Issue No. 08 - August (2007 vol. 29)
D.M. Gavrila , DahnlerChiysier R&D, Ulm
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.
Bayesian methods, Image segmentation, Robustness, Shape measurement, Stochastic processes, Testing, Vehicle detection, Vehicles, Tree data structures, Prototypes,Bayesian models., Hierarchical shape matching, chamfer distance
D.M. Gavrila, "A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 29, no. , pp. 1408-1421, August 2007, doi:10.1109/TPAMI.2007.1062