 (31)

DOI: 10.1126/sciadv.aeg8598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 31.07.2026. Verfasst von Hongzhao Wu und 14 weiteren Autor:innen. Beteiligte Einrichtung: College of Integrated Circuits, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 310027, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, National key R&D program of China, Research Grant Council of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A key challenge in visual search is that target objects defined by specific features are often mixed with distractors. This demands intelligent vision systems capable of performing selective feature acquisition instead of randomly or exhaustively scanning the environment. Here, we report a feature-attention vision sensor that integrates a semantic and geometric “dual-attention” mechanism directly at the hardware level. The sensor features reconfigurable spectral responsivity from the visible to near-infrared range, enabling tunable color attention with a spectral rejection ratio of up to 2 × 10 4 . Furthermore, we implement tunable orientation attention through an intensity-responsivity matrix. In automatic driving, the feature-attention vision sensor recognizes no stopping sign with 99.52% accuracy comparable to RGB cameras while reducing data generation by 66.7%. This approach mimics this biological “sense-only-the-useful” strategy, eliminating the need for bulky optical filters and postprocessing algorithms and offering a promising pathway for the realization of compact, resource-efficient intelligent vision systems.

Autor:innen und Institutionen

  • College of Integrated Circuits, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 310027, China.
  • School of Physical Science and Technology, Yangzhou University, Yangzhou 225002, China.
  • Department of Applied Physics, The Hong Kong Polytechnic University, Hong Kong 999077, China.

ORCID-Profile: Hongzhao Wu, Maoxin Tian, Yang Xu, Bin Yu, Yang Chai, Yuda Zhao

Förderung

  • National Natural Science Foundation of China
  • National key R&D program of China
  • Research Grant Council of Hong Kong

Zitieren

APA

Wu, H., Su, X., Zhang, C., Zhang, T., Chen, Y., Bian, Z., Zeng, X., Zhu, C., Tian, M., Miao, J., Liang, C., Xu, Y., Yu, B., Chai, Y., & Zhao, Y. (2026). Color and orientation feature-attention sensors for efficient recognition. Science Advances, 12(31). https://doi.org/10.1126/sciadv.aeg8598

Vancouver

Wu H, Su X, Zhang C, Zhang T, Chen Y, Bian Z, et al. Color and orientation feature-attention sensors for efficient recognition. Science Advances. 2026;12(31). doi:10.1126/sciadv.aeg8598

BibTeX
@article{Wu2026,
  author = {Wu, Hongzhao and Su, Xiangwei and Zhang, Cheng and Zhang, Tianjiao and Chen, Yiqi and Bian, Zheng and Zeng, Xinlong and Zhu, Chaokai and Tian, Maoxin and Miao, Jialei and Liang, Caijing and Xu, Yang and Yu, Bin and Chai, Yang and Zhao, Yuda},
  title = {Color and orientation feature-attention sensors for efficient recognition},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {31},
  doi = {10.1126/sciadv.aeg8598}
}
Kostenlos starten →