Improved HVI-CIDNet model for enhancing coal-gangue images in complex underground environments
Measurement Science and Technology · 29.05.2026 · 37 (22) · 226003
DOI: 10.1088/1361-6501/ae70cc ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 02.06.2026. Verfasst von Lei Si und 6 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The environment of underground coal mines is characterized by low-illumination intensity and high dust concentration, causing captured coal-gangue images to suffer from problems such as low contrast, blurred details, and color distortion. These degradation issues severely restrict the performance of automatic coal-gangue recognition and sorting systems. To address these challenges, this paper proposes a coal-gangue image enhancement algorithm based on an improved HVI-CIDNet model. Targeting the uneven lighting and high-dust environment, the proposed method utilizes the HVI color space to effectively decouple the intensity and color information of coal-gangue images, constructing a dual-branch decoupled deep learning network. A learnable dual-residual cross-attention block is designed to optimize feature fusion. Furthermore, by introducing a frequency domain enhancement block and optimizing the branch structure, the network synergistically enhances the recovery of weak texture details on coal-gangue surfaces. Simultaneously, a dual color space constraint loss is integrated to ensure the stability of enhancement effects under complex environmental conditions. Experimental results demonstrate that the proposed algorithm achieves a peak signal-to-noise ratio of 32.498 dB, structural similarity of 0.933, and learned perceptual image patch similarity of 0.126 on a self-constructed coal-gangue dataset, outperforming mainstream comparative methods in all metrics. Moreover, the enhanced images significantly improve the accuracy of downstream detection models, achieving average detection accuracies of 89.2% and 95.6% on vision transformer and YOLOv12 models, respectively. This research provides an effective solution for coal-gangue image enhancement under complex working conditions.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Si, L., Ji, F., Liu, Y., Wang, Z., Wei, D., Gu, J., & Li, X. (2026). Improved HVI-CIDNet model for enhancing coal-gangue images in complex underground environments. Measurement Science and Technology, 37(22), 226003. https://doi.org/10.1088/1361-6501/ae70cc
Vancouver
Si L, Ji F, Liu Y, Wang Z, Wei D, Gu J, et al. Improved HVI-CIDNet model for enhancing coal-gangue images in complex underground environments. Measurement Science and Technology. 2026;37(22):226003. doi:10.1088/1361-6501/ae70cc
BibTeX
@article{Si2026,
author = {Si, Lei and Ji, Fukang and Liu, Yang and Wang, Zhongbin and Wei, Dong and Gu, Jinheng and Li, Xin},
title = {Improved HVI-CIDNet model for enhancing coal-gangue images in complex underground environments},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {22},
pages = {226003},
doi = {10.1088/1361-6501/ae70cc}
}
EUVIMED