静止背景下的人体行为识别方法

doi:10.3969/j.issn.1000-3428.2017.10.032

计算机工程

静止背景下的人体行为识别方法

高晨兰,朱嘉钢

(江南大学物联网工程学院,江苏无锡 214122)

收稿日期:2016-10-09 出版日期:2017-10-15 发布日期:2017-10-15
作者简介:高晨兰(1992—),女,硕士研究生,主研方向为图形图像处理、人工智能、模式识别;朱嘉钢,副教授、博士。
基金资助:
江苏省产学研项目(BY2013015-40)。

Human Actions Recognition Method Under Stationary Background

GAO Chenlan,ZHU Jiagang

(School of Internet of Things Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China)

Received:2016-10-09 Online:2017-10-15 Published:2017-10-15

摘要/Abstract

摘要：

在实际工程中多数监控摄像头是固定的,为了使计算能力有限的智能摄像头实时地进行人体行为识别,提出一种将无迭代双边二维主成分分析方法(NIB2DPCA)与高斯混合模型(GMM)相结合的行为识别方法。提取视频帧序列中运动前景的稠密光流,绘制运动矢量时空(MVFI)模板,利用NIB2DPCA对MVFI模板作特征抽取,通过GMM对特征数据建模从而实现行为分类。测试结果表明,与轨迹云比较法相比,该方法对视频中的行为信息进行了有效地压缩,使得计算耗时缩短了90%以上,同时保持了较高的识别率。

关键词: 人体行为识别, 运动特征, 运动矢量, 特征抽取, 高斯混合模型

Abstract:

Aiming at the situation that most surveillance cameras are fixed in practical engineering applications,in order to enable the intelligent cameras with limited computing ability to identify human actions in real time,an action recognition method combining Non-iteration-bilateral-projection Based Two Dimensional Principal Component Analysis(NIB2DPCA) and Gaussian Mixture Model(GMM) is proposed.The dense optical flow of the motion foreground in the video frame sequence is extracted to draw the Motion Vector Flow Instance(MVFI) template.NIB2DPCA is employed for feature extraction from MVFI templates.The feature data is modeled by GMM to construct the classifier for recognizing human actions.Test results show that compared with the trajectory cloud comparison method,the proposed method which effectively compresses the action information in the video reduces the calculation time by more than 90% while maintaining a high recognition rate at the same time.

Key words: human actions recognition, motion feature, motion vector, feature extraction, Gaussian Mixture Model(GMM)

中图分类号:

TP391.413

高晨兰,朱嘉钢. 静止背景下的人体行为识别方法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.10.032.

GAO Chenlan,ZHU Jiagang. Human Actions Recognition Method Under Stationary Background[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.10.032.

https://www.ecice06.com/CN/Y2017/V43/I10/192

参考文献

参考文献［1］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. ［2］WANG L,SUTER D.Informative Shape Representations for Human Action Recognition［C］//Proceedings of International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2006:1266-1269. ［3］DERPANIS K G,SIZINTSEV M,CANNONS K,et al.Efficient Action Spotting Based on a Spacetime Oriented Structure Representation［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:1990-1997. ［4］OLIVIERI D N,CONDE I G,SOBRINO X A V.Eigenspace-based Fall Detection and Activity Recogni-tion from Motion Templates and Machine Learning［J］.Expert Systems with Applications,2012,39(5):5935-5945. ［5］WANG H,SCHMID C.Action Recognition with Improved Trajectories［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:3551-3558. ［6］VRIGKAS M,KARAVASILIS V,NIKOU C,et al.Matching Mixtures of Curves for Human Action Recognition［J］.Computer Vision and Image Under-standing,2014,119(2):27-40. ［7］ABRAMSON N,BRAVERMAN D,SEBESTYEN G.Pattern Recognition and Machine Learning［M］.［S.l.］:Academic Press,2006. ［8］GMEZ-CONDE I,OLIVIERI D N.A KPCA Spatio-temporal Differential Geometric Trajectory Cloud Classifier for Recognizing Human Actions in a CBVR System［J］.Expert Systems with Applications,2015,42(13):5472-5490. ［9］GUAN Yepeng.Robust Video Foreground Segmentation and Face Recognition［J］.Advances in Manufacturing,2009,13(4):311-315. ［10］FARNEBCK G.Two-frame Motion Estimation Based on Polynomial Expansion［J］.Image Analysis,2003,2749:363-370. ［11］LIN Z,JIANG Z,DAVIS L S.Recognizing Actions by Shape-motion Prototype Trees［C］//Proceedings of the 12th IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2009:444-451. ［12］LIU J,SHAH M.Learning Human Actions via Information Maximization［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8. ［13］WANG H,KLSER A,SCHMID C,et al.Action Recognition by Dense Trajectories［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:3169-3176. ［14］JHUANG H,SERRE T,WOLF L,et al.A Biologically Inspired System for Action Recognition［C］//Proceed-ings of the 11th International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2007:1-8. ［15］SCHULDT C,LAPTEV I,CAPUTO B.Recognizing Human Actions:A Local SVM Approach［C］//Pro-ceedings of the 17th International Conference on Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:32-36. 编辑刘冰

[1]	陈天宇, 楚程钱, 万思远, 万永菁, 孙静. 基于条件轻量级神经网络的视频入侵检测算法[J]. 计算机工程, 2023, 49(12): 152-160.
[2]	王佳波, 杨静. H.266/VVC中一种改进的仿射运动估计算法[J]. 计算机工程, 2022, 48(3): 296-301.
[3]	王文欣, 贺煜航, 陈刚. 基于EM路由算法的医学图像分割UCaps网络[J]. 计算机工程, 2022, 48(2): 268-274.
[4]	郭克友, 贺成博, 王凯迪, 王苏东, 李雪, 张沫. COVID‐19疫情下基于YOLOv4的安全社交距离风险评估[J]. 计算机工程, 2022, 48(10): 28-36.
[5]	谢树春, 陈志华, 盛斌. 增强细节的RGB‐IR多通道特征融合语义分割网络[J]. 计算机工程, 2022, 48(10): 230-237,244.
[6]	沙月, 杨静. H.266合并模式候选决策的研究与改进[J]. 计算机工程, 2022, 48(1): 260-265.
[7]	胡高珍, 徐胜军, 孟月波, 刘光辉, 冯峰, 段中兴. 基于边缘约束局部区域MRF的图像分割方法[J]. 计算机工程, 2021, 47(6): 253-261,270.
[8]	孙彦玺, 赵婉婉, 武东辉, 陈继斌, 仇森. 基于卷积长短时记忆网络的人体行为识别研究[J]. 计算机工程, 2021, 47(10): 260-268.
[9]	张墨华, 彭建华. 面向图像先验建模的可扩展高斯混合模型[J]. 计算机工程, 2020, 46(4): 220-227.
[10]	姚博凡, 邓红平, 蔡铭. 基于随机抽样GMM的城市交通运行状态模式分类[J]. 计算机工程, 2020, 46(12): 36-42.
[11]	郑文秀, 赵峻毅, 文心怡, 姚引娣. 基于瓶颈复合特征的声学模型建立方法[J]. 计算机工程, 2020, 46(11): 301-305,314.
[12]	邓路佳,刘平山. 基于GMM-FMs的广告点击率预测研究[J]. 计算机工程, 2019, 45(5): 122-126.
[13]	鹿天然,于凤芹,陈莹. 一种基于线性序列差异分析降维的人体行为识别方法[J]. 计算机工程, 2019, 45(3): 237-241,249.
[14]	王万耀,段先华,徐丹,於跃成,黄炜亮. 基于显著性的Grabcut图像分割方法[J]. 计算机工程, 2018, 44(7): 230-236,243.
[15]	朱晓妤,严云洋,刘以安,高尚兵. 基于深度森林模型的火焰检测[J]. 计算机工程, 2018, 44(7): 264-270.

选择文件类型/文献管理软件名称

选择包含的内容

静止背景下的人体行为识别方法

Human Actions Recognition Method Under Stationary Background

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

静止背景下的人体行为识别方法

Human Actions Recognition Method Under Stationary Background

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价