Action Recognition Based on Hierarchical Model

Yang-yang Wang (), Yang Liu and Jin Xu
Additional contact information
Yang-yang Wang: Shenyang Aerospace University
Yang Liu: Shenyang Aerospace University
Jin Xu: Shenyang Aerospace University

Chapter Chapter 10 in The 19th International Conference on Industrial Engineering and Engineering Management, 2013, pp 93-100 from Springer

Abstract: Abstract The feature representation of human actions is one of the important factors which influence the recognition accuracy of actions. Usually the recognition accuracy is higher, when the feature simultaneously includes both appearance and motion information. However the dimensions of the feature space is high, and this leads to high computational cost. To overcome this problem, we propose a hierarchical model for action recognition. In the first hierarchy, we adopt box features to divide the actions into two classes, according to whether or not legs are all almost stayed in a static place. In the second hierarchy, we construct different structure of motion feature descriptors to represent different kinds of actions, and use nearest neighbor classifier to obtain the final classification results. Experiments on the Weizmann dataset demonstrate the effectiveness of the proposed method.

Keywords: Action recognition; Box feature; Hierarchical model; Motion feature (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-38391-5_10

Ordering information: This item can be ordered from
http://www.springer.com/9783642383915

DOI: 10.1007/978-3-642-38391-5_10

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().