[1]郭利,曹江涛,李平,等.累积方向-数量级光流梯度直方图的人体动作识别[J].智能系统学报,2014,9(01):104-108.[doi:10.3969/j.issn.1673-4785.201305001]
 GUO Li,CAO Jiangtao,LI Ping,et al.Human action recognition based on accumulated orientation-magnitude histograms of optical flow[J].CAAI Transactions on Intelligent Systems,2014,9(01):104-108.[doi:10.3969/j.issn.1673-4785.201305001]
点击复制

累积方向-数量级光流梯度直方图的人体动作识别(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第9卷
期数:
2014年01期
页码:
104-108
栏目:
出版日期:
2014-02-25

文章信息/Info

Title:
Human action recognition based on accumulated orientation-magnitude histograms of optical flow
作者:
郭利1 曹江涛1 李平1 姬晓飞2
1. 辽宁石油化工大学 信息与控制工程学院, 辽宁 抚顺 113001;
2. 沈阳航空航天大学 自动化学院, 辽宁 沈阳 110136
Author(s):
GUO Li1 CAO Jiangtao1 LI Ping1 JI Xiaofei2
1. School of Information and Control Engineering, Liaoning Shihua University, Fushun 113001, China;
2. School of Automation, Shenyang Aerospace University, Shenyang 110136, China
关键词:
人体动作识别Horn-Schunck光流方向-数量级直方图梯度直方图
Keywords:
human action recognitionHorn-Schunck optical floworientation-magnitude histogramsgradient histograms
分类号:
TP391.41
DOI:
10.3969/j.issn.1673-4785.201305001
摘要:
为了提高光流信息在人体动作识别系统中应用的效果和效率, 提出一种累计方向-数量级光流梯度直方图的人体动作特征表示方法。该方法首先利用Horn-Schunck充流算法计算图像光流, 然后将光流矢量按照不同的方向-数量级进行直方图统计, 得到单帧图像的方向-数量级的光流梯度直方图, 最后将单帧图像的直方图特征在时间维上进行累积来表示整个视频动作的特征。利用该特征在KTH动作视频库上进行动作识别测试, 4个场景的混合测试得到了87.5%的平均正确识别率, 验证了算法的有效性。
Abstract:
In order to improve the recognition rate and efficiency of optical flow in the human action recognition system, a novel method for human action representation based on the accumulated orientation-magnitude gradient histograms of the optical flow is proposed in this paper. First the image optical flow is computed, and then every flow vector is counted according to the orientation-magnitude to obtain orientation-magnitude histograms of single frame image. Finally information of the video sequence can be represented by accumulating orientation-magnitude histograms in time dimension. The proposed feature is evaluated on a standard database of human actions: KTH. The experiment conducted on the four scenes demonstrates that this algorithm is effective and achieves a correct recognition rate of 87.5% with the KTH dataset.

参考文献/References:

[1] BLANK M, GORELICK L, SHECHTMAN E, et al. Actions as space-time shapes[C]//Proceedings of the International Conference on Computer Vision. Beijing, China, 2005: 1395-1402.
[2] GORELICK L, BLANK M, SHECHTMAN E, et al. Actions as space-time shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2247-2253.
[3] YILMAZ A, SHAH M. A differential geometric approach to representing the human actions[J]. Computer Vision and Image Understanding, 2008, 119(3): 335-351.
[4] LAPTEV I, LINDEBERG T. Space-time interest points[C]//Proceedings of the International Conference on Computer Vision. Nice, France, 2003: 432-439.
[5] LAPTEV I, CAPUTO B, SCHVLDT C, et al. Local velocity-adapted motion events for spatio-temporal recognition[J]. Computer Vision and Image Understanding, 2007, 108(3): 207-229.
[6] OIKONOMOPOULOS A, PATRAS I, PANTIC M. Spatiotemporal salient points for visual recognition of human actions[J]. IEEE Transactions on Systems Man and Cybernetics-Part B: Cybernetics, 2006, 36(3): 710-719.
[7] DANAFAR S, GHEISSARI N. Action recognition for surveillance applications using optic flow and SVM[C]//Proceedings of the Asian Conference on Computer Vision. Tokyo, Japan, 2007: 457-466.
[8] TRAN D, SOROKIN A. Human activity recognition with metric learning[C]//Proceedings of the European Conference on Computer Vision. Marseille, France, 2008: 61-66.
[9] ZHANG Ziming, HU Yiqun, CHAN Syin, et al. Motion context: a new representation for human action recognition[C]//Proceedings of the European Conference on Computer Vision. Marseille, France, 2008: 817-829.
[10] FAN Rongen, CHEN Paihsuen, LIN Chihjen. Working set selection using second order information for training SVM[J]. Journal of Machine Learning Research, 2005, 6: 1889-1918.
[11] LIU Jingen, LUO Jiebo, SHAN M. Recognizing realistic actions from videos "in the wild"[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1996-2003.
[12] QIN Yaohui, LI Hongliang, LIU Guanghui, et al. Human action recognition using PEM histogram[C]//IEEE International Conference on Computational Problem Solving. Singapore, 2010: 323-325.

备注/Memo

备注/Memo:
收稿日期:2013-05-02。
基金项目:国家自然科学青年基金资助项目(61103123).
作者简介:郭利,女,1987年生,硕士研究生,主要研究方向为模式识别、图像处理;李平,男,1964年生,教授、博士生导师,IEEE高级会员,中国自动化学会过程控制专业委员会委员,入选辽宁省百千万人才工程百人层次,主要研究方向为工业过程的先进控制理论及其应用。承担国家"863"计划项目、国家自然科学基金等项目多项,发表学术论文100余篇,其中被SCI、EI检索50余篇。
通讯作者:曹江涛,男,1978年生,教授、博士,中国自动化学会机器人专业委员会委员和青工委委员,入选辽宁省百千万人才工程千人层次、首批辽宁省高校杰出青年学者成长计划,主要研究方向为智能方法及其在工业控制和视频信息处理上的应用。承担国家自然科学基金等项目多项,发表学术论文40余篇,其中被SCI检索6篇、EI检索22篇.E-mail:jiangtao.cao08@gmail.com.
更新日期/Last Update: 1900-01-01