Underwater image de-scattering and classification by deep neural network
Underwater image de-scattering and classification by deep neural network
复制标题
DOI：
10.1016/j.compeleceng.2016.08.008
复制
发表时间：
2016-08-01
影响因子：
4.3
通讯作者：
Serikawa, Seiichi
中科院分区：
文献类型：
--
作者：
Li, Yujie;Lu, Huimin;Serikawa, Seiichi
基于视觉的水下导航和目标检测需要强大的计算机视觉算法在浑浊水中运行。许多传统方法旨在提高低浑浊水中的能见度。高浑浊度水下图像增强仍然是一个有待解决的问题。同时，我们发现水下图像的去散射和色彩校正会影响分类结果。针对高浑浊度水下图像的增强问题，本文提出了一种基于制导图像去散射和物理光谱特征的联合色彩校正方法。所提出的增强方法消除了散射并保留了颜色。此外，为了比较不同图像增强算法的性能，提出了一个更全面的图像质量评价指标Q(u)。该指数综合了SSIM指数和颜色距离指数的优点。我们还使用不同的机器学习方法进行分类，例如支持向量机，卷积神经网络。实验结果表明，该方法在统计上优于目前最先进的通用水下图像对比度增强算法。实验结果表明，该方法具有较好的图像分类效果。(C) 2016 Elsevier Ltd.版权所有。
Vision-based underwater navigation and object detection requires robust computer vision algorithms to operate in turbid water. Many conventional methods aimed at improving visibility in low turbid water. High turbid underwater image enhancement is still an opening issue. Meanwhile, we find that the de-scattering and color correction of underwater images affect classification results. In this paper, we correspondingly propose a novel joint guidance image de-scattering and physical spectral characteristics-based color correction method to enhance high turbidity underwater images. The proposed enhancement method removes the scatter and preserves colors. In addition, as a rule to compare the performance of different image enhancement algorithms, a more comprehensive image quality assessment index Q(u) is proposed. The index combines the benefits of SSIM index and color distance index. We also use different machine learning methods for classification, such as support vector machine, convolutional neural network. Experimental results show that the proposed approach statistically outperforms state-of-the-art general purpose underwater image contrast enhancement algorithms. The experiment also demonstrated that the proposed method performs well for image classification. (C) 2016 Elsevier Ltd. All rights reserved.