Non-Parametric Shape Recovery for Computer Vision

计算机视觉的非参数形状恢复

• 批准号: 9302041
• 负责人: Ari Gross
• 金额: $ 17.28万
• 依托单位: CUNY Queens College
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-05-01 至 1996-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9302041&HistoricalAwards=false
• 关键词: Non; Parametric; Shape; Recovery; Computer

This is the first year of a three-year continuing award. The research addresses recovering the 3D shape of an object from its 2D image contour. Existing 3D shape recovery algorithms tend to rely on parametric models to uniquely constrain the underlying 3D surface. Often, real-world scenes are too general to describe using parametric models. This researcher has discovered that certain non-parametric shape models allow a much greater flexibilty while at the same time providing constraints that can be used in the shape recovery process. Using planar symmetry as a model, the PI has constructed a symmetry analyzer, SYMAN, that finds axes of symmetry from contour. In addition, he has developed algorithms that use symmetry and orthogonality as object-based heuristics to constrain or recover 3D shape from image contour. With this award, the research is extended to mathematical study of the surface and projective properties of curved symmetric surfaces as well as their application to the shape recovery problem, and use of "crystallographic" methods to describe and recover shape by viewing classes of shapes with similar structure as being equivalent, so that all "octally symmetric" objects (e.g., spheres, cubes, superquadrics) might be considered equivalent.

这是三年连续奖的第一年。 该研究致力于从 2D 图像轮廓恢复物体的 3D 形状。 现有的 3D 形状恢复算法往往依赖参数模型来唯一约束底层 3D 表面。 通常，现实世界的场景过于笼统，无法使用参数模型进行描述。 该研究人员发现，某些非参数形状模型具有更大的灵活性，同时提供可用于形状恢复过程的约束。使用平面对称作为模型，PI 构建了一个对称分析器 SYMAN，它可以从轮廓中找到对称轴。此外，他还开发了使用对称性和正交性作为基于对象的启发法来约束或从图像轮廓恢复 3D 形状的算法。 凭借该奖项，该研究扩展到对称曲面的表面和投影特性的数学研究及其在形状恢复问题中的应用，并使用“晶体学”方法通过将具有相似结构的形状类别视为等效来描述和恢复形状，以便所有“八对称”物体（例如球体、立方体、超二次曲面）都可以被认为是等效的。