Closed-Form Hierarchical Finite Element Models for Part-Based Object Detection

Files

137-144.pdf (6.14 MB)

Date

2013

Authors

Rak, Marko
Engel, Karin
Tönnies, Klaus D.

Publisher

The Eurographics Association

Abstract

In this work we address part-based object detection under variability of part shapes and spatial relations. Our approach bases on the hierarchical finite element modeling concept of Engel and Tönnies [ET09a, ET09b]. They model object parts by elastic materials, which adapt to image structures via image-derived forces. Spatial part relations are realized through additional layers of elastic material forming an elastic hierarchy. We present a closed-form solution to this concept, reformulating the hierarchical optimization problem into the optimization of a non-hierarchical finite element model. This allows us to apply standard finite element techniques to hierarchical problems and to provide an efficient framework for part-based object detection. We demonstrate our approach at the example of lumbar column detection in magnetic resonance imaging on a data set of 49 subjects. Given a rough model initialization, our approach solved the detection problem reliably in 45 out of 49 cases, showing computation times of only a few seconds per subject.

        @inproceedings{:10.2312/PE.VMV.VMV13.137-144
,
booktitle = {Vision, Modeling & Visualization
},
editor = {Michael Bronstein and Jean Favre and Kai Hormann
},
title = {{Closed-Form Hierarchical Finite Element Models for Part-Based Object Detection
}},
author = {Rak, Marko and 
Engel, Karin and 
Tönnies, Klaus D.
},
year = {2013
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905674-51-4
},
DOI = {/10.2312/PE.VMV.VMV13.137-144
}
}