Expandable data-driven graphical modeling of human actions based on salient postures Li, Wanqing; Zhang, Zhengyou; Liu, Zicheng

User activity

Share to:
Li, Wanqing ; Zhang, Zhengyou ; Liu, Zicheng
Physical Sciences and Mathematics; era2012
Li, W., Zhang, Z. & Liu, Z. (2008). Expandable data-driven graphical modeling of human actions based on salient postures. IEEE Transactions on Circuits and Systems for Video Technology, 18 (11), 1499-1510. This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred to as action graph, where nodes of the graph represent salient postures that are used to characterize the actions and are shared by all actions. The weight between two nodes measures the transitional probability between the two postures represented by the two nodes. An action is encoded as <em>one</em> or multiple paths in the action graph. The salient postures are modeled using Gaussian mixture models (GMMs). Both the salient postures and action graph are automatically learned from training samples through unsupervised clustering and expectation and maximization (EM) algorithm. The proposed action graph not only performs effective and robust recognition of actions, but it can also be expanded efficiently with new actions. An algorithm is also proposed for adding a new action to a trained action graph without compromising the existing action graph. Extensive experiments on widely used and challenging data sets have verified the performance of the proposed methods, its tolerance to noise and viewpoints, its robustness across different subjects and data sets, as well as the effectiveness of the algorithm for learning new actions.
Work ID

2 editions of this work

Find a specific edition
Thumbnail [View as table] [View as grid] Title, Author, Edition Date Language Format Libraries

User activity

e.g. test cricket, Perth (WA), "Parkes, Henry"

Separate different tags with a comma. To include a comma in your tag, surround the tag with double quotes.

Be the first to add a tag for this work

Be the first to add this to a list

Comments and reviews

What are comments? Add a comment

No user comments or reviews for this work

Add a comment

Show comments and reviews from Amazon users