[1]WANG Ce,JI Xiaofei,LI Yibo.Study on a simple view-invariant action recognition method[J].CAAI Transactions on Intelligent Systems,2014,9(5):577-583.[doi:10.3969/j.issn.1673-4785.201307057]
Copy

Study on a simple view-invariant action recognition method

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 9 Number of periods: 2014 5 Page number: 577-583 Column: 学术论文—机器学习 Public date: 2014-10-25
Title:
Study on a simple view-invariant action recognition method
Author(s):
WANG Ce;  JI Xiaofei;  LI Yibo
School of Automation, Shenyang Aerospace University, Shenyang 110136, China
Keywords:
action recognition; view-invariant; view-space partitioning; interest points; optical flow; mixed feature; hidden Markov model; likelihood probability weighted fusion
CLC:
TP391.4
DOI:
10.3969/j.issn.1673-4785.201307057
Abstract:
It is difficult to recognize the human actions under view changes in daily living. In order to solve this problem, a novel multi-view space hidden Markov model algorithm for view-invariant action recognition based on view space partitioning is proposed in this paper. First, the whole view space is partitioned into multiple sub-view spaces according to the rotation direction of a person relative to camera. Next, a view-robust feature representation by combination of the bag of interest point words in shot length-based video and amplitude histogram of local optical flow is utilized for describing the information of human actions. Thereafter, the human action models in each sub-view space are trained by HMM algorithm. Finally, the unknown view action is recognized via the likelihood probability weighted fusion of the corresponding action models in multi-view space. The experimental results on multi-view action recognition dataset IXMAS demonstrated that the proposed approach is easy to implement and has satisfactory performance for the unknown view action recognition.
References:
[1] WEINLAND D, RONFARD R, BOYER E. A survey of vision-based methods for action representation, segmentation, and recognition [J]. Computer Vision and Image Understanding, 2011, 115(2):224-241
[2] SEO H, MILANFAR P. Action recognition from one example[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):867-882.
[3] JI X, LIU H. Advances in view-invariant human motion analysis:a review[J]. IEEE Transactions on Systems, Man and Cybernetics, Part C, 2010, 40(1):13-24.
[4] JUNEJO I, DEXTER E, LAPTEV I. Action recognition from temporal self-similarities[C]//Proceeding of the 10th European Conference on Computer Vision. Marseille, France, 2008:293-306.
[5] LYU F, NEVATIA R. Recognition and segmentation of 3-D human action using HMM and multi-class AdaBoost[C]//Proceeding of the 9th European Conference Computer Vision, Graz, 2006:359-372
[6] YU S, TAN D, TAN T. Modelling the effect of view angle variation on appearance-based gait recognition[C]//Proceeding of the 8th Asian Conference Computer Vision. Hyderabad, 2006:807-816.
[7] WEINLAND D, RONFARD R, BOYER E. Free viewpoint action recognition using motion history volumes[J]. Computer Vision and Image Understanding, 2006, 104(2):249-257.
[8] PEURSUM P, VENKATESH S, WEST G. Tracking as recognition for articulated full body human motion analysis[C]//Proceeding of the 25th IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007:1-8.
[9] LYU F, NEVATIA R. Single view human action recognition using key pose matching and Viterbi path searching//Proceeding of the 25th IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007:1-8.
[10] DOLLAR P, RABAUD V, COTTRELL G, et al. Behavior recognition via sparse spatio-temporal features[C]//Proceeding of IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. 2005:65-72.
[11] SONG Y, TANG S. A distribution based video representation for human action recognition[C]//Proceeding of the IEEE International Conference on Multimedia and Expo. Suntec, Singapore, 2010:772-777.
[12] REN H, THOMAS B. Action recognition using salient neighboring histograms[C]//Proceeding of the 20th IEEE International Conference on Image Processing. Melbourne, Australia, 2013:2807-2811.
[13] BREGOMZIO M, GONG S, XIANG T. Recognizing action as clouds of space-time interest points[C]//Proceeding of the 27th IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009:1948-1955.
[14] SCOVANNER P, ALI S, SHAH M. A 3-dimensional sift descriptor and its application to action recognition[C]//Proceeding of the 15th International Conference on Multimedia. Augsburg, Germany, 2007:357-360.
[15] 姬晓飞, 王策, 李一波. 一种基于视角鲁棒性特征的人体动作识别方法研究[C]//第32届中国控制会议论文集. 西安, 中国, 2013:3877-3881.JI Xiaofei, WANG Ce, LI Yibo. An action recognition method based on view-insensitive feature representation[C]//Proceeding of the 32th Chinese Control Conference. Xi’an, China, 2013:3877-3881.
[16] TRAN D, SOROKIN A. Human activity recognition with metric learning[C]//Proceeding of the 10th European Conference on Computer Vision. Marseille, France, 2008:548-561.
[17] JUNEJO I, DEXTER E, LAPTEV I, et al. Cross-view action recognition from temporal self-similarities[C]//Proceeding of the 10th European Conference on Computer Vision. Marseille, France, 2008:293-306.
[18] WEINLAND D, OZUYSAL M, FUA P. Making action recognition robust to occlusions and viewpoint changes[C]//Proceeding of the 11th European Conference on Computer Vision. Heraklion, Greece, 2010:635-648.
[19] LIU J, SHAH M, KUIPERS B, et al. Cross-view action recognition via view knowledge transfer[C]//Proceeding of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Colorado, USA, 2011:3209-3216.
[20] JIANG Z, ZHE L, LARRY D. Recognizing human actions by learning and matching shape-motion prototype trees[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3):533-547.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems