摘要
提出一种基于行为能量图像(AEI)和双向二维主成分分析((2D)2PCA)的行为分类算法解决行为分类问题。该算法利用AEI作为识别特征,无需运动周期的分割,运用(2D)2PCA对特征空间降维,用最近邻方法分类。实验结果表明,该算法能以较少的运行时间获得较高的分类准确率。
To efficiently resolve action classification problem, a classification algorithm based on Action Energy Image（AEI） is proposed. The high dimensional feature space is reduced to lower dimensional space with （2D）^2PCA. The nearest-neighbor classifier is adopted to distinguish different actions. It need not extract the period of the video, which is indispensable in some other methods. Experimental results show that the algorithm achieves higher classification accuracy with less running time and less memory space.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第24期145-146,149,共3页
Computer Engineering
基金
黑龙江省杰出青年科学基金资助项目(JC200703)
哈尔滨市科技创新人才研究专项基金资助项目(2007RFXXG009)
国家重点实验室开放基金资助项目(SKLRS200702)
