Slow Feature Analysis for Human Action Recognition
文献类型：期刊论文
| 作者 | Zhang, Zhang1 ; Tao, Dacheng2
|
| 刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
 |
| 出版日期 | 2012-03-01 |
| 卷号 | 34期号:3页码:436-450 |
| 关键词 | Human action recognition slow feature analysis |
| 英文摘要 | Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal [1]. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. Experimental results suggest that the SFA-based approach 1) is able to extract useful motion patterns and improves the recognition performance, 2) requires less intermediate processing steps but achieves comparable or even better performance, and 3) has good potential to recognize complex multiperson activities. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
| 研究领域[WOS] | Computer Science ; Engineering |
| 关键词[WOS] | FACE RECOGNITION ; POINTS |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000299381600002 |
| 公开日期 | 2015-09-22 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/8003]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 2.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia |
| 推荐引用方式 GB/T 7714 | Zhang, Zhang,Tao, Dacheng. Slow Feature Analysis for Human Action Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2012,34(3):436-450. |
| APA | Zhang, Zhang,&Tao, Dacheng.(2012).Slow Feature Analysis for Human Action Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,34(3),436-450. |
| MLA | Zhang, Zhang,et al."Slow Feature Analysis for Human Action Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 34.3(2012):436-450. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。