Complex Background Gesture Recognition Based on Convolutional Pose Machines

DOI

10.2991/cnci-19.2019.41How to use a DOI?

Keywords

CPM, CNN, gesture recognition, Joint.

Abstract

Gesture recognition is a research hotspot in HCI (Human-Computer Interaction). The camera-based gesture recognition method has become the focus of research in this field due to its low cost. Due to the lack of three-dimensional coordinate information and depth information, image-based gesture recognition has been a difficult point. Therefore, this paper applies the Convolutional Pose Machine method which is more mature in human body pose estimate in the field of gesture recognition. In this paper we collect gesture data and create a gesture database for training and testing. From the results of the test, this paper has certain practical significance.

Copyright

© 2019, 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  - Ganzhou Liao
AU  - Xia Zeng
PY  - 2019/05
DA  - 2019/05
TI  - Complex Background Gesture Recognition Based on Convolutional Pose Machines
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 277
EP  - 281
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.41
DO  - 10.2991/cnci-19.2019.41
ID  - Liao2019/05
ER  -