Gait Appearance for Recognition

Abstract

This paper describes a set of representations of gait appearance features for the purpose of person identification. Our gait representation has two stages: the first stage computes a set of image features that are based on moments extracted from orthogonal view video silhouettes of human walking motion; the second stage applies three methods of aggregating these image features over time to create the gait sequence features. Despite their simplicity, the resulting gait sequence feature vectors contain enough information to perform well on human identification. We demonstrate the accuracy of recognition using gait video sequences collected over different days and times, under varying lighting environments and explore the differences in the three time-aggregation methods for the purpose of recognition.

Cite

Text

Lee and Grimson. "Gait Appearance for Recognition." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47917-1_15

Markdown

[Lee and Grimson. "Gait Appearance for Recognition." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/lee2002eccv-gait/) doi:10.1007/3-540-47917-1_15

BibTeX

@inproceedings{lee2002eccv-gait,
  title     = {{Gait Appearance for Recognition}},
  author    = {Lee, L. and Grimson, W. Eric L.},
  booktitle = {European Conference on Computer Vision},
  year      = {2002},
  pages     = {143-154},
  doi       = {10.1007/3-540-47917-1_15},
  url       = {https://mlanthology.org/eccv/2002/lee2002eccv-gait/}
}