• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>European Conference on Computer Vision(ECCV 2004) pt.4; 20040511-20040514; Prague; CZ >Stereo Using Monocular Cues within the Tensor Voting Framework
【24h】

Stereo Using Monocular Cues within the Tensor Voting Framework

机译：在张量投票框架内使用单眼提示进行立体声

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

We address the fundamental problem of matching two static images. Significant progress has been made in this area, but the correspondence problem has not been solved. Most of the remaining difficulties are caused by occlusion and lack of texture. We propose an approach that addresses these difficulties within a perceptual organization framework, taking into account both binocular and monocular sources of information. Geometric and color information from the scene is used for grouping, complementing each other's strengths. We begin by generating matching hypotheses for every pixel in such a way that a variety of matching techniques can be integrated, thus allowing us to combine their particular advantages. Correct matches are detected based on the support they receive from their neighboring candidate matches in 3-D, after tensor voting. They are grouped into smooth surfaces, the projections of which on the images serve as the reliable set of matches. The use of segmentation based on geometric cues to infer the color distributions of scene surfaces is arguably the most significant contribution of our research. The inferred reliable set of matches guides the generation of disparity hypotheses for the unmatched pixels. The match for an unmatched pixel is selected among a set of candidates as the one that is a good continuation of the surface, and also compatible with the observed color distribution of the surface in both images. Thus, information is propagated from more to less reliable pixels considering both geometric and color information. We present results on standard stereo pairs.
机译：我们解决了匹配两个静态图像的基本问题。在这一领域已经取得了重大进展，但是对应问题尚未解决。剩下的大多数困难是由咬合和缺乏质地引起的。我们提出了一种在感知组织框架内解决这些困难的方法，同时考虑了双眼和单眼信息源。场景中的几何和颜色信息用于分组，以补充彼此的优势。我们首先以可以集成各种匹配技术的方式为每个像素生成匹配假设，从而使我们能够结合其特殊优势。在张量投票后，根据他们从其相邻的3D候选匹配中获得的支持，检测到正确的匹配。它们被分组为平滑的表面，其在图像上的投影可作为可靠的匹配项。使用基于几何线索的分割来推断场景表面的颜色分布可以说是我们研究的最重要贡献。推断出的可靠匹配集指导了未匹配像素的视差假设的生成。从一组候选对象中选择一个不匹配像素的匹配对象，作为表面的良好连续性，并且还与两个图像中观察到的表面颜色分布兼容。因此，考虑到几何和颜色信息，信息从可靠性更高的像素传播到可靠性更低的像素。我们在标准立体声对上呈现结果。

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