- Author
- Vincent Spruyt (UGent) , Alessandro Ledda (UGent) and Wilfried Philips (UGent)
- Organization
- Abstract
- Hand tracking in video is an increasingly popular research field due to the rise of novel human-computer interaction methods. However, robust and real-time hand tracking in unconstrained environments remains a challenging task due to the high number of degrees of freedom and the non-rigid character of the human hand. In this paper, we propose an unsupervised method to automatically learn the context in which a hand is embedded. This context includes the arm and any other object that coherently moves along with the hand. We introduce two novel methods to incorporate this context information into a probabilistic tracking framework, and introduce a simple yet effective solution to estimate the position of the arm. Finally, we show that our method greatly increases robustness against occlusion and cluttered background, without degrading tracking performance if no contextual information is available. The proposed real-time algorithm is shown to outperform the current state-of-the-art by evaluating it on three publicly available video datasets. Furthermore, a novel dataset is created and made publicly available for the research community.
- Keywords
- GESTURES, FEATURES, OBJECT, hand tracking, particle filter, unsupervised learning, random forest, context learning, importance sampling, RECOGNITION
Downloads
-
sensors-14-12023.pdf
- full text (Published version)
- |
- open access
- |
- |
- 14.52 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-4443428
- MLA
- Spruyt, Vincent, et al. “Robust Arm and Hand Tracking by Unsupervised Context Learning.” SENSORS, vol. 14, no. 7, 2014, pp. 12023–58, doi:10.3390/s140712023.
- APA
- Spruyt, V., Ledda, A., & Philips, W. (2014). Robust arm and hand tracking by unsupervised context learning. SENSORS, 14(7), 12023–12058. https://doi.org/10.3390/s140712023
- Chicago author-date
- Spruyt, Vincent, Alessandro Ledda, and Wilfried Philips. 2014. “Robust Arm and Hand Tracking by Unsupervised Context Learning.” SENSORS 14 (7): 12023–58. https://doi.org/10.3390/s140712023.
- Chicago author-date (all authors)
- Spruyt, Vincent, Alessandro Ledda, and Wilfried Philips. 2014. “Robust Arm and Hand Tracking by Unsupervised Context Learning.” SENSORS 14 (7): 12023–12058. doi:10.3390/s140712023.
- Vancouver
- 1.Spruyt V, Ledda A, Philips W. Robust arm and hand tracking by unsupervised context learning. SENSORS. 2014;14(7):12023–58.
- IEEE
- [1]V. Spruyt, A. Ledda, and W. Philips, “Robust arm and hand tracking by unsupervised context learning,” SENSORS, vol. 14, no. 7, pp. 12023–12058, 2014.
@article{4443428,
abstract = {{Hand tracking in video is an increasingly popular research field due to the rise of novel human-computer interaction methods. However, robust and real-time hand tracking in unconstrained environments remains a challenging task due to the high number of degrees of freedom and the non-rigid character of the human hand. In this paper, we propose an unsupervised method to automatically learn the context in which a hand is embedded. This context includes the arm and any other object that coherently moves along with the hand. We introduce two novel methods to incorporate this context information into a probabilistic tracking framework, and introduce a simple yet effective solution to estimate the position of the arm. Finally, we show that our method greatly increases robustness against occlusion and cluttered background, without degrading tracking performance if no contextual information is available. The proposed real-time algorithm is shown to outperform the current state-of-the-art by evaluating it on three publicly available video datasets. Furthermore, a novel dataset is created and made publicly available for the research community.}},
author = {{Spruyt, Vincent and Ledda, Alessandro and Philips, Wilfried}},
issn = {{1424-8220}},
journal = {{SENSORS}},
keywords = {{GESTURES,FEATURES,OBJECT,hand tracking,particle filter,unsupervised learning,random forest,context learning,importance sampling,RECOGNITION}},
language = {{eng}},
number = {{7}},
pages = {{12023--12058}},
title = {{Robust arm and hand tracking by unsupervised context learning}},
url = {{http://doi.org/10.3390/s140712023}},
volume = {{14}},
year = {{2014}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: