Learning a Hierarchical Deformable Template for Rapid Deformable Object Parsing

In this paper, we address the tasks of detecting, segmenting, parsing, and matching deformable objects. We use a novel probabilistic object model that we call a hierarchical deformable template (HDT). The HDT represents the object by state variables defined over a hierarchy (with typically 5 levels). The hierarchy is built recursively by composing elementary structures to form more complex structures. A probability distribution – a parameterized exponential model – is defined over the hierarchy to quantify the variability in shape and appearance of the object at multiple scales. To perform inference – to estimate the most probable states of the hierarchy for an input image – we use a bottom-up algorithm called compositional inference. This algorithm is an approximate version of dynamic programming where approximations are made (e.g., pruning) to ensure that the algorithm is fast while maintaining high performance. We adapt the structure-perceptron algorithm to estimate the p...

• Type: Journal
• Year: 2010
• Where: PAMI
• Authors: Long Zhu, Yuanhao Chen, Alan L. Yuille
• Keywords: Algorithms, Hierarchical Deformable Template, PAMI 2010, Parameterized Exponential Model