摘要： 为获取高质量的水下生物图像，解决水下生物图像在实际拍摄中产生的色偏、对比度低等问题，以提供精准的海洋数据支持，促进海洋资源的开发与保护，设计了一种轻量级色温调整和动态卷积多色校正水下生物图像复原方法。该方法采用全局平均和最大池化补偿水下生物图像的色彩失真，并加入Ghost卷积降低特征图的冗余降低模型参数量。同时，利用动态卷积自适应地校正图像在三种色彩空间中的亮度和对比度。结果显示：在EUVP(Enhancing Underwater Visual Perception)中的水下场景数据集上，本模型在峰值信噪比(PSNR)和结构相似性(SSIM)指标上分别上升到24.298和0.891，表现均优于基于非物理和物理模型的对比方法。在EUVP中的水下生物图像数据集上，本模型与Shallow-Uwnet和Water-Net两种深度学习模型相比，其计算量仅占后两者的0.27%和0.04%，且存储容量仅为41KB，而增强后的图像在SSIM指标上比后两者分别提高了3.77%和6.72%。研究表明，该模型方法能有效增强水下生物图像，同时由于其具有极低的计算量和存储空间，能够大幅降低水下设备部署的门槛。

关键词: 水下图像增强, 图像处理, 深度学习, 颜色校正

Abstract: This study proposes a lightweight underwater image restoration method for obtaining high-quality underwater biological images and addressing issues such as color cast and low contrast. The method compensates for color distortion in underwater images through global averaging and max pooling, reducing the influence of irrelevant features in the input images and enhancing the model's focus on key features. It introduces ghost convolution to reduce redundancy in feature maps and model parameters. Additionally, dynamic convolution is used to adaptively adjust the brightness and contrast of images in three color spaces, overcoming the limitations of single-color restoration and enhancing the tone and brightness of the images based on RGB restoration. The results show that the proposed model outperforms contrast methods based on non-physical and physical models in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), with values of 24.298 and 0.891, respectively, on the Enhanced Underwater Vision Perception (EUVP) underwater scene dataset. Compared to the deep learning models Shallow-Uwnet and Water-Net on the EUVP underwater biological image dataset, the proposed model achieves computational efficiency of only 0.27% and 0.04%, respectively. The improved images show an SSIM improvement of 3.77% and 6.72%, compared to the two aforementioned models. By directly adjusting pixel values to restore underwater image colors, this model occupies only 41 KB of storage space, making it suitable for deployment on underwater robots. This study demonstrates that the proposed model effectively enhances underwater biological images, and due to its low computational load and storage requirements, it contributes to the accurate support of ocean data and promotes the development of marine resources.

Key words: underwater image enhancement, image processing, deep learning, color correction