Human Action Recognition Using Salient Opponent-Based Motion Features

Human action recognition can be performed using multiscale salient features which encode the local events in the video. Existing feature extraction methods use non-causal spatio-temporal filtering, and hence, they are not biologically plausible. To address this inconsistency, new features extracted...

Full description

Saved in:
Bibliographic Details
Main Authors: Shabani, Amir-Hossein, Zelek, John S, Clausi, David A
Format: Conference Proceeding
Language:English
Subjects:
Biological information theory
Biological system modeling
causal scale-space filtering
Computer vision
Data mining
Encoding
Feature extraction
Filtering
Filters
Human action recognition
Humans
Image recognition
opponent-based motion features
spatio-temporal salinet features
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human action recognition can be performed using multiscale salient features which encode the local events in the video. Existing feature extraction methods use non-causal spatio-temporal filtering, and hence, they are not biologically plausible. To address this inconsistency, new features extracted from a biologically plausible perception model are introduced. In this model, the opponent-based motion energy is computed using oriented motion filters constructed from a bio-inspired time-causal filtering. The salient features are then extracted from the regions of interest in the motion energy map. The extracted opponent based motion features are then utilized for action classification with a bag-of-words approach. Experiments using a publicly available (Weizmann) data set shows 93:5% classification accuracy which is an improvement over comparable methods.
DOI:10.1109/CRV.2010.54