Title: | Integrating depth-HOG and spatio-temporal joints data for action recognition |
Authors: | Arora, Noopur Shukla, Parul Biswas, Kanad K. |
Citation: | WSCG '2016: short communications proceedings: The 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2016 in co-operation with EUROGRAPHICS: University of West Bohemia, Plzen, Czech RepublicMay 30 - June 3 2016, p. 245-252. |
Issue Date: | 2016 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | wscg.zcu.cz/WSCG2016/!!_CSRN-2602.pdf http://hdl.handle.net/11025/29710 |
ISBN: | 978-80-86943-58-9 |
ISSN: | 2464-4617 |
Keywords: | rozpoznávání akce;hluboké HOG;kynetika;data o těle a spojích |
Keywords in different language: | action recognition;depth-HOG;kinectics;body-joints data |
Abstract: | In this paper, we propose an approach for human activity recognition using gradient orientation of depth maps and spatio-temporal features from body-joints data. Our approach is based on an amalgamation of key local and global feature descriptors such as spatial pose, temporal variation in ‘joints’ position and spatio-temporal gradient orientation of depth maps. Additionally, we obtain a motion-induced global shape feature describing the motion dynamics during an action. Feature selection is carried out to select a relevant subset of features for action recognition. The resultant features are evaluated using SVM classifier. We validate our proposed method on our own dataset consisting of 11 classes and a total of 287 videos. We also compare the effectiveness of our method on the MSR-Action3D dataset. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG '2016: Short Papers Proceedings |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/29710
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.