Human Action Recognition Using a Modified Convolutional Neural Network

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 435
  • Download : 3
In this paper, a human action recognition method using a hybrid neu- ral network is presented. The method consists of three stages: preprocessing, feature extraction, and pattern classification. For feature extraction, we propose a modified convolutional neural network (CNN) which has a three-dimensional receptive field. The CNN generates a set of feature maps from the action de- scriptors which are derived from a spatiotemporal volume. A weighted fuzzy min-max (WFMM) neural network is used for the pattern classification stage. We introduce a feature selection technique using the WFMM model to reduce the dimensionality of the feature space. Two kinds of relevance factors between features and pattern classes are defined to analyze the salient features.
Publisher
Springer Verlag (Germany)
Issue Date
2007
Citation

Lecture Notes on Computer Science, Vol.4492, pp.715-723

ISBN
978-3-540-72392-9
DOI
10.1007/978-3-540-72393-6_85
URI
http://hdl.handle.net/10203/17220
Appears in Collection
CS-Journal Papers(저널논문)

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0