Integration Of Perceptual Grouping Modules With 3D Interpretation Modules In Computer Vision

视觉加工的中间阶段由通用感知组织模块和三维解释模块组成。本研究主要关注中间处理模块的计算模型和算法模型，以及这些模块之间的相互作用。它将研究一些感知分组模块与三维解释模块的集成。如果像这里建议的那样跨级别进行集成，那么关于物理世界的特定知识将提供一组强大的约束，用于组合分组模块的输出。该项目涉及以集成的方式开发和实现可能的视觉处理模块的子集。该项目的目标是证明，当较低和中级模块的结果在3D模块的背景下进行解释时，即当从较高级模块提供反馈时，获得的结果更加鲁棒且定义良好。本文重点研究的具体模块有：(1)与对称检测模块相结合的接近性和平滑性分组模块。(2)与三维线标注模块集成的分组模块。(3)与轮廓模块相结合的对称检测模块。算法将在不透明、分段平滑物体的混乱场景的真实图像上进行测试，并评估分组算法和分析这些图像的集成过程的有用性。

The intermediate stage of visual processing consists of general purpose perceptual organization modules and 3D interpretation modules. This research is concerned with the computational and algorithmic models of the intermediate processing modules, and the interaction of these modules with each other. It will study the integration of a number of perceptual grouping modules with 3D interpretation modules. If the integration is done across levels as proposed here, the specific knowledge about the physical world provides a powerful set of constraints with which to combine the outputs of the grouping modules. The project involves the development and implementation of a subset of the possible visual processing modules in an integrated manner. The goal of this project is to demonstrate that when the results of lower and intermediate level modules are interpreted within the context of 3D modules, that is, when feedback is provided from the higher level modules, the results obtained are more robust and well defined. The specific modules that this proposal concentrates upon are: (1) the proximity and smoothness grouping modules integrated with symmetry detection modules. (2) the grouping modules integrated with 3D line labeling modules. (3) the symmetry detection module integrated with shape from contour modules. Algorithms will be tested on real images of cluttered scenes of opaque, piecewise smooth objects and the usefulness of the grouping algorithm and the integration process in analyzing these images will be assessed.