Earticle

초록

영어

Most of existed action recognition methods based on spatio-temporal descriptors have ignored their spatial distribution information. However the spatial distribution information usually is very useful to improve the discriminative ability of the motion representation. An improved spatio-temporal is proposed in this paper by combining local spatio-temporal feature and global positional distribution information (FEA) of interest points. Furthermore, in order to improve the classifier’s performance, an Adaboost-SVM method is utilized to recognize the human actions by using the proposed motion descriptor. The proposed recognition method is tested on the public dataset of KTH. The test results verified the proposed representation and recognition method can more accurately describe and recognize the human motion.

목차

Abstract
 1. Introduction
 2. Feature Extraction and Representation
  2.1. Interest Point Feature Extraction
  2.2. Interest Point Feature Dimension Reduction
  2.3 Position Distribution Information of Interest Points
  2.4. The Combination of the Interest point feature and PDI
 3. Action Recognition Based on Adaboost-SVM Classifiers
  3.1. AdaBoost Algorithm [17-18]
  3.2. Weak Classifiers Using SVM
 4. Experiment and Results Analysis
  4.1. Dataset
  4.2. Experimental Results
 5. Conclusion
 Acknowledgements
 References

키워드

저자

• Xiaofei Ji [ School of Automation, Shenyang Aerospace University Shenyang, China ]
• Lu Zhou [ School of Automation, Shenyang Aerospace University Shenyang, China ]
• Qianqian Wu [ School of Automation, Shenyang Aerospace University Shenyang, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605