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

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.

[1]  Weiyu Zhao,et al.  A Two-Stage Network Based on Transformer and Physical Model for Single Underwater Image Enhancement , 2023, Journal of Marine Science and Engineering.

[2]  Jiangbin Zheng,et al.  Cross-domain learning for underwater image enhancement , 2022, Signal Process. Image Commun..

[3]  Zhenkuan Pan,et al.  Single underwater image enhancement using integrated variational model , 2022, Digit. Signal Process..

[4]  Jingchun Zhou,et al.  Underwater image enhancement method with light scattering characteristics , 2022, Comput. Electr. Eng..

[5]  Dandan Ding,et al.  An efficient learning-based method for underwater image enhancement , 2022, Displays.

[6]  Q. M. Jonathan Wu,et al.  Underwater Image Co-Enhancement With Correlation Feature Matching and Joint Learning , 2022, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  S. Pei,et al.  Domain Adaptation for Underwater Image Enhancement via Content and Style Separation , 2022, IEEE Access.

[8]  Kai Hu,et al.  An Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning , 2022, Journal of Marine Science and Engineering.

[9]  Leonardo Vanneschi,et al.  Structural similarity index (SSIM) revisited: A data-driven approach , 2021, Expert Syst. Appl..

[10]  Xin Wang,et al.  WSUIE: Weakly Supervised Underwater Image Enhancement for Improved Visual Perception , 2021, IEEE Robotics and Automation Letters.

[11]  Junhui Hou,et al.  Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding , 2021, IEEE Transactions on Image Processing.

[12]  Peixian Zhuang,et al.  DewaterNet: A fusion adversarial real underwater image enhancement network , 2021, Signal Process. Image Commun..

[13]  Ankita Naik,et al.  Shallow-UWnet : Compressed Model for Underwater Image Enhancement , 2021, AAAI.

[14]  Xiaodong Liu,et al.  IPMGAN: Integrating physical model and generative adversarial network for underwater image enhancement , 2020, Neurocomputing.

[15]  Hanyu Li,et al.  Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network , 2020, IEEE Journal of Oceanic Engineering.

[16]  Zhiqiang Wei,et al.  Underwater image enhancement based on conditional generative adversarial network , 2020, Signal Process. Image Commun..

[17]  Fatih Murat Porikli,et al.  Underwater scene prior inspired deep underwater image and video enhancement , 2020, Pattern Recognit..

[18]  Xiaodong Xie,et al.  FFA-Net: Feature Fusion Attention Network for Single Image Dehazing , 2019, AAAI.

[19]  Junaed Sattar,et al.  Fast Underwater Image Enhancement for Improved Visual Perception , 2019, IEEE Robotics and Automation Letters.

[20]  S. Kwong,et al.  An Underwater Image Enhancement Benchmark Dataset and Beyond , 2019, IEEE Transactions on Image Processing.

[21]  Ke Gu,et al.  Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Pamela C. Cosman,et al.  Generalization of the Dark Channel Prior for Single Image Restoration , 2018, IEEE Transactions on Image Processing.

[23]  Yan Wang,et al.  An imaging-inspired no-reference underwater color image quality assessment metric , 2017, Comput. Electr. Eng..

[24]  Nor Ashidi Mat Isa,et al.  Automatic system for improving underwater image contrast and color through recursive adaptive histogram modification , 2017, Comput. Electron. Agric..

[25]  Jie Li,et al.  WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images , 2017, IEEE Robotics and Automation Letters.

[26]  Chen Gao,et al.  Human-Visual-System-Inspired Underwater Image Quality Measures , 2016, IEEE Journal of Oceanic Engineering.

[27]  Mario Fernando Montenegro Campos,et al.  Underwater Depth Estimation and Image Restoration Based on Single Images , 2016, IEEE Computer Graphics and Applications.

[28]  Arcot Sowmya,et al.  An Underwater Color Image Quality Evaluation Metric , 2015, IEEE Transactions on Image Processing.

[29]  Zhou Wang,et al.  A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images , 2015, IEEE Signal Processing Letters.

[30]  Jason Jianjun Gu,et al.  No-reference blur assessment based on edge modeling , 2015, J. Vis. Commun. Image Represent..

[31]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[32]  G. Buchsbaum A spatial processor model for object colour perception , 1980 .

[33]  Yi Wang,et al.  Joint Luminance and Chrominance Learning for Underwater Image Enhancement , 2021, IEEE Signal Processing Letters.

[34]  Guojia Hou,et al.  A Hybrid Framework for Underwater Image Enhancement , 2020, IEEE Access.

[35]  Codruta O. Ancuti,et al.  Color Balance and Fusion for Underwater Image Enhancement , 2018, IEEE Transactions on Image Processing.