Submit Your Manuscript Online

Human Action Recognition using Average VLBP

	International Journal of Scientific Research and Engineering Development (IJSRED)	Full Text:
	Published Issue : Volume-4 Issue-1
	Year of Publication : 2021
	Unique Identification Number : IJSRED-V4I1P57
	Authors : Dr. Chidananda H
	: Click Here | DOI : https://doi.org/10.5281/zenodo.4505639

Abstract :

This work, we proposed a new method to perceive human actions from visual information. An efficient alternative descriptor is constituted by customizing Volume Local Binary Patterns (VLBP)as Average VLBP. An Average VLBP of static human actions along with its visual information in spatio-temporal domain is determined. A Random Forest classifier is trained to learn histograms of human actions. This work has been tested on the popular and freely accessible KTH and Weizmandataset for human action understanding from input visuals. The outcomes show best instate-of-the-art efficiency in contrast with different strategies.