TY - GEN
T1 - Locally time-invariant models of human activities using trajectories on the grassmannian
AU - Turaga, Pavan
AU - Chellappa, Rama
PY - 2009
Y1 - 2009
N2 - Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities are characterized by non-linear dynamics that make learning, inference and recognition hard. In this paper, we consider the problem of modeling and recognizing complex activities which exhibit time-varying dynamics. To this end, we describe activities as outputs of linear dynamic systems (LDS) whose parameters vary with time, or a Time-Varying Linear Dynamic System (TV-LDS). We discuss parameter estimation methods for this class of models by assuming that the parameters are locally time-invariant. Then, we represent the space of LDS models as a Grassmann manifold. Then, the TV-LDS model is defined as a trajectory on the Grassmann manifold. We show how trajectories on the Grassmannian can be characterized using appropriate distance metrics and statistical methods that reflect the underlying geometry of the manifold. This results in more expressive and powerful models for complex human activities. We demonstrate the strength of the framework for activity-based summarization of long videos and recognition of complex human actions on two datasets.
AB - Human activity analysis is an important problem in computer vision with applications in surveillance and summarization and indexing of consumer content. Complex human activities are characterized by non-linear dynamics that make learning, inference and recognition hard. In this paper, we consider the problem of modeling and recognizing complex activities which exhibit time-varying dynamics. To this end, we describe activities as outputs of linear dynamic systems (LDS) whose parameters vary with time, or a Time-Varying Linear Dynamic System (TV-LDS). We discuss parameter estimation methods for this class of models by assuming that the parameters are locally time-invariant. Then, we represent the space of LDS models as a Grassmann manifold. Then, the TV-LDS model is defined as a trajectory on the Grassmann manifold. We show how trajectories on the Grassmannian can be characterized using appropriate distance metrics and statistical methods that reflect the underlying geometry of the manifold. This results in more expressive and powerful models for complex human activities. We demonstrate the strength of the framework for activity-based summarization of long videos and recognition of complex human actions on two datasets.
UR - http://www.scopus.com/inward/record.url?scp=70450207848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70450207848&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2009.5206710
DO - 10.1109/CVPRW.2009.5206710
M3 - Conference contribution
AN - SCOPUS:70450207848
SN - 9781424439935
T3 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
SP - 2435
EP - 2441
BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PB - IEEE Computer Society
T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Y2 - 20 June 2009 through 25 June 2009
ER -