TCRN: A Two-Step Underwater Image Enhancement Network Based on Triple-Color Space Feature Reconstruction

被引:4
作者
Lin, Sen [1 ]
Zhang, Ruihang [1 ]
Ning, Zemeng [1 ]
Luo, Jie [1 ]
机构
[1] Shenyang Ligong Univ, Sch Automation & Elect Engn, Shenyang 110159, Peoples R China
关键词
underwater image enhancement; visual color correction; feature reconstruction; deep learning; QUALITY ASSESSMENT; MODEL; SYSTEM;
D O I
10.3390/jmse11061221
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
The underwater images acquired by marine detectors inevitably suffer from quality degradation due to color distortion and the haze effect. Traditional methods are ineffective in removing haze, resulting in the residual haze being intensified during color correction and contrast enhancement operations. Recently, deep-learning-based approaches have achieved greatly improved performance. However, most existing networks focus on the characteristics of the RGB color space, while ignoring factors such as saturation and hue, which are more important to the human visual system. Considering the above research, we propose a two-step triple-color space feature fusion and reconstruction network (TCRN) for underwater image enhancement. Briefly, in the first step, we extract LAB, HSV, and RGB feature maps of the image via a parallel U-net-like network and introduce a dense pixel attention module (DPM) to filter the haze noise of the feature maps. In the second step, we first propose the utilization of fully connected layers to enhance the long-term dependence between high-dimensional features of different color spaces; then, a group structure is used to reconstruct specific spacial features. When applied to the UFO dataset, our method improved PSNR by 0.21% and SSIM by 0.1%, compared with the second-best method. Numerous experiments have shown that our TCRN brings competitive results compared with state-of-the-art methods in both qualitative and quantitative analyses.
引用
收藏
页数:17
相关论文
共 45 条
[21]   DewaterNet: A fusion adversarial real underwater image enhancement network [J].
Li, Hanyu ;
Zhuang, Peixian .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 2021, 95
[22]   WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images [J].
Li, Jie ;
Skinner, Katherine A. ;
Eustice, Ryan M. ;
Johnson-Roberson, Matthew .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (01) :387-394
[23]   Single underwater image enhancement using integrated variational model [J].
Li, Nan ;
Hou, Guojia ;
Liu, Yuhai ;
Pan, Zhenkuan ;
Tan, Lu .
DIGITAL SIGNAL PROCESSING, 2022, 129
[24]   A Hybrid Framework for Underwater Image Enhancement [J].
Li, Xinjie ;
Hou, Guojia ;
Tan, Lu ;
Liu, Wanquan .
IEEE ACCESS, 2020, 8 :197448-197462
[25]   IPMGAN: Integrating physical model and generative adversarial network for underwater image enhancement [J].
Liu, Xiaodong ;
Gao, Zhi ;
Chen, Ben M. .
NEUROCOMPUTING, 2021, 453 :538-551
[26]   An efficient learning-based method for underwater image enhancement [J].
Lyu, Zhangkai ;
Peng, Andrew ;
Wang, Qingwei ;
Ding, Dandan .
DISPLAYS, 2022, 74
[27]  
Naik A, 2021, AAAI CONF ARTIF INTE, V35, P15853
[28]   Human-Visual-System-Inspired Underwater Image Quality Measures [J].
Panetta, Karen ;
Gao, Chen ;
Agaian, Sos .
IEEE JOURNAL OF OCEANIC ENGINEERING, 2016, 41 (03) :541-551
[29]  
Peng LT, 2022, Arxiv, DOI arXiv:2111.11843
[30]   Generalization of the Dark Channel Prior for Single Image Restoration [J].
Peng, Yan-Tsung ;
Cao, Keming ;
Cosman, Pamela C. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (06) :2856-2868