TRAJECTORIES-BASED MOTION NEIGHBORHOOD FEATURE FOR HUMAN ACTION RECOGNITION

被引:0
|
作者
Xiao, Xiang [1 ]
Hu, Haifeng [1 ]
Wang, Weixuan [1 ]
机构
[1] Sun Yat Sen Univ, Sch Elect & Informat Engn, Guangzhou, Guangdong, Peoples R China
来源
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2017年
关键词
Action Recognition; Dense Trajectories; Improved VLAD; linear SVM;
D O I
暂无
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
Recently, a common and popular method that produces competitive accuracy is to employ dense trajectories to identity human action. However, computing descriptors of dense trajectories may spend lots of time, and many trajectories which belong to the background trajectories may not be useful for the recognition. Moreover, the relationship between trajectories is always ignored. In this paper, we propose a trajectories-based motion neighborhood feature (TMNF) method for action recognition. We first select the trajectories of central particular region at the original video resolution to reduce the computation as well as the background trajectories. A new descriptor, which is referred to as TMNF, is proposed to explore the orientation and motion relationship between different trajectories. Finally, an improved vector of locally aggregated descriptors (IVLAD) method is used to represent videos and linear SVM is applied for classification. Experiments on the YouTube dataset demonstrate that our approach achieves superior performance.
引用
收藏
页码:4147 / 4151
页数:5
相关论文
共 50 条
  • [21] Structural feature representation and fusion of human spatial cooperative motion for action recognition
    Chao, Xin
    Hou, Zhenjie
    Mo, Yujian
    Shi, Haiyong
    Yao, Wenjing
    MULTIMEDIA SYSTEMS, 2023, 29 (03) : 1301 - 1314
  • [22] On the use of Local Motion Information for Human Action Recognition via Feature Selection
    Ladjailia, Ammar
    Bouchrika, Imed
    Merouani, Hayet Farida
    Harrati, Nouzha
    2015 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2015, : 160 - +
  • [23] Structural feature representation and fusion of human spatial cooperative motion for action recognition
    Xin Chao
    Zhenjie Hou
    Yujian Mo
    Haiyong Shi
    Wenjing Yao
    Multimedia Systems, 2023, 29 : 1301 - 1314
  • [24] Motion Feature Network: Fixed Motion Filter for Action Recognition
    Lee, Myunggi
    Lee, Seungeui
    Son, Sungjoon
    Park, Gyutae
    Kwak, Nojun
    COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 : 392 - 408
  • [25] Human Motion Recognition Based on Feature Fusion and Transfer Learning
    Luo X.
    Li Q.
    Progress In Electromagnetics Research C, 2024, 143 : 11 - 21
  • [26] A Local Feature-based Human Motion Recognition Framework
    Lai, Yu-Chun
    Liao, Hong-Yuan Mark
    Lin, Cheng-Chung
    Chen, Jian-Ren
    Luo, Y. -F. Peter
    ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5, 2009, : 722 - +
  • [27] Human motion recognition based on feature fusion and residual networks
    Luo, Xiaoyu
    Li, Qiusheng
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [28] Human action recognition based on AdaBoost algorithm for feature extraction
    Ji, Xiaofei
    Zhou, Lu
    Li, Yibo
    2014 IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY (CIT), 2014, : 801 - 805
  • [29] Research on Human Action Recognition Algorithm Based on Sine Feature
    Zhang, Haiyun
    Dou, Huazhou
    Li, Bo
    2020 4TH INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2020), 2020, 1518
  • [30] Human Action Recognition Based on Dense Trajectories Analysis and Random Forest
    PinZhong Pan
    ChungLin Huang
    Journal of Electronic Science and Technology, 2016, 14 (04) : 370 - 376