PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A coarse-to-fine taxonomy of constellations for fast multi-class object detection
Marko Boben, Sanja Fidler and Aleš Leonardis
Lect. notes comput. sci. Volume 6315, pp. 687-700, 2010. ISSN 0302-9743

Abstract

In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number of classes [1, 2]. In this paper we propose a novel approach for speeding up recognition times of multi-class part-based object representations. The main idea is to construct a taxon- omy of constellation models cascaded from coarse-to-ne resolution and use it in recognition with an ecient search strategy. The taxonomy is built automatically in a way to minimize the number of expected compu- tations during recognition by optimizing the cost-to-power ratio [3]. The structure and the depth of the taxonomy is not pre-determined but is inferred from the data. The approach is utilized on the hierarchy-of-parts model [4] achieving eciency in both, the representation of the structure of objects as well as in the number of modeled object classes. We achieve speed-up even for a small number of object classes on the ETHZ and TUD dataset. On a larger scale, our approach achieves detection time that is logarithmic in the number of classes.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:8195
Deposited By:Boris Horvat
Deposited On:21 February 2012