Human Action Recognition using Average VLBP

Main Author: Dr. Chidananda H
Format: Article
Terbitan: , 2021
Subjects:
ABP
Online Access: https://zenodo.org/record/4505639
Daftar Isi:
  • 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.
  • IJSRED - International Journal of Scientific Research and Engineering Development