A Bayesian, exemplar-based approach to hierarchical shape matching
A Bayesian, exemplar-based approach to hierarchical shape matching
复制标题
DOI：
10.1109/tpami.2007.1062
复制
发表时间：
2007-08-01
影响因子：
23.6
通讯作者：
Gavrila, Dariu M.
中科院分区：
文献类型：
--
作者：
Gavrila, Dariu M.
本文提出了一种新的基于样本的分层形状匹配的概率方法。样本之间不需要特征对应，只需要一个合适的成对相似性度量。该方法使用模板树来有效地表示和匹配各种形状样本。该树是通过使用随机优化的自下而上聚类方法离线生成的。在线匹配包括在模板树和转换参数上同时采用粗到精的方法。本文的主要贡献是一个贝叶斯模型，用于估计目标类在树的某个节点匹配后的后验概率。该模型考虑了对象的规模和显著性，并允许有原则地设置匹配阈值，以便尽早消除树遍历过程中没有希望的路径。该方法已在多个应用领域中进行了测试。在这里，结果呈现在一个更具挑战性的领域：从移动的车辆实时行人检测。将提出的概率匹配方法与人工调整的非概率匹配方法进行比较，可以获得显著的加速，两者都使用相同的模板树结构。
This paper presents a novel probabilistic approach to hierarchical, exemplar-based shape matching. No feature correspondence is needed among exemplars, just a suitable pairwise similarity measure. The approach uses a template tree to efficiently represent and match the variety of shape exemplars. The tree is generated offline by a bottom-up clustering approach using stochastic optimization. Online matching involves a simultaneous coarse-to-fine approach over the template tree and over the transformation parameters. The main contribution of this paper is a Bayesian model to estimate the a posteriori probability of the object class, after a certain match at a node of the tree. This model takes into account object scale and saliency and allows for a principled setting of the matching thresholds such that unpromising paths in the tree traversal process are eliminated early on. The proposed approach was tested in a variety of application domains. Here, results are presented on one of the more challenging domains: real-time pedestrian detection from a moving vehicle. A significant speed-up is obtained when comparing the proposed probabilistic matching approach with a manually tuned nonprobabilistic variant, both utilizing the same template tree structure.