Selecting Effective and Discriminative Spatio-Temporal Interest Points for Recognizing Human Action
首发时间:2012-11-05
Abstract:Many successful methods for recognizing human action are spatio-temporal interest point (STIP) based methods. Given a test video sequence, for matching-based method using 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 test set must be selected for voting. This work uses e-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.paper.
keywords: Artificial Intelligence Human action recognition discriminative power class likelihood probability variance filter.
点击查看论文中文信息
人体行为识别中具有判别力的时空特征选择方法
摘要:针对人体行为识别中时空特征的类条件概率估计问题和特征选择问题,本文提出基于改进的类条件概率估计的人体行为识别方法,以及基于互信息方差的特征选择方法。实验结果表明本文提出的方法能有效提高时空特征的类条件概率估计的准确性以及选择判别性强的时空特征,从而提高人体行为识别的准确率。
基金:
论文图表:
引用
No.****
同行评议
勘误表
人体行为识别中具有判别力的时空特征选择方法
评论
全部评论0/1000