DocumentCode :
177852
Title :
A Framework of Multi-classifier Fusion for Human Action Recognition
Author :
Bagheri, M.A. ; Gang Hu ; Qigang Gao ; Escalera, S.
Author_Institution :
Fac. of Comput. Sci., Dalhousie Univ., Halifax, NS, Canada
fYear :
2014
fDate :
24-28 Aug. 2014
Firstpage :
1260
Lastpage :
1265
Abstract :
The performance of different action-recognition methods using skeleton joint locations have been recently studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of five action learning techniques, each performing the recognition task from a different perspective. The underlying rationale of the fusion approach is that different learners employ varying structures of input descriptors/features to be trained. These varying structures cannot be attached and used by a single learner. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a poorly performing learner. This leads to having a more robust and general-applicable framework. Also, we propose two simple, yet effective, action description techniques. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers´ output, showing advanced performance of the proposed methodology.
Keywords :
computer vision; feature extraction; image classification; image fusion; inference mechanisms; learning (artificial intelligence); Dempster-Shafer theory; action description techniques; action learning techniques; computer vision; human action recognition; input descriptors; input features; multiclassifier fusion; performance evaluation; recognition performance improvement; skeleton joint locations; Accuracy; Gesture recognition; Joints; Support vector machines; Three-dimensional displays; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
ISSN :
1051-4651
Type :
conf
DOI :
10.1109/ICPR.2014.226
Filename :
6976936
Link To Document :
بازگشت