复杂背景下的风力机组叶片图像分割方法研究

Research on blade image segmentation of wind turbine under complicated background

针对单一的图像分割方法对复杂背景下的风力机组叶片图像进行分割时,得到的结果不具备准确性的问题,提出一种将Canny边缘检测与形态学分析相结合的方法,对Canny算法处理之后的二值图像进行腐蚀膨胀,去除背景区域。在分割一种具有颜色差异的风机叶片图像时,将RGB图像转化为HSV图像,再分别对HSV图像的色度、饱和度、和明度分量进行处理,并运用开运算去除图像噪声,得到理想的分割结果。实验结果表明,提出的图像分割方法能得到完整的风机叶片图像分割结果。

When a single image segmentation method is used to segment a wind turbine blade image under a complex background, the results obtained are not accurate and complete. This paper proposes a method of combinating Canny edge detection and morphological analysis, in which the binary image processed by the Canny algorithm is etched and expanded to remove the background area. When it segments a fan blade image with color difference, firstly, the RGB image is converted into a HSV image, and then the chroma, saturation, and brightness components of the HSV image are processed respectively. Finally, an open operation is used to remove image noise and an ideal segmentation result is obtained. Experimental results show that the image segmentation method proposed in this paper can obtain a complete fan blade image segmentation results.