• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Mathematical Problems in Engineering >Multiscale Point Correspondence Using Feature Distribution and Frequency Domain Alignment
【24h】

Multiscale Point Correspondence Using Feature Distribution and Frequency Domain Alignment

机译：使用特征分布和频域对准的多尺度点对应

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, a hybrid scheme is proposed to find the reliable point-correspondences between two images, which combines the distribution of invariant spatial feature description and frequency domain alignment based on two-stage coarse to fine refinement strategy. Firstly, the source and the target images are both down-sampled by the image pyramid algorithm in a hierarchical multi-scale way. The Fourier-Mellin transform is applied to obtain the transformation parameters at the coarse level between the image pairs; then, the parameters can serve as the initial coarse guess, to guide the following feature matching step at the original scale, where the correspondences are restricted in a search window determined by the deformation between the reference image and the current image; Finally, a novel matching strategy is developed to reject the false matches by validating geometrical relationships between candidate matching points. By doing so, the alignment parameters are refined, which is more accurate and more flexible than a robust fitting technique. This in return can provide a more accurate result for feature correspondence. Experiments on real and synthetic image-pairs show that our approach provides satisfactory feature matching performance.
机译：本文提出了一种混合方案来找到两幅图像之间的可靠点对应关系，该方案基于两阶段的粗到细化策略，结合不变空间特征描述的分布和频域对齐。首先，通过图像金字塔算法以分层多尺度方式对源图像和目标图像均进行下采样。应用傅里叶-梅林变换来获得图像对之间的粗糙水平的变换参数。然后，这些参数可以作为初始的粗略猜测，以原始尺度指导接下来的特征匹配步骤，其中，将对应关系限制在由参考图像和当前图像之间的变形确定的搜索窗口中；最后，开发了一种新颖的匹配策略，通过验证候选匹配点之间的几何关系来拒绝错误匹配。通过这样做，比对参数更精确，这比健壮的拟合技术更准确，更灵活。反过来，这可以为特征对应提供更准确的结果。在真实和合成图像对上的实验表明，我们的方法提供了令人满意的特征匹配性能。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2012年第12期|382369.1-382369.14|共14页
  • 作者

    Zeng-Shun Zhao; Xiang Feng; Sheng-Hua Teng; Yi-Bin Li; Chang-Shui Zhang;

  • 作者单位

    School of Control Science and Engineering, Shandong University, Jinan 250061, China,College of Information and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, China;

    College of Information and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, China;

    College of Information and Electrical Engineering, Shandong University of Science and Technology, Qingdao 266590, China;

    School of Control Science and Engineering, Shandong University, Jinan 250061, China;

    State Key Lab of Intelligent Technologies and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Department of Automation, Tsinghua University, Beijing 100084, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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