Action recognition based on the feature trajectories

Authors:
Ji-Xiang Du;Kai Yang;Chuan-Min Zhai
Affiliations:
Department of Computer Science and Technology, Huaqiao University, Xiamen, China;Department of Computer Science and Technology, Huaqiao University, Xiamen, China;Department of Computer Science and Technology, Huaqiao University, Xiamen, China
Venue:
ICIC'12 Proceedings of the 8th international conference on Intelligent Computing Theories and Applications
Year:
2012

Citing 6
Cited 0

The visual analysis of human movement: a survey

Computer Vision and Image Understanding
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Actions as Space-Time Shapes

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Human detection using oriented histograms of flow and appearance

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we proposed an intuitive approach on videos based on the feature trajectories. In contrast to the spatio-temporal interest points, feature trajectories is a more adapted representation and able to benefit from the rich motion information which is described by the HOF. The main contribution of our paper is the combination of the HOG and HOF feature description which represented the shape information and the motion information. We present recognition results on a variety of dataset such as YouTobe and KTH, compared to previous work, the results showed that our algorithm is more efficient and accurate compared with the previous work.