Selecting Effective and Discriminative Spatio-Temporal Interest Points for Recognizing Human Action

スポンサーリンク

概要

• 論文の詳細を見る

• Many successful methods for recognizing human action are spatio-temporal interest point (STIP) based methods. Given a test video sequence, for a matching-based method using a voting mechanism, each test STIP casts a vote for each action class based on its mutual information with respect to the respective class, which is measured in terms of class likelihood probability. Therefore, two issues should be addressed to improve the accuracy of action recognition. First, effective STIPs in the training set must be selected as references for accurately estimating probability. Second, discriminative STIPs in the test set must be selected for voting. This work uses <I>ε</I>-nearest neighbors as effective STIPs for estimating the class probability and uses a variance filter for selecting discriminative STIPs. Experimental results verify that the proposed method is more accurate than existing action recognition methods.

• The Institute of Electronics, Information and Communication Engineersの論文

著者

• CHEN Shu-Yuan

  Department of Computer Science and Engineering, Yuan Ze University

• ZHANG Hongbo

  School of Information Science and Technology, Xiamen University

• LI Shaozi

  School of Information Science and Technology, Xiamen University

• SU Songzhi

  School of Information Science and Technology, Xiamen University

関連論文

• Selecting Effective and Discriminative Spatio-Temporal Interest Points for Recognizing Human Action

スポンサーリンク