The Community for Technology Leaders
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2339-2
pp: 1-6
Erhardt Barth , Institute for Neuro- and Bioinformatics, University of Lübeck Ratzeburger Allee 160, 23538, Germany
Martin Bohme , Institute for Neuro- and Bioinformatics, University of Lübeck Ratzeburger Allee 160, 23538, Germany
Martin Haker , Institute for Neuro- and Bioinformatics, University of Lübeck Ratzeburger Allee 160, 23538, Germany
Thomas Martinetz , Institute for Neuro- and Bioinformatics, University of Lübeck Ratzeburger Allee 160, 23538, Germany
ABSTRACT
We describe a technique for computing scale-invariant features on range maps produced by a range sensor, such as a time-of-flight camera. Scale invariance is achieved by computing the features on the reconstructed three-dimensional surface of the object. The technique is general and can be applied to a wide range of operators. Features are computed in the frequency domain; the transform from the irregularly sampled mesh to the frequency domain uses the Nonequispaced Fast Fourier Transform. We demonstrate the technique on a facial feature detection task. On a dataset containing faces at various distances from the camera, the equal error rate (EER) for the case of scale-invariant features is halved compared to features computed on the range map in the conventional way. When the scale-invariant range features are combined with intensity features, the error rate on the test set reduces to zero.
INDEX TERMS
CITATION
Erhardt Barth, Martin Bohme, Martin Haker, Thomas Martinetz, "Scale-invariant range features for time-of-flight camera applications", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-6, 2008, doi:10.1109/CVPRW.2008.4563169
99 ms
(Ver )