• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on sensing and imaging >Approximated Scale Space for Efficient and Accurate SIFT Key-Point Detection
【24h】

Approximated Scale Space for Efficient and Accurate SIFT Key-Point Detection

机译：近似尺度空间，用于高效准确的筛选键点检测

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

摘要

The SIFT (scale invariant feature transform) key-point serves as an indispensable role in many computer vision applications. This paper presents an approximation of the SIFT scale space for key-point detection with high efficiency while preserving the accuracy. We build the scale space by repeated averaging filters to approximate the Gaussian filters used in SIFT algorithm. The accuracy of the proposed method is guaranteed by that an image undergoes repeated smoothing with an averaging filter is approximately equivalent to the smoothing with a specified Gaussian filter, which can be proved by the center limit theorem. The efficiency is improved by using integral image to fast compute the averaging filtering. In addition, we also present a method to filter out unstable key-points on the edges. Experimental results demonstrate the proposed method can generate high repeatable key-points quite close to the SIFT with only about one tenth of computational complexity of SIFT, and concurrently the proposed method does outperform many other methods.
机译：SIFT（Scale Invariant Feature Transform）键点在许多计算机视觉应用程序中作为不可或缺的角色。本文提出了筛选尺度空间的近似，以实现高效率，同时保持精度。我们通过重复平均过滤器构建刻度空间，以近似于SIFT算法中使用的高斯滤波器。所提出的方法的准确性被保证通过平均滤波器重复平滑的图像近似相当于使用指定的高斯滤波器的平滑，这可以通过中心限制定理证明。通过使用积分图像来快速计算平均滤波来提高效率。此外，我们还提出了一种在边缘上过滤掉不稳定键点的方法。实验结果证明了所提出的方法可以产生高可重复的键点，仅靠近筛选，只有大约十分之一的筛选的复杂性，并且同时提出的方法表明了许多其他方法。

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