结合纹理去除的遥感图像分割

发布时间：2018-02-08 22:17

本文关键词： 纹理相对全变差均值漂移遥感图像分割　出处：《计算机应用》2017年11期 　论文类型：期刊论文

【摘要】：针对包含复杂纹理信息的遥感图像难以进行精准图像分割的问题,提出了一种结合纹理去除的遥感图像分割方法。首先,改进了相对全变差纹理去除方法,通过引入新的范数约束使相对全变差纹理去除方法可以在去除纹理信息的同时凸显图像中的主要结构,达到辅助分割的效果;然后,使用均值漂移算法对经过纹理去除的遥感图像进行无监督聚类,达到分割的目的;最后,提出的遥感图像分割算法在不同遥感图像上进行了测试。实验结果表明,在高分辨遥感图像的分割上,所提算法可以分割出遥感图像中的主要目标,和直接分割或者结合其他纹理去除方法相比取得了更好的分割结果。所提出的分割算法可以降低纹理信息对图像分割的影响,提高遥感图像分割的精度。
[Abstract]:Aiming at the difficulty of accurate image segmentation in remote sensing images with complex texture information, a remote sensing image segmentation method combined with texture removal is proposed. Firstly, the relative total variation texture removal method is improved. By introducing new norm constraints, the relative total variation texture removal method can not only remove texture information, but also highlight the main structure of the image, so as to achieve the effect of auxiliary segmentation. The mean shift algorithm is used for unsupervised clustering of remote sensing images after texture removal. Finally, the proposed remote sensing image segmentation algorithm is tested on different remote sensing images. The experimental results show that, In the segmentation of high-resolution remote sensing images, the proposed algorithm can segment the main targets in remote sensing images. The proposed segmentation algorithm can reduce the influence of texture information on image segmentation and improve the accuracy of remote sensing image segmentation.
【作者单位】：陕西师范大学计算机科学学院;
【基金】：国家自然科学基金资助项目(41171338,41471280,61401265)~~
【分类号】：TP751

【相似文献】