首页> 外文会议>International Symposium on Visual Computing >Dense Correspondence and Optical Flow Estimation Using Gabor, Schmid and Steerable Descriptors
【24h】

Dense Correspondence and Optical Flow Estimation Using Gabor, Schmid and Steerable Descriptors

机译:使用Gabor,Schmid和可转向描述符密集的对应和光学流量估计

获取原文

摘要

In this paper, the use of three dense descriptors, namely Schmid, Gabor and steerable descriptors, is introduced and investigated for optical flow estimation and dense correspondence of different scenes and compared with the well-known dense SIFT/SIFTFlow. Several examples of optical flow estimation and dense correspondence across scenes with high variations in the intensity levels, difference in the presence of features and different misalignment models (rigid, deformable, homography etc.) are studied and the results are quantitatively/qualitatively compared with dense SIFT/SIFTFlow. The proposed dense descriptors provide comparable or better results than dense SIFT/SIFTFlow which shows the high potential in this area for more thorough investigations.
机译:在本文中,使用三个致密的描述符,即施密,Gabor和可操纵描述符,并研究了不同场景的光学流量估计和密集对应,并与众所周知的致密筛选/施加污水相比。 在强度水平的高变化的场景中的几个例子示例,在强度水平的高变化,研究了特征和不同的错位模型(刚性,可变形,同位等)的差异,并将结果与致密相比定量/定性相比 SIFT / SIFTFLOW。 所提出的致密描述符提供比致密的筛选/三丝流提供可比或更好的结果,其显示该区域的高潜力以获得更彻底的研究。

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