Color Correction of Underwater Images for Aquatic Robot Inspection
Color Correction of Underwater Images for Aquatic Robot Inspection
复制标题
DOI：
10.1007/11585978_5
复制
发表时间：
2005-11
期刊：
影响因子：
--
通讯作者：
L. Torres-Méndez;G. Dudek
中科院分区：
文献类型：
--
作者：
L. Torres-Méndez;G. Dudek
在本文中，我们考虑使用统计先验的颜色恢复问题。这是适用于水下图像的颜色恢复，使用能量最小化配方。水下图像提出了一个挑战，当试图纠正蓝绿色单色外观，以带出我们所知道的海洋生物的颜色。对于水上机器人任务，图像的质量是至关重要的，需要实时。我们的方法通过使用马尔可夫随机场（MRF）来表示颜色耗尽和彩色图像之间的关系来增强图像的颜色。MRF模型的参数从训练数据中学习，然后通过使用置信度传播（BP）推断给定颜色耗尽图像中每个像素的最可能颜色分配。这允许系统使颜色恢复算法适应当前环境条件以及任务要求。在多种水下场景下的实验结果证明了该方法的可行性。
In this paper, we consider the problem of color restoration using statistical priors. This is applied to color recovery for underwater images, using an energy minimization formulation. Underwater images present a challenge when trying to correct the blue-green monochrome look to bring out the color we know marine life has. For aquatic robot tasks, the quality of the images is crucial and needed in real-time. Our method enhances the color of the images by using a Markov Random Field (MRF) to represent the relationship between color depleted and color images. The parameters of the MRF model are learned from the training data and then the most probable color assignment for each pixel in the given color depleted image is inferred by using belief propagation (BP). This allows the system to adapt the color restoration algorithm to the current environmental conditions and also to the task requirements. Experimental results on a variety of underwater scenes demonstrate the feasibility of our method.