Video based human action recognition has attained more attraction from the researchers and it predominates in the field of computer vision and pattern recognition. In this paper we deliver a new approach to suppress the background data and to extract 2D data of foreground human object of the video sequence. A combination of convex hull area, convex hull perimeter, solidity and eccentricity is used to represent the feature vector. Experiments are conducted on Weizmann video dataset to assess how the system is doing. The discriminative nature of the feature vectors assures accuracy in action recognition.
CITATION STYLE
2D Information Space Based Action Recognition. (2019). International Journal of Innovative Technology and Exploring Engineering, 9(1S), 295–298. https://doi.org/10.35940/ijitee.a1060.1191s19
Mendeley helps you to discover research relevant for your work.