• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on graphic and image processing >Filtering Method of Star Control Points for Geometric Correction of Remote Sensing Image Based on RANSAC Algorithm
【24h】

Filtering Method of Star Control Points for Geometric Correction of Remote Sensing Image Based on RANSAC Algorithm

机译：基于RANSAC算法的遥感影像几何校正星控制点滤波方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the process of geometric correction of remote sensing image, occasionally, a large number of redundant control points may result in low correction accuracy. In order to solve this problem, a control points filtering algorithm based on RANdom SAmple Consensus (RANSAC) was proposed. The basic idea of the RANSAC algorithm is that using the smallest data set possible to estimate the model parameters and then enlarge this set with consistent data points. In this paper, unlike traditional methods of geometric correction using Ground Control Points (GCPs), the simulation experiments are carried out to correct remote sensing images, which using visible stars as control points. In addition, the accuracy of geometric correction without Star Control Points (SCPs) optimization is also shown. The experimental results show that the SCPs' s filtering method based on RANSAC algorithm has a great improvement on the accuracy of remote sensing image correction.
机译：在遥感图像的几何校正过程中，偶尔，大量的冗余控制点可能会导致较低的校正精度。为了解决这个问题，提出了一种基于RANdom SAmple Consensus（RANSAC）的控制点过滤算法。 RANSAC算法的基本思想是使用最小的数据集来估计模型参数，然后使用一致的数据点来扩大该集。与传统的使用地面控制点（GCP）进行几何校正的方法不同，本文通过模拟实验来校正遥感图像，该方法以可见星为控制点。此外，还显示了没有星形控制点（SCP）优化的几何校正的准确性。实验结果表明，基于RANSAC算法的SCPs滤波方法在遥感图像校正精度上有很大的提高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号