Volume 4, Issue 1, June 2017, Pages 5 - 9
Action recognition based on binocular vision
Yiwei Ru, Hongyue Du, Shuxiao Li, Hongxing Chang
Available Online 1 June 2017.
- 10.2991/jrnal.2017.4.1.2How to use a DOI?
- action recognition; binocular version; convolutional neural networks; motion history image;
Aimed at the problem that the recognition accuracy of the monocular camera is low, we propose a binocular vision recognition algorithm for action recognition based on HART-Net(Human action recognition networks).Firstly, the left and right views obtained by the binocular camera are matched to obtain the depth map of the human body. Then, the depth information is projected onto the three planes, the projection images of three directions are used to construct MHI (motion history image), and are combined into a new image. Finally, we use HART-Net to train a classifier for action recognition. Experimental results show that the binocular recognition algorithm is 18% more accurate than the monocular recognition algorithm.
- © 2013, 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/).
Cite this article
TY - JOUR AU - Yiwei Ru AU - Hongyue Du AU - Shuxiao Li AU - Hongxing Chang PY - 2017 DA - 2017/06/01 TI - Action recognition based on binocular vision JO - Journal of Robotics, Networking and Artificial Life SP - 5 EP - 9 VL - 4 IS - 1 SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.2017.4.1.2 DO - 10.2991/jrnal.2017.4.1.2 ID - Ru2017 ER -