Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model
Sensors · 2024-06-09 · 24 (12) · 3746
DOI: 10.3390/s24123746 ↗At a glance
Journal article in Sensors, published online on 2024-06-09. Written by Yunho Han and 5 co-authors. Institution: Department of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of Korea. Cited 21 times so far (Crossref); 33 references. The full text is freely available (open access, CC BY 4.0). Funded by: Institute for Information and Communications Technology Promotion, Korea Creative Content Agency, MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center).
Abstract (original language)
In this paper, we propose a lightweight U-net architecture neural network model based on Dark Channel Prior (DCP) for efficient haze (fog) removal with a single input. The existing DCP requires high computational complexity in its operation. These computations are challenging to accelerate, and the problem is exacerbated when dealing with high-resolution images (videos), making it very difficult to apply to general-purpose applications. Our proposed model addresses this issue by employing a two-stage neural network structure, replacing the computationally complex operations of the conventional DCP with easily accelerated convolution operations to achieve high-quality fog removal. Furthermore, our proposed model is designed with an intuitive structure using a relatively small number of parameters (2M), utilizing resources efficiently. These features demonstrate the effectiveness and efficiency of the proposed model for fog removal. The experimental results show that the proposed neural network model achieves an average Peak Signal-to-Noise Ratio (PSNR) of 26.65 dB and a Structural Similarity Index Measure (SSIM) of 0.88, indicating an improvement in the average PSNR of 11.5 dB and in SSIM of 0.22 compared to the conventional DCP. This shows that the proposed neural network achieves comparable results to CNN-based neural networks that have achieved SOTA-class performance, despite its intuitive structure with a relatively small number of parameters.
Subjects
Author keywords
Authors and institutions
- Department of Computer Science and Engineering, Sejong University, Seoul 05006, Republic of Korea.
- Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea.
- Department of Computer Science, Sangmyung University, Seoul 03016, Republic of Korea.
- EXARION, Seoul 05006, Republic of Korea.
ORCID profiles: Yunho Han, Jinyoung Lee
Funding
- Institute for Information and Communications Technology Promotion
- Korea Creative Content Agency
- MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center)
Cite
APA
Han, Y., Kim, J., Lee, J., Nah, J. H., Ho, Y. S., & Park, W. C. (2024). Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model. Sensors, 24(12), 3746. https://doi.org/10.3390/s24123746
Vancouver
Han Y, Kim J, Lee J, Nah JH, Ho YS, Park WC. Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model. Sensors. 2024;24(12):3746. doi:10.3390/s24123746
BibTeX
@article{Han2024,
author = {Han, Yunho and Kim, Jiyoung and Lee, Jinyoung and Nah, Jae-Ho and Ho, Yo-Sung and Park, Woo-Chan},
title = {Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model},
journal = {Sensors},
year = {2024},
volume = {24},
number = {12},
pages = {3746},
doi = {10.3390/s24123746}
}
EUVIMED