Peng Yan-Tsung, Chen Yen-Rong, Chen Zihao, Wang Jung-Hua, Huang Shih-Chia
Department of Computer Science, National Chengchi University, Taipei City 116, Taiwan.
Department of Mechanical Aerospace Engineering, University of California, San Diego, CA 92093, USA.
Sensors (Basel). 2022 Mar 10;22(6):2168. doi: 10.3390/s22062168.
This work proposes to develop an underwater image enhancement method based on histogram-equalization (HE) approximation using physics-based dichromatic modeling (PDM). Images captured underwater usually suffer from low contrast and color distortions due to light scattering and attenuation. The PDM describes the image formation process, which can be used to restore nature-degraded images, such as underwater images. However, it does not assure that the restored images have good contrast. Thus, we propose approximating the conventional HE based on the PDM to recover the color distortions of underwater images and enhance their contrast through convex optimization. Experimental results demonstrate the proposed method performs favorably against state-of-the-art underwater image restoration approaches.
这项工作旨在基于使用基于物理的双色模型（PDM）的直方图均衡化（HE）近似来开发一种水下图像增强方法。由于光散射和衰减，水下拍摄的图像通常对比度低且存在颜色失真。PDM描述了图像形成过程，可用于恢复自然退化的图像，如水下图像。然而，它不能确保恢复的图像具有良好的对比度。因此，我们建议基于PDM对传统HE进行近似，以恢复水下图像的颜色失真并通过凸优化增强其对比度。实验结果表明，该方法相对于现有最先进的水下图像恢复方法具有良好的性能。
