An Unsupervised Feature learning and clustering method for key frame extraction on human action recognition

被引:0
|
作者
Pei, Xiaomin [1 ]
Fan, Huijie [1 ]
Tang, Yandong [1 ]
机构
[1] Chinese Acad Sci, Shenyang Inst Automat, State Key Lab Robot, Shenyang 110016, Liaoning, Peoples R China
关键词
human action recognition; learning feature; stacked aut-encoder; Affinity Propagation Clustering;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recognizing Human action in video is an very active research topic. There are a growing variety of human action datasets with different video length, different practitioners. Make human action recognition becomes a very difficult topic. A majority researchers solve the problem by extracting key frames from the videos.Most paper use feature Clustering methods to extract key frames in videos. On one hand, the large variety of visual content in videos make hand-craft feature isn't effective enough, since there are no fixed descriptors can describe all video cases. On the other hand, traditional clustering algorithms are easily influenced by the choice of initial clustering centers. An Unsupervised feature learning and clustering method for key frame extraction is proposed in this paper,which can be used for human action recognition. Stacked auto-encoder(SAE) is trained using videos from 10 different human actions, SAE is used as a feature extractor to learn features representing human actions. Affinity Propagation Clustering algorithm is used to select key frames from video sequences. We use a variety of videos to do the experiments. Experiments demonstrate that our method can be effectively summarizing video shots considering different human actions.
引用
收藏
页码:759 / 762
页数:4
相关论文
共 50 条
  • [1] Unsupervised Feature Based Key-frame Extraction Towards Face Recognition
    Selvaganesan, Jana
    Natarajan, Kannan
    [J]. INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2016, 13 (6A) : 777 - 783
  • [2] Feature fusion and clustering for key frame extraction
    Sun, Yunyun
    Li, Peng
    Jiang, Zhaohui
    Hu, Sujun
    [J]. MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2021, 18 (06) : 9294 - 9311
  • [3] Adaptive key frame extraction using unsupervised clustering
    Zhuang, YT
    Rui, Y
    Huang, TS
    Mehrotra, S
    [J]. 1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 1, 1998, : 866 - 870
  • [4] Key frame and skeleton extraction for deep learning-based human action recognition
    Hai-Hong Phan
    Trung Tin Nguyen
    Ngo Huu Phuc
    Nguyen Huu Nhan
    Do Minh Hieu
    Cao Truong Tran
    Bao Ngoc Vi
    [J]. 2021 RIVF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION TECHNOLOGIES (RIVF 2021), 2021, : 180 - 185
  • [5] Video key frame extraction by unsupervised clustering and feedback adjustment
    Zhuang Y.
    Rui Y.
    Huang T.S.
    [J]. Journal of Computer Science and Technology, 1999, 14 (3) : 283 - 287
  • [6] Video Key Frame Extraction by Unsupervised Clustering and Feedback Adjustment
    庄越挺
    芮勇
    [J]. Journal of Computer Science & Technology, 1999, (03) : 283 - 287
  • [7] Human action classification using adaptive key frame interval for feature extraction
    Lertniphonphan, Kanokphan
    Aramvith, Supavadee
    Chalidabhongse, Thanarat H.
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (01)
  • [8] Feature Extraction for Human Action Classification using Adaptive Key Frame Interval
    Lertniphonphan, Kanokphan
    Aramvith, Supavadee
    Chalidabhongse, Thanarat H.
    [J]. 2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
  • [9] Key Frame Extraction Using Unsupervised Clustering Based on a Statistical Model
    阳书平
    林行刚
    [J]. Tsinghua Science and Technology, 2005, (02) : 169 - 173
  • [10] Behavior key frame extraction using invariant moment and unsupervised clustering
    Peng, Yang
    Pei, Jihong
    Xuan, Yang
    [J]. PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2008, : 2503 - +