ML Anthology

High Performance Moves Recognition and Sequence Segmentation Based on Key Poses Filtering

Claudio Marcio de Souza Vicente, Erickson R. Nascimento, Luiz Eduardo C. Emery, Cristiano Arruda G. Flor, Thales Vieira, Leonardo B. Oliveira
WACV 2016 pp. 1-8
doi:10.1109/WACV.2016.7477711 /wacv/2016/desouzavicente2016wacv-high/

Abstract

We present a discriminative key pose-based approach for moves recognition and segmentation of training sequences for high performance sports. Compared to daily human gestures, moves in high performance sports are faster and have low inter-class variability, which produce noisy features and ambiguity. Our approach combines a robust filtering strategy to select frames composed of discriminative poses (key poses) and the discriminative Latent-Dynamic Conditional Random Fields (LDCRF) model to predict a label for each frame from the training sequence. We evaluate our approach on unsegmented sequences of Taekwondo training. Experimental results indicate that our methodology outperforms the Decision Forests method in terms of efficiency and accuracy. Our average recognition rate was equal to 74.72% while Decision Forests achieves 58.29%. The experiments also show that our approach was able to recognize and segment high speed moves like roundhouse kicks, which can reach peak linear speeds up to 26 m/s.

PDF WACV Semantic Scholar

Cite

Text

de Souza Vicente et al. "High Performance Moves Recognition and Sequence Segmentation Based on Key Poses Filtering." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477711

Markdown

[de Souza Vicente et al. "High Performance Moves Recognition and Sequence Segmentation Based on Key Poses Filtering." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/desouzavicente2016wacv-high/) doi:10.1109/WACV.2016.7477711

BibTeX

@inproceedings{desouzavicente2016wacv-high,
  title     = {{High Performance Moves Recognition and Sequence Segmentation Based on Key Poses Filtering}},
  author    = {de Souza Vicente, Claudio Marcio and Nascimento, Erickson R. and Emery, Luiz Eduardo C. and Flor, Cristiano Arruda G. and Vieira, Thales and Oliveira, Leonardo B.},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2016},
  pages     = {1-8},
  doi       = {10.1109/WACV.2016.7477711},
  url       = {https://mlanthology.org/wacv/2016/desouzavicente2016wacv-high/}
}