Using Partial Edge Contour Matches for Efficient Object Category Localization
Abstract
We propose a method for object category localization by partially matching edge contours to a single shape prototype of the category. Previous work in this area either relies on piecewise contour approximations, requires meaningful supervised decompositions, or matches coarse shape-based descriptions at local interest points. Our method avoids error-prone pre-processing steps by using all obtained edges in a partial contour matching setting. The matched fragments are efficiently summarized and aggregated to form location hypotheses. The efficiency and accuracy of our edge fragment based voting step yields high quality hypotheses in low computation time. The experimental evaluation achieves excellent performance in the hypotheses voting stage and yields competitive results on challenging datasets like ETHZ and INRIA horses.
Cite
Text
Riemenschneider et al. "Using Partial Edge Contour Matches for Efficient Object Category Localization." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_3Markdown
[Riemenschneider et al. "Using Partial Edge Contour Matches for Efficient Object Category Localization." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/riemenschneider2010eccv-using/) doi:10.1007/978-3-642-15555-0_3BibTeX
@inproceedings{riemenschneider2010eccv-using,
title = {{Using Partial Edge Contour Matches for Efficient Object Category Localization}},
author = {Riemenschneider, Hayko and Donoser, Michael and Bischof, Horst},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {29-42},
doi = {10.1007/978-3-642-15555-0_3},
url = {https://mlanthology.org/eccv/2010/riemenschneider2010eccv-using/}
}