Publication: 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes
Loading...
Identifiers
Publication date
2018-09-13
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Export
Abstract
Given the high demand for automated systems for human action recognition, great efforts have been undertaken in recent decades to progress the field. In this paper, we present frameworks for single and multi-viewpoints action recognition based on Space-Time Volume (STV) of human silhouettes and 3D-Histogram of Oriented Gradient (3D-HOG) embedding. We exploit fast-computational approaches involving Principal Component Analysis (PCA) over the local feature spaces for compactly describing actions as combinations of local gestures and L 2 -Regularized Logistic Regression (L 2 -RLR) for learning the action model from local features. Outperforming results on Weizmann and i3DPost datasets confirm efficacy of the proposed approaches as compared to the baseline method and other works, in terms of accuracy and robustness to appearance changes.
Description
This paper has been presented at : 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Keywords
Single-viewpoint, Multi-viewpoints, Human action recognition, 3d histogram of oriented gradient, Silhouettes
Bibliographic citation
Angelini, F., Fu, Z., Velastin, S.A, Chambers, J.A. y Naqvi, S.M. (2018). 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).