Shape-Colour Histograms for Matching 3D Video Sequences
Abstract
Most 3D object retrieval and matching methods only consider geometric similarity. This paper introduces a novel descriptor, Shape-Colour Histograms, to match objects with similar shape and appearance. This is motivated by the requirement to concatenate captured 3D video sequences for animation production. A quantitative evaluation based on the Receiver-Operator Characteristic (ROC) curve is presented to compare the performance of conventional 3D shape descriptors and new shape-colour descriptors with temporal filtering in the task to match 3D video sequences. 3D shape descriptors including Shape Histogram, LightField are considered. Evaluation shows that filtered Shape-Colour Histograms outperform descriptors using shape only. Finally, temporal Shape-Colour Histograms are applied to a publically available database of 3D video of people to identify optimal transitions and synthesize 3D character animation. Results demonstrate the accurate matching of surface shape, appearance and motion at transition points.
Cite
Text
Huang and Hilton. "Shape-Colour Histograms for Matching 3D Video Sequences." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457434Markdown
[Huang and Hilton. "Shape-Colour Histograms for Matching 3D Video Sequences." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/huang2009iccvw-shapecolour/) doi:10.1109/ICCVW.2009.5457434BibTeX
@inproceedings{huang2009iccvw-shapecolour,
title = {{Shape-Colour Histograms for Matching 3D Video Sequences}},
author = {Huang, Peng and Hilton, Adrian},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2009},
pages = {1510-1517},
doi = {10.1109/ICCVW.2009.5457434},
url = {https://mlanthology.org/iccvw/2009/huang2009iccvw-shapecolour/}
}