自适应形态学与多尺度结合的植被区域遥感图像分割方法

Multiscale and Adaptive Morphology for Remote Sensing Image Segmentation of Vegetation Areas

为减小植被区域遥感图像分割误差,解决植被区域中待分割目标因覆盖度和噪声等因素造成的过分割和欠分割问题,提出了一种自适应形态学与多尺度结合的植被区域遥感图像分割方法。首先,通过general adaptive neighborhood(GAN)结构元素构造膨胀和腐蚀运算,推导出GAN形态学开、闭运算;然后,构造一种GAN形态学复合型滤波器,填充植被覆盖度不足的孔洞,减小噪声对图像的干扰;最后,通过多尺度分割算法,对遥感图像植被区域进行分割。实验结果表明:所提方法能够有效避免欠分割和过分割现象且能对遥感图像植被区域进行准确分割;与传统多尺度分割和传统形态学与多尺度结合方法相比,所提方法的分割误差较小。

For reducing the segmentation error in remote sensing images of vegetation regions and for solving oversegmentation and under-segmentation of targets caused by various factors such as coverage and noise,an adaptive morphology combined with multiscale remote sensing image segmentation method for vegetation regions is proposed.First,general adaptive neighborhood(GAN)is used to construct dilation and corrosion operations,and GAN morphological opening and closing operations are derived.Then,a GAN morphological compound filter is constructed to fill the holes with insufficient vegetation coverage to reduce the interference of noise on the images.Finally,the remote sensing image of the vegetation region is segmented using the multiscale segmentation algorithm.The experimental results show that the proposed method can effectively avoid the phenomenon of under-segmentation and over-segmentation.Moreover,it can effectively segment the remote sensing images of vegetation areas with different coverage.Compared with the traditional multiscale segmentation method and traditional morphological and multiscale combined method,the proposed method has higher segmentation accuracy.