EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism

Rongfeng Zhou, Ping Li, Mingyang Zhang, Qingyao Lin, Yuanyuan Wang, Xuesheng Bian, Feng Zhou, Rugang Wang

IEEE Access · 2024 · 12 · 45773-45784

DOI: 10.1109/access.2024.3381514 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Rongfeng Zhou und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Jiangsu Graduate Practical Innovation Project, Natural Science Foundation of China, Major Project of Natural Science Research of Jiangsu Province Colleges and Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming at the conventional low-light enhancement algorithms for low-light image enhancement with problems of loss of details, low contrast and low color saturation, a detection algorithm called CE-Retinex(Cross Expansion Retinex) by incorporating the cross-mixed attention mechanism and the receptive field expansion mechanism is proposed and demonstrated for the first time. It mainly consists of three parts: initial module, optimization module, and detail restoration. Firstly, in the initial module, the image is decomposed into reflectance and illuminance using two different U-shaped networks with multiple layers of convolution. Secondly, in the optimization network module, the image brightness is enhanced using multi-scale lighting mechanism. Denoising is also performed. After that, a multi-layer convolutional fusion cross-mixed attention mechanism is used to filter the information from the four dimensions of channel, spatial, vertical and horizontal attention, so that it can be effectively reduce the negative effects of the low-light image enhancement process. In the detail restoration module, the receptive field expansion mechanism is utilized to enhance the receptive field and strengthen the detail information. Also, the color consistency loss function is used to recover colors in the loss function. The CE-Retinex algorithm was experimentally analyzed on the LOL dataset, and the PSNR of the CE-Retinex algorithm was 25.33, and the NIQE was 3.37, and the subjective feelings and objective evaluation indicators have effectively improved. So the proposed algorithm could be effectively solve the problems of loss of detail, low contrast, and low color saturation in low-light image enhancement.

Förderung

  • Jiangsu Graduate Practical Innovation Project
  • Natural Science Foundation of China
  • Major Project of Natural Science Research of Jiangsu Province Colleges and Universities
  • Natural Science Research Project of Jiangsu University

Zitieren

APA

Zhou, R., Li, P., Zhang, M., Lin, Q., Wang, Y., Bian, X., Zhou, F., & Wang, R. (2024). A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism. IEEE Access, 12, 45773-45784. https://doi.org/10.1109/access.2024.3381514

Vancouver

Zhou R, Li P, Zhang M, Lin Q, Wang Y, Bian X, et al. A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism. IEEE Access. 2024;12:45773-45784. doi:10.1109/access.2024.3381514

BibTeX
@article{Zhou2024,
  author = {Zhou, Rongfeng and Li, Ping and Zhang, Mingyang and Lin, Qingyao and Wang, Yuanyuan and Bian, Xuesheng and Zhou, Feng and Wang, Rugang},
  title = {A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {45773--45784},
  doi = {10.1109/access.2024.3381514}
}
Kostenlos starten →