A Multi-scale Feature Likelihood Map for Direct Evaluation of Object Hypotheses⋆
This paper develops and investigates a new approach for evaluating feature based object hypotheses in a direct way. The idea is to compute a feature likelihood map (FLM), which is a function normalized to the interval [0; 1], and which approximates the likelihood of image features at all points in scale-space. In our case, the FLM is defined from Gaussian derivative operators and in such a way that it assumes its strongest responses near the centers of symmetric blob-like or elongated ridge-like structures and at scales that reflect the size of these structures in the image domain. While the FLM inherits several advantages of feature based image representations, it also (i) avoids the need for explicit search when matching features in object models to image data, and (ii) eliminates the need for thresholds present in most traditional feature based approaches. In an application presented in this paper, the FLM is applied to simultaneous tracking and recognition of hand models based on particle filtering. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by a pyramid implementation of the proposed concept.
KeywordsImage Structure Scale Selection Object Hypothesis Simultaneous Tracking Local Image Structure
Unable to display preview. Download preview PDF.
- Bretzner, L. and Lindeberg, T. (1999). Qualitative multi-scale feature hierarchies for object tracking, JVCIR 11: 115–129.Google Scholar
- Chomat, O., de Verdiere, V., Hall, D. and Crowley, J. (2000). Local scale selection for gaussian based description techniques, ECCV’00, Dublin, Ireland, 117–133.Google Scholar
- Fleck, M., Forsyth, D. and Bregler, C. (1996). Finding naked people, ECCV’96, Cambridge, UK, II:593–602.Google Scholar
- Florack, L.M.J. (1997). Image Structure, Kluwer.Google Scholar
- Isard, M. and Blake, A. (1996). Contour tracking by stochastic propagation of conditional density, ECCV’96, Cambridge, UK, I:343–356.Google Scholar
- Laptev, I and Lindeberg, T. (2001) “A multi-scale feature likelihood map for direct evaluation of object hypotheses”, Technical report ISRN KTH/NA/P01/03-SE. http://www.nada.kth.se/cvap/abstracts/cvap249.html
- Lindeberg, T. (1994). Scale-Space Theory in Computer Vision, Kluwer.Google Scholar
- Lindeberg, T. (1998). Feature detection with automatic scale selection, IJCV, 30(2): 77–116.Google Scholar
- Witkin, A.P. (1983). Scale-space filtering, Proc. IJCAI’83, Karlsruhe, West Germany, 1019–1022.Google Scholar