Publication: Fusion of Single View Soft k-NN Classifiers for Multicamera Human Action Recognition
Loading...
Identifiers
Publication date
2010
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Impact
Export
Abstract
This paper presents two different classifier fusion algorithms applied in the domain of Human Action Recognition from video. A set of cameras observes a person performing an action from a predefined set. For each camera view a 2D descriptor is computed and a posterior on the performed activity is obtained using a soft classifier. These posteriors are combined using voting and a bayesian network to obtain a single belief measure to use for the final decision on the performed action. Experiments are conducted with different low level frame descriptors on the IXMAS dataset, achieving results comparable to state of the art 3D proposals, but only performing 2D processing.
Description
Proceedings of: 5th International Conference on Hybrid Artificial Intelligence Systems (HAIS 2010). San Sebastián, Spain, June 23-25, 2010
Keywords
Single camera, Soft classifiers, Human Action Recognition
Bibliographic citation
Corchado, E. et al. (eds.) (2010) Hybrid Artificial Intelligent Systems: 5th International Conference, HAIS 2010, San Sebastián, Spain, June 23-25, 2010. Proceedings, Part II. (Lecture Notes in Computer Science, 6077). Springer, pp. 436- 443.