摘要
针对水下图像由于水的散射和吸收而存在颜色失真和细节丢失等问题,提出了一种综合多尺度信息和注意力机制的生成对抗网络模型来增强水下图像。首先,为了充分利用和增强图像的局部信息和全局信息,使用局部编码器和全局编码器分别提取图像的局部特征和全局特征,并互相融合以实现互补性。接着,设计多尺度混合卷积来捕捉多尺度信息,增加网络对不同尺度特征的适应性。然后,利用注意力机制增加特征提取的准确性,加强网络对高价值特征的关注度。最后,重复使用多尺度混合卷积和注意力机制进一步细化特征后,逐步上采样得到增强图像。与六种经典和最新的方法相比,提出的模型不仅在主观评价中取得了最好的视觉感受,而且在整个测试集上,峰值信噪比(PSNR)、结构相似指数(SSIM)、水下图像质量指标(UIQM)和自然图像质量(NIQE)四种客观评价指标分别取得了22.499,0.789,2.911和4.175的平均分数,均优于六种对比方法,较对比方法中的最优值分别提升0.353,0.002,0.025和0.307,证明提出的模型不仅能够矫正图像颜色失真,而且在恢复图像细节、增加图像对比度和清晰度等方面均有较好的表现,具有良好的应用前景。
Aiming at the problems of color distortion and detail loss in underwater images due to water scattering and absorption,a generative adversarial network model integrating multi-scale information and attention mechanism was proposed to enhance underwater images.Firstly,to fully exploit and enhance both local and global information of the image,local encoders and global encoders were employed to extract local and global features respectively,which were then fused to achieve complementarity.Next,a multi-scale hybrid convolution was designed to capture multi-scale information,increasing the network's adaptability to features at different scales.Subsequently,attention mechanisms were utilized to enhance the accuracy of feature extraction,emphasizing the focus on high-value features.Finally,by iteratively applying multi-scale hybrid convolution and attention mechanisms to refine features,the enhanced image was gradually up-sampled.Compared with the six classical and state-of-the-art methods,the proposed model not only achieved the best visual perception in subjective evaluations but also outperformed the six comparative methods on the entire test set in terms of four objective evaluation metrics peak signal-to-noise ratio(PSNR),structural similarity(SSIM),underwater image quality measurement(UIQM),and natural image quality evaluation(NIQE)with average scores of 22.499,0.789,2.911,and 4.175,respectively.The improvements over the best scores among the comparative methods are 0.353,0.002,0.025,and 0.307,respectively.These results indicate that the proposed model not only corrects image color distortion but also performs well in restoring image details,increasing image contrast,and enhancing clarity.Therefore,it shows promising prospects for practical applications in underwater image enhancement.
作者
夏晓华
钟预全
胡鹏
姚运仕
耿继光
张良奇
XIA Xiaohua;ZHONG Yuquan;HU Peng;YAO Yunshi;GENG Jiguang;ZHANG Liangqi(Key Laboratory of Road Construction Technology and Equipment,Ministry of Education,Chang'an University,Xi'an 710064,China;Henan Wanli Transportation Technology Group Co.Ltd.,Xuchang 461000,China)
出处
《光学精密工程》
EI
CAS
CSCD
北大核心
2024年第10期1582-1594,共13页
Optics and Precision Engineering
基金
国家自然科学基金(No.61901056)
秦创原引用高层次创新创业人才项目(No.QCYRCXM-2022-352)。
关键词
水下图像增强
生成对抗网络
编码器
多尺度混合卷积
注意力机制
underwater image enhancement
generative adversarial network
encoder
multi-scale hybrid convolution
attention mechanism
