Laboratory for Vision Systems, Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712-1084, USA.
IEEE Trans Image Process. 1998;7(9):1283-99. doi: 10.1109/83.709661.
This paper describes a novel system for computing a three-dimensional (3-D) range segmentation of an arbitrary visible scene using focus information. The process of range segmentation is divided into three steps: an initial range classification, a surface merging process, and a 3-D multiresolution range segmentation. First, range classification is performed to obtain quantized range estimates. The range classification is performed by analyzing focus cues within a Bayesian estimation framework. A combined energy functional measures the degree of focus and the Gibbs distribution of the class field. The range classification provides an initial range segmentation. Second, a statistical merging process is performed to merge the initial surface segments. This gives a range segmentation at a coarse resolution. Third, 3-D multiresolution range segmentation (3-D MRS) is performed to refine the range segmentation into finer resolutions. The proposed range segmentation method does not require initial depth estimates, it allows the analysis of scenes containing multiple objects, and it provides a rich description of the 3-D structure of a scene.
本文提出了一种使用聚焦信息计算任意可见场景的三维（3-D）距离分割的新系统。距离分割的过程分为三个步骤：初始距离分类、表面合并过程和 3-D 多分辨率距离分割。首先，进行距离分类以获得量化的距离估计。距离分类是在贝叶斯估计框架内通过分析聚焦线索来执行的。一个组合能量函数度量聚焦程度和类场的吉布斯分布。距离分类提供了初始距离分割。其次，执行统计合并过程以合并初始表面段。这给出了粗分辨率的距离分割。第三，执行 3-D 多分辨率距离分割（3-D MRS）以将距离分割细化为更精细的分辨率。所提出的距离分割方法不需要初始深度估计，它允许分析包含多个对象的场景，并提供了场景的 3-D 结构的丰富描述。
