ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login


Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.7, No. 5)

Publication Date:

Authors : ; ;

Page : 412-417

Keywords : computer visions; human action recognition; view-invariant feature descriptor; classification; support vector machines;

Source : Downloadexternal Find it from : Google Scholarexternal


We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of lines which are fitted to boundaries of human figures. By using an entropy-based approach, we apply feature selection to identify our feature representation, thus, minimizing classification time without degrading accuracy. We also use a compact representation of optical flow for motion information. Using line and flow histograms together with global velocity information, we show that high-accuracy action recognition is possible, even in challenging recording conditions. This paper presents a novel feature descriptor for multi view human action recognition. This descriptor employs the region-based features extracted from the human silhouette. To achieve this, the human silhouette is divided into regions in a radial fashion with the interval of a certain degree, and then region-based geometrical and Humoments features are obtained from each radial bin to articulate the feature descriptor. A multiclass support vector machine classifier is used for action classification.

Last modified: 2018-05-18 21:34:48