'Dynamism of a Dog on a Leash' or Behavior Classification by Eigen-Decomposition of Periodic Motions
Abstract
Following Futurism, we show how periodic motions can be represented by a small number of eigen-shapes that capture the whole dynamic mechanism of periodic motions. Spectral decomposition of a silhouette of an object in motion serves as a basis for behavior classification by principle component analysis. The boundary contour of the walking dog, for example, is first computed efficiently and accurately. After normalization, the implicit representation of a sequence of silhouette contours given by their corresponding binary images, is used for generating eigen-shapes for the given motion. Singular value decomposition produces these eigen-shapes that are then used to analyze the sequence. We show examples of object as well as behavior classification based on the eigen-decomposition of the binary silhouette sequence.
Cite
Text
Goldenberg et al. "'Dynamism of a Dog on a Leash' or Behavior Classification by Eigen-Decomposition of Periodic Motions." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47969-4_31Markdown
[Goldenberg et al. "'Dynamism of a Dog on a Leash' or Behavior Classification by Eigen-Decomposition of Periodic Motions." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/goldenberg2002eccv-dynamism/) doi:10.1007/3-540-47969-4_31BibTeX
@inproceedings{goldenberg2002eccv-dynamism,
title = {{'Dynamism of a Dog on a Leash' or Behavior Classification by Eigen-Decomposition of Periodic Motions}},
author = {Goldenberg, Roman and Kimmel, Ron and Rivlin, Ehud and Rudzsky, Michael},
booktitle = {European Conference on Computer Vision},
year = {2002},
pages = {461-475},
doi = {10.1007/3-540-47969-4_31},
url = {https://mlanthology.org/eccv/2002/goldenberg2002eccv-dynamism/}
}