基于Lab和YUV颜色空间的农田图像分割方法

Farmland image segmentation based on Lab and YUV color spaces

针对农田这种非结构环境下的图像分割问题,提出了一种基于Lab和YUV颜色空间的农田图像分割方法。该方法首先将获得的原始农田彩色图像分别转换到Lab颜色空间和YUV颜色空间,然后分别对Lab颜色空间进行Otsu阈值分割,对YUV颜色空间进行加权模糊熵分割,最后将2种分割方法得到的二值图像进行合并、滤波,以得到最终的分割图像。结果表明,该方法能够有效地实现农田图像的精准分割,并滤除噪声及抑制光照不均匀等复杂环境带来的影响,获得令人满意的结果。

In order to solve the image segmentation problems under farmland‐the unstructured environment ,a farmland image segmentation based on Lab and YUV color spaces was proposed .The original color image was firstly converted to Lab and YUV color spaces separately .And then ,Otsu threshold segmentation was used in Lab color space ,weighted fuzzy entropy threshold segmentation was used in YUV color space .At last ,the two binary images obtained by two seg‐mentation methods were combined together and filtered to get the final segmented image . The experimental results showed that the proposed method can segment farmland image effectively ,filter the noise ,suppress the effects of com‐plex environment such as uneven illumination ,and obtain satisfactory results .