A general descriptor for detecting abnormal action performance from skeletal data. Elkholy, A., Hussein, M. E., Gomaa, W., Damen, D., & Saba, E. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 1401–1404, 2017.
doi  abstract   bibtex   
We propose an action-independent descriptor for detecting abnormality in motion, based on medically-inspired skeletal features. The descriptor is tested on four actions/motions captured using a single depth camera: sit-to-stand, stand-to-sit, flat-walk, and climbing-stairs. For each action, a Gaussian Mixture Model (GMM) trained on normal motions is built using the action-independent feature descriptor. Test sequences are evaluated based on their fitness to the normal motion models, with a threshold over the likelihood, to assess abnormality. Results show that the descriptor is able to detect abnormality with accuracy ranging from 0.97 to 1 for the various motions.
@inproceedings{elkholy_general_2017,
	title = {A general descriptor for detecting abnormal action performance from skeletal data},
	rights = {All rights reserved},
	doi = {10.1109/EMBC.2017.8037095},
	abstract = {We propose an action-independent descriptor for detecting abnormality in motion, based on medically-inspired skeletal features. The descriptor is tested on four actions/motions captured using a single depth camera: sit-to-stand, stand-to-sit, flat-walk, and climbing-stairs. For each action, a Gaussian Mixture Model ({GMM}) trained on normal motions is built using the action-independent feature descriptor. Test sequences are evaluated based on their fitness to the normal motion models, with a threshold over the likelihood, to assess abnormality. Results show that the descriptor is able to detect abnormality with accuracy ranging from 0.97 to 1 for the various motions.},
	eventtitle = {2017 39th Annual International Conference of the {IEEE} Engineering in Medicine and Biology Society ({EMBC})},
	pages = {1401--1404},
	booktitle = {2017 39th Annual International Conference of the {IEEE} Engineering in Medicine and Biology Society ({EMBC})},
	author = {Elkholy, A. and Hussein, M. E. and Gomaa, W. and Damen, D. and Saba, E.},
	year = {2017},
	keywords = {abnormal action performance detection, action-independent feature descriptor, cameras, Cameras, climbing-stairs motion, Feature extraction, flat-walk motion, gait analysis, Gaussian mixture model, Gaussian processes, Legged locomotion, medically-inspired skeletal features, Motion, Movement, Musculoskeletal System, Normal Distribution, Sensors, single depth camera, sit-to-stand motion, skeletal data, Skeleton, stand-to-sit motion, Testing, Three-dimensional displays, Walking},
	file = {IEEE Xplore Abstract Record:C\:\\Users\\Mohamed Hussein\\Zotero\\storage\\VBHX3VCD\\8037095.html:text/html}
}

Downloads: 0