Human Action Recognition Based on Global Silhouette and Local Optical Flow

DOI

10.2991/ismems-17.2018.1How to use a DOI?

Keywords

Action recognition; Computer vision; Global silhouette; Local optical

Abstract

Currently, Human Activity Recognition is a research hotspot in the field of machine vision, it involves knowledge of image processing, pattern recognition, artificial intelligence and many other disciplines. Video-based Human Activity Recognition including human area detection, movement and gesture segmentation, objective analysis and behavior understands for activity recognition and so on. In the past, the behavior recognition technology based on the single characteristic was too restrictive, in this paper, we proposed a mixed feature which combined global silhouette feature and local optical flow feature, and this combined representation was used for human action recognition. In the end, test the model with other samples from the database.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ning Zhang
AU  - Zeyuan Hu
AU  - Sukhwan Lee
AU  - Eungjoo Lee
PY  - 2017/11
DA  - 2017/11
TI  - Human Action Recognition Based on Global Silhouette and Local Optical Flow
BT  - Proceedings of the International Symposium on Mechanical Engineering and Material Science (ISMEMS 2017)
PB  - Atlantis Press
SP  - 1
EP  - 5
SN  - 2352-5401
UR  - https://doi.org/10.2991/ismems-17.2018.1
DO  - 10.2991/ismems-17.2018.1
ID  - Zhang2017/11
ER  -