[论文解读] Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map

Wei Song, Yan Wang+3 more|arXiv (Cornell University)|Jun 19, 2019

Image Enhancement Techniques参考文献 43被引用 16

一句话总结

本文提出了一种新颖的水下图像增强方法，结合了背景光估计的统计模型与优化的透射率图，以提升图像质量。通过利用人工标注的背景光数据库，并结合深度和饱和度先验优化透射率图，该方法在颜色保真度、对比度和计算效率方面均优于当前最先进的方法。

ABSTRACT

Underwater images often have severe quality degradation and distortion due to light absorption and scattering in the water medium. A hazed image formation model is widely used to restore the image quality. It depends on two optical parameters: the background light and the transmission map. Underwater images can also be enhanced by color and contrast correction from the perspective of image processing. In this paper, we propose an effective underwater image enhancement method for underwater images in composition of underwater image restoration and color correction. Firstly, a manually annotated background lights (MABLs) database is developed. With reference to the relationship between MABLs and the histogram distributions of various underwater images, robust statistical models of BLs estimation are provided. Next, the TM of R channel is roughly estimated based on the new underwater dark channel prior via the statistic of clear and high resolution underwater images, then a scene depth map based on the underwater light attenuation prior and an adjusted reversed saturation map are applied to compensate and modify the coarse TM of R channel. Next, TMs of G-B channels are estimated based on the difference of attenuation ratios between R channel and G-B channels. Finally, to improve the color and contrast of the restored image with a natural appearance, a variation of white balance is introduced as post-processing. In order to guide the priority of underwater image enhancement, sufficient evaluations are conducted to discuss the impacts of the key parameters including BL and TM, and the importance of the color correction. Comparisons with other state-of-the-art methods demonstrate that our proposed underwater image enhancement method can achieve higher accuracy of estimated BLs, less computation time, more superior performance, and more valuable information retention.

研究动机与目标

• 解决由于光吸收和散射导致的水下环境中图像严重退化问题。
• 通过基于人工标注数据库推导出的统计模型，提高背景光（BL）估计的准确性。
• 通过整合深度和饱和度先验，优化透射率图（TM）估计，以提升图像恢复的保真度。
• 通过改进的白平衡后处理步骤，自然地增强颜色与对比度。
• 评估关键参数（BL与TM）的影响，并验证颜色校正在水下图像增强中的有效性。

提出的方法

• 构建一个人工标注的背景光（MABLs）数据库，以建立MABLs与图像直方图分布之间的统计关系。
• 基于MABLs数据库与直方图分析，开发一种鲁棒的背景光估计统计模型。
• 利用基于清晰高分辨率图像的改进水下暗通道先验，初步估计红色（R）通道的透射率图。
• 通过光衰减与颜色分布先验，利用场景深度图与调整后的反向饱和度图，对粗略的R通道透射率图进行优化。
• 通过建模R通道与G-B通道之间的差异性衰减比率，估计绿色（G）和蓝色（B）通道的透射率图。
• 应用一种改进的白平衡作为后处理步骤，以增强最终恢复图像的颜色自然性与对比度。

实验结果

研究问题

• RQ1 如何通过标注数据的统计建模，改进水下图像中的背景光估计？
• RQ2 利用深度和饱和度先验优化透射率图在多大程度上提升了图像恢复质量？
• RQ3 通过白平衡进行颜色校正对增强后水下图像的感知质量与自然外观有何影响？
• RQ4 背景光与透射率图等关键参数如何影响整体增强性能？
• RQ5 所提出方法在定量与定性方面与现有最先进的水下图像增强技术相比表现如何？

主要发现

• 得益于在人工标注数据库上训练的统计模型，所提方法在背景光估计方面相比现有方法具有更高的准确性。
• 通过深度与饱和度先验优化的透射率图，实现了更准确且视觉上更合理的图像恢复。
• 该方法在保持优异图像质量指标的同时，显著降低了计算时间。
• 集成改进的白平衡后处理步骤显著提升了颜色保真度与对比度，使结果更加自然。
• 对比评估结果表明，所提方法在定量指标与视觉质量方面均优于当前最先进的技术，信息保留能力更优。