基于视觉显著特征的光学与SAR影像快速粗配准方法

来源期刊:中南大学学报(自然科学版)2019年第7期

论文作者:徐川 华丽 眭海刚

文章页码:1602 - 1611

关键词:视觉显著特征;合成孔径雷达影像;影像配准;水平集;形状曲线

Key words:visual saliency feature; synthetic aperture radar image; image registration; level set; shape curve

摘    要:在经典的Itti模型基础上,结合纹理特征及SAR影像显著目标的灰度特性,TW-Itti视觉显著模型能快速精确地反映显著地物的范围,获取显著区域。在显著区域内,利用水平集分割提取显著目标,通过形状曲线匹配算法对显著目标进行配准。研究结果表明:与经典的Itti模型相比,TW-Itti模型得到的显著区域目标整体更连贯,边缘细节更丰富,目标区域更准确,提高了后续影像粗配准的鲁棒性。同时,配准效率得到显著提高。

Abstract: Combining texture features and gray level characteristics of salient targets in SAR(Synthetic aperture radar) images, on the basis of classical Itti model, TW-Itti visual saliency model can quickly and accurately reflect the range of salient objects, and then obtain salient regions. In salient regions, salient targets were extracted by level set segmentation, and registered by shape curve matching algorithm. The results show that, compared with the classical Itti model, the TW-Itti model obtains more coherent, richer edge details and more accurate target area, which improves the robustness of subsequent image rough registration. At the same time, the registration efficiency of this method is significantly improved.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号