Human action recognition by SOM considering the probability of spatio-temporal features

Authors:
Yanli Ji;Atsushi Shimada;Rin-ichiro Taniguchi
Affiliations:
Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan;Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan;Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan
Venue:
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
Year:
2010

Citing 9
Cited 0

Self-Organizing Maps

Self-Organizing Maps
Space-time Interest Points

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Recognizing Human Actions: A Local SVM Approach

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
A Bayesian Hierarchical Model for Learning Natural Scene Categories

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Creating Efficient Codebooks for Visual Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Behavior recognition via sparse spatio-temporal features

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
A 3-dimensional sift descriptor and its application to action recognition

Proceedings of the 15th international conference on Multimedia
An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Machine learning for high-speed corner detection

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an action recognition system was invented by proposing a compact 3D descriptor to represent action information, and employing self-organizing map (SOM) to learn and recognize actions. Histogram Of Gradient 3D (HOG3D) performed better among currently used descriptors for action recognition. However, the calculation of the descriptor is quite complex. Furthermore, it used a vector with 960 elements to describe one interest point. Therefore, we proposed a compact descriptor, which shortened the support region of interest points, combined symmetric bins after orientation quantization. In addition, the top value bin of quantized vector was kept instead of setting threshold experimentally. Comparing with HOG3D, our descriptor used 80 bins to describe a point, which reduced much computation complexity. The compact descriptor was used to learn and recognize actions considering the probability of local features in SOM, and the results showed that our system outperformed others both on KTH and Hollywood datasets.