School of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan 430074 ,China ;No.710 R&D Institute,Yichang 443003 ,China ;Qingjiang Innovation Center,Wuhan 430076 ,China 在期刊界中查找 在百度中查找 在本站中查找
The existing underwater image enhancement methods based on deep learning have achieved good results in synthetic underwater images. However,due to the large gap between the simplified synthetic image and the complicated real image,the performance of learning based methods will be significantly degraded when dealing with real images. To solve the problem,a joint underwater image generation and removal(JUIGR)method is proposed. This method adopts the decomposition idea to decompose the underwater image into a clean background layer and a degraded layer. The background is better restored through cyclic consistency loss and adversarial loss,and then the transformation between the real image and the synthetic image is realized,which not only corrects the color,but also improves the image contrast,so as to achieve a good enhancement effect. Extensive experimental results show that the proposed method is superior to the existing methods in terms of color,texture detail and clarity on the real underwater image dataset.
[1] MA J X,FAN X N,YANG S X,et al.Contrast limitedadaptive histogram equalization-based fusion in YIQand HSI color spaces for underwater image enhancement[J].International Journal of Pattern Recognition andArtificial Intelligence,2018,32(07):1854018.
[2] HUANG D M,WANG Y,SONG W,et al.Shallow-water image enhancement using relativeglobal histogram stretching based on adaptiveparameter acquisition[C]//International Conference onmultimedia modeling.Cham:Springer,2018.
[3] ANCUTI C,ANCUTI C O,HABER T,et al.Enhancingunderwater images and videos by fusion[C]//2012IEEE Conference on Computer Vision and PatternRecognition.Providence:IEEE,2012.
[4] ANCUTI C O,ANCUTI C,DE VLEESCHOUWER C,et al.Color balance and fusion for underwater imageenhancement[J].IEEE Transactions on ImageProcessing,2017,27(1):379-393.
[5] MARQUES T P,ALBU A B.L2UWE:a framework forthe efficient enhancement of low-light underwaterimages using local contrast and multi-scale fusion[C]//Proceedings of the IEEE/CVF Conference on ComputerVision and Pattern Recognition Workshops.Online:IEEE,2020.
[6] FU X Y,ZHUANG P X,HUANG Y,et al.Aretinex-based enhancing approach for singleunderwater image[C]//2014 IEEE InternationalConference on Image Processing(ICIP).Melbourne:IEEE,2014.
[8] HE K M,SUN J,TANG X O.Single image hazeremoval using dark channel prior[J].IEEE Transactionson Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353.
[9] CHIANG J Y,CHEN Y C.Underwater image enhancementby wavelength compensation and dehazing[J].IEEETransactions on Image Processing,2011,21(4):1756-1769.
[10] DREWS P,NASCIMENTO E,MORAES F,et al.Transmission estimation in underwater singleimages[C]//Proceedings of the IEEE InternationalConference on Computer Vision Workshops.Sydney:IEEE,2013.
[11] PENG Y T,CAO K,COSMAN P C.Generalization ofthe dark channel prior for single image restoration[J].IEEE Transactions on Image Processing,2018,27(6):2856-2868.
[12] AKKAYNAK D,TREIBITZ T.Sea-thru:a method forremoving water from underwater images[C]//Proceedingsof the IEEE/CVF Conference on Computer Vision andPattern Recognition.Long Beach:IEEE,2019.
[13] LI C Y,GUO J C,CONG R M,et al.Underwater imageenhancement by dehazing with minimum informationloss and histogram distribution prior[J].IEEE Transactionson Image Processing,2016,25(12):5664-5677.
[14] LI C Y,ANWAR S,PORIKLI F.Underwater sceneprior inspired deep underwater image and videoenhancement[J].Pattern Recognition,2020,98:107038.
[15] LI C Y,GUO C L,REN W Q,et al.An underwaterimage enhancement benchmark dataset and beyond[J].IEEE Transactions on Image Processing,2019,29:4376-4389.
[16] ISLAM M J,XIA Y Y,SATTAR J.Fast underwaterimage enhancement for improved visual perception[J].IEEE Robotics and Automation Letters,2020,5(2):3227-3234.
[17] WANG Y D,GUO J C,GAO H,et al.UIEC^ 2-Net:CNN-based underwater image enhancement using twocolor space[J].Signal Processing:Image Communication,2021,96:116250.