中文

概率搜索用于目标分割与识别

计算机视觉与模式识别 2007-05-23 v1

摘要

本文在概率框架内分析了基于模型的场景解释搜索问题。将目标模型形式化为场景范围数据的数据生成模型。引入一种新统计准则——截断目标概率,用于推断需评估其与数据匹配度的目标假设序列。该截断概率受目标先验知识和从数据中学习到的信息共同决定。 presented of some experiments on sequence quality and object segmentation and recognition from stereo data. The article recovers classic concepts from object recognition (grouping, geometric hashing, alignment) from the probabilistic perspective and adds insight into the optimal ordering of object hypotheses for evaluation. Moreover, it introduces point-relation densities, a key component of the truncated probability, as statistical models of local surface shape. 实验结果展示了在序列质量和从立体数据中进行目标分割与识别方面的应用。该文从概率视角恢复了目标识别中的经典概念(分组、几何哈希、对齐),并阐明了目标假设评估顺序的最优性。此外,本文引入点-关系密度(point-relation densities),作为局部表面形状的统计模型,这是截断概率的关键组成部分。

关键词

引用

@article{arxiv.cs/0208005,
  title  = {Probabilistic Search for Object Segmentation and Recognition},
  author = {Ulrich Hillenbrand and Gerd Hirzinger},
  journal= {arXiv preprint arXiv:cs/0208005},
  year   = {2007}
}

备注

18 pages, 5 figures