PGT-Net: A Physics-Guided Transformer–CNN Hybrid Network for Low-Light Image Enhancement and Object Detection in Traffic Scenes
Journal of Imaging · 28.04.2026 · 12 (5) · 191
DOI: 10.3390/jimaging12050191 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 28.04.2026. Verfasst von Bin Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450002, China. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In autonomous driving and intelligent transportation systems, the degradation of image quality under low-light conditions severely impacts the reliability of subsequent object detection. Existing methods predominantly employ data-driven deep learning models for image enhancement, often lacking physical interpretability and struggling to maintain robustness in complex lighting-varying traffic scenarios. To address this, this paper proposes a Physically Guided Transformer–CNN Hybrid Network (Physically Guided Transformer–CNN Hybrid Network, PGT-Net) for end-to-end joint optimization of low-light enhancement and object detection. PGT-Net innovatively integrates the atmospheric scattering physical model with deep learning architecture: first, a learnable physical guidance branch estimates the scene’s atmospheric illumination map and transmittance map, providing explicit physical priors for the network; second, a dual-branch enhancement backbone is designed, where the local CNN branch (based on an improved UNet) restores fine textures, while the Global Transformer Branch (based on Swin Transformer) models long-range dependencies to correct global uneven illumination, with features adaptively combined via a Physical Fusion Module to ensure enhancement results align with physical laws while retaining rich visual features; finally, the enhanced images are directly fed into a lightweight detection head (e.g., YOLOv7) for joint training and optimization. Comprehensive experiments on public datasets (ExDark, BDD100K-night, etc.) demonstrate that PGT-Net significantly outperforms mainstream methods (e.g., RetinexNet, KinD, Zero-DCE) in both low-light image enhancement quality (PSNR/SSIM) and object detection accuracy (mAP), while maintaining high inference efficiency. This research offers an interpretable, high-performance solution for visual perception tasks under adverse lighting conditions, holding strong theoretical significance and practical value.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450002, China.
- XJ Electric Co., Ltd., Xuchang 461000, China.
- State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University (Baoding), Baoding 071003, China.
- School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China.
- State Key Laboratory of Target Vulnerability Assessment, Luoyang 471023, China.
ORCID-Profile: Wei She
Zitieren
APA
Chen, B., Qiao, J., Li, B., Liu, S., & She, W. (2026). PGT-Net: A Physics-Guided Transformer–CNN Hybrid Network for Low-Light Image Enhancement and Object Detection in Traffic Scenes. Journal of Imaging, 12(5), 191. https://doi.org/10.3390/jimaging12050191
Vancouver
Chen B, Qiao J, Li B, Liu S, She W. PGT-Net: A Physics-Guided Transformer–CNN Hybrid Network for Low-Light Image Enhancement and Object Detection in Traffic Scenes. Journal of Imaging. 2026;12(5):191. doi:10.3390/jimaging12050191
BibTeX
@article{Chen2026,
author = {Chen, Bin and Qiao, Jian and Li, Baowei and Liu, Shipeng and She, Wei},
title = {PGT-Net: A Physics-Guided Transformer–CNN Hybrid Network for Low-Light Image Enhancement and Object Detection in Traffic Scenes},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {5},
pages = {191},
doi = {10.3390/jimaging12050191}
}
EUVIMED