| 基于L2,1范数稀疏特征选择和超法向量的深度图像序列行为识别 |
| |
| 引用本文： | 宋相法,张延锋,郑逢斌.基于L2,1范数稀疏特征选择和超法向量的深度图像序列行为识别[J].计算机科学,2017,44(2):306-308, 323. |
| |
| 作者姓名： | 宋相法 张延锋 郑逢斌 |
| |
| 作者单位： | 河南大学计算机与信息工程学院 开封475004,河南大学计算机与信息工程学院 开封475004,河南大学计算机与信息工程学院 开封475004 |
| |
| 基金项目： | 本文受国家自然科学基金(U1504611,61272282),河南省教育厅科学技术研究重点项目(15A520010)资助 |
| |
| 摘 要： | 结合L2,1范数稀疏特征选择和超法向量提出了一种新的深度图像序列行为识别方法。首先从深度图像序列中提取超法向量特征；然后利用L2,1范数稀疏特征选择方法从超法向量特征中选择出最具判别性的稀疏特征子集作为特征表示；最后利用线性分类器Liblinear进行分类。在MSR Action3D数据库上的实验结果表明,所提方法使用2%的超法向量特征获得的识别率为94.55%,并且 具有比 其他方法更高的识别精度。
|
| 关 键 词： | 行为识别 深度图像序列 超法向量 稀疏特征选择 L2 1范数 |
| 收稿时间： | 2016/2/26 0:00:00 |
| 修稿时间： | 2016/5/29 0:00:00 |
Activity Recognition from Depth Image Sequences Based on L2,1-norm Sparse Feature Selection and Super Normal Vector |
| |
| SONG Xiang-f,ZHANG Yan-feng and ZHENG Feng-bin.Activity Recognition from Depth Image Sequences Based on L2,1-norm Sparse Feature Selection and Super Normal Vector[J].Computer Science,2017,44(2):306-308, 323. |
| |
| Authors: | SONG Xiang-f ZHANG Yan-feng and ZHENG Feng-bin |
| |
| Affiliation: | School of Computer and Information Engineering,Henan University,Kaifeng 475004,China,School of Computer and Information Engineering,Henan University,Kaifeng 475004,China and School of Computer and Information Engineering,Henan University,Kaifeng 475004,China |
| |
| Abstract: | This paper presented a novel method of activity recognition from depth image sequences based on L2,1-norm sparse feature selection and super normal vector.First,the super normal vector feature is extracted from depth image sequences.Then the most discriminative feature subset is selected from the whole super normal vector feature set based on the method of L2,1-norm sparse feature selection.Finally,the classification is based on Liblinear classifier.Experimental results on MSR Action3D dataset show that the proposed method achieves 94.55% of recognition accuracy using only 2% of the whole super normal vector feature,and is superior to the state-of-art methods. |
| |
| Keywords: | Activity recognition Depth image sequences Super normal vector Sparse feature selection L2 1-norm |
|
|
点击此处可从《计算机科学》下载全文 |
|
