一种基于分水岭和Radon变换的波向检测方法

Wave Direction Extraction Based on Watershed and Radon Transforms

根据波浪图像的纹理特征,提出了一种新的基于分水岭和Radon变换的波向检测算法,该方法利用波浪纹理特征,选择效率高且易于实现的分水岭变换,对图像波谷进行分割,提取波谷形态方向并推算出带有±180°方向模糊的波浪方向;截取波浪纹理图像并生成时栈图像,通过Radon变换去除方向模糊,实现波向的有效检测。仿真实验结果表明,该算法简单有效,有利于提高波向检测的精度和效率。

To extract wave direction from sea surface images, a new method is proposed, which is based on a combination of watershed transform and Radon transform. Using the feature of sea wave images, this method first selects a watershed transform to segment the image into wave trough regions. Then the wave direction that has an associated 180 degree ambiguity is calculated from the trough areas. Meanwhile, a time stack image is generated from the frames and processed by Radon transform to find the forward wave direction in specific orientation. Lastly, the wave direction without ambiguity is determined effectively. The experiment results of numerical simulation show the validity and feasibility of the proposed method, and improve the accuracy and efficiency of wave direction measurement.