A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching Export

@article{citeulike:2949675, abstract = {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.}, author = {Gavrila, D. M.}, booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, citeulike-article-id = {2949675}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1271931.1272144}, citeulike-linkout-1 = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2007.1062}, citeulike-linkout-2 = {http://dx.doi.org/10.1109/TPAMI.2007.1062}, citeulike-linkout-3 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4250466}, doi = {10.1109/TPAMI.2007.1062}, journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, keywords = {exemplar-based, hierachical}, number = {8}, pages = {1408--1421}, posted-at = {2008-11-12 00:17:45}, priority = {2}, title = {A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching}, url = {http://dx.doi.org/10.1109/TPAMI.2007.1062}, volume = {29}, year = {2007} }

TY - JOUR ID - citeulike:2949675 L3 - citeulike-article-id:2949675 N2 - 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. IS - 8 JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on EP - 1421 TI - A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching VL - 29 T2 - Pattern Analysis and Machine Intelligence, IEEE Transactions on SP - 1408 KW - exemplar-based KW - hierachical AU - Gavrila, DM PY - 2007/// UR - http://dx.doi.org/10.1109/TPAMI.2007.1062 ER -