Gavrila Dariu M
Machine Perception Department of DainlerChrysler R&D, Ulm, Germany.
IEEE Trans Pattern Anal Mach Intell. 2007 Aug;29(8):1408-21. doi: 10.1109/TPAMI.2007.1062.
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.
本文提出了一种新颖的概率方法，用于基于示例的分层形状匹配。示例之间无需特征对应，仅需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示例。该树通过使用随机优化的自底向上聚类方法离线生成。在线匹配涉及在模板树和变换参数上同时采用从粗到细的方法。本文的主要贡献是一个贝叶斯模型，用于在树的某个节点进行一定匹配后估计对象类别的后验概率。该模型考虑了对象的尺度和显著性，并允许对匹配阈值进行有原则的设置，以便在树遍历过程中尽早消除没有希望的路径。所提出的方法在各种应用领域进行了测试。在此，给出了在一个更具挑战性的领域中的结果：从移动车辆上进行实时行人检测。当将所提出的概率匹配方法与手动调整的非概率变体进行比较时，二者都利用相同的模板树结构，结果显示速度显著提高。
