光学技术, 2017, 43 (4): 323, 网络出版: 2017-08-09   

一种基于关键帧的人体行为识别方法

A human behavior recognition method based on key frames
作者单位
上海理工大学  光电信息与计算机工程学院,  上海  200093
摘要
为了提高人体动作识别的准确率和实时性, 提出了一种基于关键帧的人体行为识别新方法。用Kinect提取人体骨架信息(各关节点的3D坐标), 将中心点(人体基准参考点)分别与其他各关节点作结构向量, 根据空间不变性选取中心向量, 计算各个结构向量和中心向量之间的夹角,并将夹角的角速度作为一种新的姿态描述特征, 利用AP (Affinity Propagation)聚类算法提取关键帧, 利用SVM将得到的关键帧进行动作序列的分类。在Cornell Activity Dataset-60 (CAD-60)数据库实验结果表明, 新方法具有良好的识别能力。
Abstract
In order to improve the accuracy and real time of human action recognition, a new method about recognition of human behavior based on key frame is proposed. The information (coordinates of all human joints) of human skeleton is extracted and the structural vectors based on the center (body baseline reference point) and each other joints are constituted. According to the invariance of spatial, the angular velocities of joint angles are calculated between the respective structural vectors. The center vector is considered as a new feature. The AP clustering algorithm is used to extract key frames. The key frames are classified by SVM. The results of experiment at Cornell Activity Dataset-60 (CAD-60) show that the algorithm has a good recognition rate.
参考文献

[1] KONSTANTINIDIS K, GASTERATOS A, ANDREADIS I. Image retrieval based on fuzzy color histogram processing[J]. Optics Communications, 2005, 248(4-6):375-386.

[2] 胡琼, 秦磊, 黄庆明. 基于视觉的人体动作识别综述[J].计算机学报, 2013, 36(12): 2512-2524.

    HU Qiong, QIN Lei, HUANG Qingming. A survey on visual human action recognition[J]. Chinese Journal of Computers, 2013, 36(12): 2512-2524.

[3] WEINLAND D, RONFARD R, BOYER E. A survey of vision-based methods for action representation, segmentation and recognition[J]. Comput. Vis. Image Underst., 2011,115 (2) : 224-241.

[4] LIU C, YUEN P C. Human action recognition using boosted Eigen Actions[J]. Image Vis. Comput., 2010,28 (5) :825-835.

[5] LIM I S, THALMANN D. Key posture extraction out of human motion data by curve simplification[C]∥Proceedings of the International Conference of the IEEE Engineering in Medicine and Biology Society, Turkey: Istanbul, USA: IEEE, 2001: 116-1169.

[6] WANG J, BODENHEIMER B. An evaluation of a cost metric for selecting transitions between motion segments[C]∥Proceedings of the ACM SIGGRAPH/Eurographics symposium on Computer animation, San Diego, California, USA: Eurographics Association, 2003: 232-238.

[7] LEE J, CHAI J, REITSMA P S A. Interactive control of avatars animated with human motion data[J]. ACM Transactions on Graphics (S0730-0301), 2002, 21(3): 491-500.

[8] Meinard Muller. Information retrieval for music and motion[M]. USA: Springer-Verlag New York, Inc., 2007.

[9] WANG J, LIU Z, WU Y, et al. Mining actionlet ensemble for action recognition with depth cameras[C]∥Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, IEEE, 2012: 1290-1297.

[10] LIU L, SHAO L, ROCKETT P. Boosted key-frame selection and correlated pyramidal motion-feature representation for human action recognition[J]. Pattern Recogn, 2013,46 (7):1810-1818.

[11] 彭淑娟. 基于中心距离特征的人体运动序列关键帧提取[J]. 系统仿真学报, 2012, 24(3): 61-65.

    PENG Shujuan. Key frame extraction using central distance feature for human motion data[J]. Journal of System Simulation, 2012, 24(3): 61-65.

[12] WANG Y, SUN S, DING X. A self-adaptive weighted affinity propagation clustering for key frames extraction on human action recognition[J]. Journal of Visual Communication & Image Representation, 2015, 33(C):193-202.

[13] 朱映映, 周洞汝. 一种基于视频聚类的关键帧提取方法[J]. 计算机工程, 2004, 30(4):12-13.

    ZHU Yingying, ZHOU Dongru. An approach of key frame extraction based on video clustering[J]. Computer Engineering, 2004, 30(4):12-13.

[14] 印勇, 蒋海娜.优化初始聚类中心的关键帧提取[J]. 计算机工程与应用, 2007, 43(21): 165-167.

    YIN Yong, JAING Haina, Key frame extraction based on clustering of optimizing initial centers[J]. Computering and Application, 2007, 43(21): 165-167.

[15] 石祥滨, 刘拴朋, 张德园. 基于关键帧的人体动作识别方法[J]. 系统仿真学报, 2015, 27(10): 2401-2408.

    SHI Xiangbin, LIU Shuanpeng, ZHANG Deyuan. An approach of human action recognition based on key frames[J]. Journal of System Simulation, 2015, 27(10): 2401-2408.

[16] FREY B J, DUECK D. Clustering by passing messages between data points[J]. Science, 2007,5814(315): 972-976.

[17] CHANG C C, LIN C J. LIBSVM: A library for support vector machines[J]. ACM Trans. Intell. Syst. Technol. (TIST), 2011,2 (3): 27.

[18] 陈本廷, 周骛, 蔡小舒,等. 基于K-均值聚类的岩芯偏振显微图像粒径分析[J]. 上海理工大学学报, 2016, 38(4): 341-345.

    CHEN Benting ZHOU Wu, CAI Xiaoshu, et al. New method for the segmentation of polarizing microscope image of rock core based on K-means cluster algorithm[J]. J. University of Shanghai for Science and Technology, 2016, 38(4): 314-345.

[19] 杨晓慧, 王莉莉, 李登峰. 一种新的层次谱聚类算法[J]. 上海理工大学学报, 2014, 36(1):49-52.

    YANG Xiaohui, WANG Lili, LI Dengfeng. New hierarchical spectral clustering algorithm[J]. J. University of Shanghai for Science and Technology, 2014, 36(1): 49-52.

梅阳, 王永雄, 秦琪, 尹钟, 张孙杰. 一种基于关键帧的人体行为识别方法[J]. 光学技术, 2017, 43(4): 323. MEI Yang, WANG Yongxiong, QIN Qi, YIN Zhong, ZHANG Sunjie. A human behavior recognition method based on key frames[J]. Optical Technique, 2017, 43(4): 323.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!