首页 >  , Vol. , Issue () : 1993-2002

摘要

引用本文:

DOI:

10.11834/jrs.20209280

收稿日期:

2019-07-30

修改日期:

2019-09-24

PDF Free   EndNote   BibTeX
基于光流校正的复杂地形区多时相遥感影像配准
冯蕊涛1, 杜清运1, 罗恒2, 沈焕锋1, 李星华3, 刘波2
1.武汉大学 资源与环境科学学院;2.广西壮族自治区基础地理信息中心;3.武汉大学 遥感信息工程学院
摘要:

几何配准是影像后续处理的重要前提,是遥感信息处理领域研究的热点之一。复杂地形区多时相遥感影像的高精度配准一直是难以突破的难题,光流估计法通过逐像素位移增量解算为此提供了可行的解决思路,但光流法对地物变化异常敏感,经常导致计算的光流场及配准影像存在异常。为此,本文提出一种基于光流校正的复杂地形区多时相遥感影像配准方法,采用亮度和梯度双重约束获取光流场初值,在此基础上使用高斯拉普拉斯算子对异常光流进行检测,然后通过Delaunay三角形曲面插值对异常光流进行校正处理,从而得到各像素精准位移。实验表明,本文提出方法对存在地物变化的复杂地形区多时相遥感影像,可实现高保真、高精度的配准。

Multi-temporal remote sensing images registration based on optical flow modification in complex terrain areas
Abstract:

Image registration is an important prerequisite for subsequent processing, and it is one of spotlights in the field of remote sensing information processing. High-precision registration of multi-temporal remote sensing images covering complex-terrain region is always a problem to break through. Optical flow estimation calculates per-pixel displacements considering the very local distortions, providing a feasible solution. However, it is sensitive to land cover changes, which often lead to abnormal optical flow field and further affect the registered image. To this end, a registration algorithm based on the optical flow modification for multi-temporal remote sensing images covering the complex-terrain region is proposed. On the preliminary optical flow field estimated by both the brightness and gradient constraints strategy, Laplace of Gaussian operator is employed to detect the abnormal optical flow. With the mask of abnormal optical flow, the Delaunay triangle curved surface interpolation is utilized to correct them. After coordinates transformation and resampling, the aligned image is generated. Experiments demonstrate that the proposed method achieves high-fidelity and high-precision registration for multi-temporal remote sensing images covering the complex-terrain region with land cover changes.

本文暂时没有被引用!

欢迎关注学报微信

遥感学报交流群 分享按钮