TY - GEN
T1 - A Probabilistic Approach for Human Everyday Activities Recognition using Body Motion from RGB-D Images
AU - Faria, Diego R.
AU - Premebida, Cristiano
AU - Nunes, Urbano
N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2014/10/20
Y1 - 2014/10/20
N2 - In this work, we propose an approach that relies on cues from depth perception from RGB-D images, where features related to human body motion (3D skeleton features) are used on multiple learning classifiers in order to recognize human activities on a benchmark dataset. A Dynamic Bayesian Mixture Model (DBMM) is designed to combine multiple classifier likelihoods into a single form, assigning weights (by an uncertainty measure) to counterbalance the likelihoods as a posterior probability. Temporal information is incorporated in the DBMM by means of prior probabilities, taking into consideration previous probabilistic inference to reinforce current-frame classification. The publicly available Cornell Activity Dataset [1] with 12 different human activities was used to evaluate the proposed approach. Reported results on testing dataset show that our approach overcomes state of the art methods in terms of precision, recall and overall accuracy. The developed work allows the use of activities classification for applications where the human behaviour recognition is important, such as human-robot interaction, assisted living for elderly care, among others.
AB - In this work, we propose an approach that relies on cues from depth perception from RGB-D images, where features related to human body motion (3D skeleton features) are used on multiple learning classifiers in order to recognize human activities on a benchmark dataset. A Dynamic Bayesian Mixture Model (DBMM) is designed to combine multiple classifier likelihoods into a single form, assigning weights (by an uncertainty measure) to counterbalance the likelihoods as a posterior probability. Temporal information is incorporated in the DBMM by means of prior probabilities, taking into consideration previous probabilistic inference to reinforce current-frame classification. The publicly available Cornell Activity Dataset [1] with 12 different human activities was used to evaluate the proposed approach. Reported results on testing dataset show that our approach overcomes state of the art methods in terms of precision, recall and overall accuracy. The developed work allows the use of activities classification for applications where the human behaviour recognition is important, such as human-robot interaction, assisted living for elderly care, among others.
UR - http://ieeexplore.ieee.org/document/6926340/
U2 - 10.1109/ROMAN.2014.6926340
DO - 10.1109/ROMAN.2014.6926340
M3 - Conference publication
SN - 978-1-4799-6763-6
T3 - The 23rd IEEE International Symposium on Robot and Human Interactive Communication
SP - 732
EP - 737
BT - IEEE RO-MAN'14: IEEE International Symposium on Robot and Human Interactive Communication. Edinburgh-Scotland. * Finalist for Kazuo Tanie Award
PB - IEEE
T2 - 2014 RO-MAN: The 23rd IEEE International Symposium on Robot and Human Interactive Communication
Y2 - 25 April 2014 through 29 April 2014
ER -