Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network
Aiming at the problem that it is difficult to balance the speed and accuracy of human behaviour recognition, this paper proposes a method of motion recognition based on random projection. Firstly, the optical flow picture and Red, Green, Blue (RGB) picture obtained by the Lucas-Kanade algorithm are...
Main Author: | Yang Ju |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2021-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2021/7646813 |
Similar Items
-
A Novel Multichannel Dilated Convolution Neural Network for Human Activity Recognition
by: Yingjie Lin, et al.
Published: (2020-01-01) -
3D Human Motion Synthesis Based on Convolutional Neural Network
by: Dongsheng Zhou, et al.
Published: (2019-01-01) -
Dynamic Gesture Recognition Algorithm Based on 3D Convolutional Neural Network
by: Yuting Liu, et al.
Published: (2021-01-01) -
Human action recognition with 3D convolutional neural networks
by: Cronje, Frans
Published: (2015) -
Multichannel Convolutional Neural Network for Biological Relation Extraction
by: Chanqin Quan, et al.
Published: (2016-01-01)