The recognition of human actions recorded in a multi-camera environment faces the challenging issue of viewpoint variation. Multi-view methods employ videos from different views to generate a compact view-invariant representation of human actions. This paper proposes a novel multi-view human action recognition approach that uses multiple low-dimensional temporal templates and a reconstruction-based encoding scheme. The proposed approach is based upon the extraction of multiple 2D motion history images (MHIs) of human action videos over non-overlapping temporal windows, constructing multiple batches of motion history images (MB-MHIs). Then, two kinds of descriptions are computed for these MHIs batches based on (1) a deep residual network (ResNet) and (2) histogram of oriented gradients (HOG) to effectively quantify a change in gradient. ResNet descriptions are average pooled at each batch. HOG descriptions are processed independently at each batch to learn a class-based dictionary using a K-spectral value decomposition algorithm. Later, the sparse codes of feature descriptions are obtained using an orthogonal matching pursuit approach. These sparse codes are average pooled to extract encoded feature vectors. Then, encoded feature vectors at each batch are fused to form a final view-invariant feature representation. Finally, a linear support vector machine classifier is trained for action recognition. Experimental results are given on three versions of a multi-view dataset: MuHAVi-8, MuHAVi-14, and MuHAVi-uncut. The proposed approach shows promising results when tested for a novel camera. Results on deep features indicate that action representation by MB-MHIs is more view-invariant than single MHIs. ; Muhammad Haroon Yousaf has received funding from Higher Education Commission, Pakistan, for Swarm Robotics Lab under National Centre for Robotics and Automation (NCRA). S.A. Velastin is grateful to funding received from the Universidad Carlos III de Madrid, the European Union’s Seventh Framework Programme for research, technological development, and demonstration under Grant Agreement No. 600371, el Ministerio de Economía y Competitividad (COFUND2013-51509), and Banco Santander. The authors also acknowledge support from the Directorate of ASR&TD, University of Engineering and Technology, Taxila, Pakistan, and of Nvidia Corporation for its donation of GPU equipment.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multiple Batches of Motion History Images (MB-MHIs) for Multi-view Human Action Recognition



    Erscheinungsdatum :

    2020-03-31


    Anmerkungen:

    AR/0000025470



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Multi-view Human Action Recognition using Histograms of Oriented Gradients (HOG) Description of Motion History Images (MHIs)

    Murtaza, Fiza / Yousaf, Muhammad Haroon / Velastin Carroza, Sergio Alejandro | BASE | 2015

    Freier Zugriff

    View Invariants for Human Action Recognition

    Parameswaran, V. / Chellappa, R. / IEEE | British Library Conference Proceedings | 2003


    View Invariance for Human Action Recognition

    Parameswaran, V. / Chellappa, R. | British Library Online Contents | 2006


    View invariants for human action recognition

    Parameswaran, V. / Chellappa, R. | IEEE | 2003


    Free viewpoint action recognition using motion history volumes

    Weinland, D. / Ronfard, R. / Boyer, E. | British Library Online Contents | 2006