Using Binary Decision Tree and Multiclass SVM for Human Gesture Recognition

被引：0

作者：

Oh, Juhee ^{[1
]}

Kim, Taehyub ^{[1
]}

Hong, Hyunki ^{[1
]}

机构：

[1] Chung Ang Univ, Dept Imaging Sci & Arts, GSAIM, Seoul 156756, South Korea

来源：

2013 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND APPLICATIONS (ICISA 2013) | 2013年

关键词：

Gesture recognition; kinect; binary decision tree; multiclass SVM; chain code;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a novel method to recognize the human gesture using binary decision tree and Multi-class Support Vector Machine (MCSVM). In a learning stage, 3D trajectory of the human gesture by a kinect sensor is assigned into the tree node of the binary decision tree according to its distribution property. The user's gesture trajectory is resampled and normalized, and we extract the chain code histogram at a regular interval. After training MCSVM in each node, we are able to recognize the human gestures.

引用

页数：4

共 13 条

[1]

[Anonymous], 2011, P 8 EUROGRAPHICS S S

[2]

[Anonymous], 2003, PROC GRAPHICON

[3]

Chen Ming-yu., 2010, Proceedings of the International Conference on Multimedia Information Retrieval (MIR'10), P405, DOI [DOI 10.1145/1743384, DOI 10.1145/1743384.1743453]

[4]

Francke H, 2007, LECT NOTES COMPUT SC, V4872, P533

[5]

Hong Taeho, 2009, Asia Pacific Journal of Information Systems, V19, P139

[6]

Jain H. P., 2010, TECHNICAL REPORT

[7]

Kang SI, 2011, IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE 2011), P155, DOI 10.1109/ICCE.2011.5722513

[8]

Kristensson P.O., 2012, P 2012 ACM INT C INT, P89, DOI DOI 10.1145/2166966.2166983

[9] An HMM-based threshold model approach for gesture recognition [J].

Lee, HK ;

Kim, JH .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (10) :961-973

[10] LATTICESVM-A New Method for Multi-class Support Vector Machines [J].

Liu Zhibin ;

Jin Lianwen .

2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, :727-733

← 1 2 →