Action Recognition Using Visual-Neuron Feature of Motion-Salience Region

Authors

  • Ning Li
  • De Xu
  • Lu Liu

Keywords:

Action recognition, shape-based neurobiological approach (SBNA), motion-salience region, visual-neuron template, visual-neuron feature, visual cortex

Abstract

This paper proposes a shape-based neurobiological approach for action recognition. Our work is motivated by the successful quantitative model for the organization of the shape pathways in primate visual cortex. In our approach the motion-salience region (MSR) is firstly extracted from the sequential silhouettes of an action. Then, the MSR is represented by simulating the static object representation in the ventral stream of primate visual cortex. Finally, a linear multi-class classifier is used to classify the action. Experiments on publicly available action datasets demonstrate the proposed approach is robust to partial occlusion and deformation of actors and has lower computational cost than the neurobiological models that simulate the motion representation in primate dorsal stream.

Downloads

Download data is not yet available.

Author Biographies

Ning Li

Institute of Computer Science and Engineering
Beijing Jiaotong University
Xizhi Men Wai, Shangyuan Cun 3, 100044 Beijing, P.R. China

De Xu

Institute of Computer Science and Engineering
Beijing Jiaotong University
Xizhi Men Wai, Shangyuan Cun 3, 100044 Beijing, P.R. China

Lu Liu

School of Electronic Engineering
Beijing University of Posts and Telecommunications
Xitu Cheng street 10, 100088 Beijing, P.R. China

Downloads

Published

2012-01-26

How to Cite

Li, N., Xu, D., & Liu, L. (2012). Action Recognition Using Visual-Neuron Feature of Motion-Salience Region. COMPUTING AND INFORMATICS, 29(2), 281–301. Retrieved from https://www.cai.sk/ojs/index.php/cai/article/view/87