TY - GEN
T1 - Rolling rotations for recognizing human actions from 3D skeletal data
AU - Vemulapalli, Raviteja
AU - Chellappa, Rama
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/9
Y1 - 2016/12/9
N2 - Recently, skeleton-based human action recognition has been receiving significant attention from various research communities due to the availability of depth sensors and real-time depth-based 3D skeleton estimation algorithms. In this work, we use rolling maps for recognizing human actions from 3D skeletal data. The rolling map is a welldefined mathematical concept that has not been explored much by the vision community. First, we represent each skeleton using the relative 3D rotations between various body parts. Since 3D rotations are members of the special orthogonal group SO3, our skeletal representation becomes a point in the Lie group SO3 ×... × SO3, which is also a Riemannian manifold. Then, using this representation, we model human actions as curves in this Lie group. Since classification of curves in this non-Euclidean space is a difficult task, we unwrap the action curves onto the Lie algebra so3 ×... × so3 (which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Lie algebra. Experimental results on three action datasets show that the proposed approach performs equally well or better when compared to state-of-the-art.
AB - Recently, skeleton-based human action recognition has been receiving significant attention from various research communities due to the availability of depth sensors and real-time depth-based 3D skeleton estimation algorithms. In this work, we use rolling maps for recognizing human actions from 3D skeletal data. The rolling map is a welldefined mathematical concept that has not been explored much by the vision community. First, we represent each skeleton using the relative 3D rotations between various body parts. Since 3D rotations are members of the special orthogonal group SO3, our skeletal representation becomes a point in the Lie group SO3 ×... × SO3, which is also a Riemannian manifold. Then, using this representation, we model human actions as curves in this Lie group. Since classification of curves in this non-Euclidean space is a difficult task, we unwrap the action curves onto the Lie algebra so3 ×... × so3 (which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Lie algebra. Experimental results on three action datasets show that the proposed approach performs equally well or better when compared to state-of-the-art.
UR - http://www.scopus.com/inward/record.url?scp=84986271081&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84986271081&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2016.484
DO - 10.1109/CVPR.2016.484
M3 - Conference contribution
AN - SCOPUS:84986271081
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 4471
EP - 4479
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PB - IEEE Computer Society
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Y2 - 26 June 2016 through 1 July 2016
ER -