Representation
and Optimal Recognition of Human Activities
Authors
Somboon Hongeng, François Brémond, Ramakant Nevatia
Abstract:
Towards the goal of realizing a generic automatic human activity recognition system,
a new formalism is proposed. Activities are described by a chained hierarchical
representation using three type of entities: image features, mobile object properties
and scenarios. Taking image features of tracked moving regions from an image sequence
as input, mobile object properties are first computed by specific methods while
noise is suppressed by statistical methods. Scenarios are recognized from mobile
object properties based on Bayesian analysis. A sequential occurrence several
scenarios are recognized by an algorithm using a probabilistic finite-state automaton
(a variant of structured HMM). The demonstration of the optimality of these recognition
method is discussed. Finally, the validity and the effectiveness of our approach
is demonstrated on both real-world and perturbed data
Keywords:
To get this article, click
here
BibTeX reference:
@ARTICLE{bre00a,
AUTHOR = {S. Hongeng and F. Br\'emond and R. Nevatia},
BOOKTITLE = {Proc. of the IEEE Conference on {C}omputer {V}ision and {P}attern
{R}ecognition},
TITLE = { Representation and Optimal Recognition of Human Activities },
MONTH = jun, YEAR = {2000}
}
Last modified : 17/05/01
Agnes.Cortell@sophia.inria.fr