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: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2021-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2021/7646813 |
id |
doaj-773534ab51dd4b20b59dc01fe90391a2 |
---|---|
record_format |
Article |
spelling |
doaj-773534ab51dd4b20b59dc01fe90391a22021-06-07T02:14:17ZengHindawi-WileyComplexity1099-05262021-01-01202110.1155/2021/7646813Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural NetworkYang Ju0Department of Physical EducationAiming 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 used. Secondly, the data of optical flow pictures and RGB pictures are compressed based on a random projection matrix of compressed sensing, which effectively reduces power consumption. At the same time, based on random projection compression data, it can effectively find the optimal linear representation to reconstruct training samples and test samples. Thirdly, a multichannel 3D convolutional neural network is proposed, and the multiple information extracted by the network is fused to form an output recognizer. Experimental results show that the algorithm in this paper significantly improves the recognition rate of multicategory actions and effectively reduces the computational complexity and running time of the recognition algorithm.http://dx.doi.org/10.1155/2021/7646813 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yang Ju |
spellingShingle |
Yang Ju Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network Complexity |
author_facet |
Yang Ju |
author_sort |
Yang Ju |
title |
Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network |
title_short |
Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network |
title_full |
Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network |
title_fullStr |
Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network |
title_full_unstemmed |
Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network |
title_sort |
study of human motion recognition algorithm based on multichannel 3d convolutional neural network |
publisher |
Hindawi-Wiley |
series |
Complexity |
issn |
1099-0526 |
publishDate |
2021-01-01 |
description |
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 used. Secondly, the data of optical flow pictures and RGB pictures are compressed based on a random projection matrix of compressed sensing, which effectively reduces power consumption. At the same time, based on random projection compression data, it can effectively find the optimal linear representation to reconstruct training samples and test samples. Thirdly, a multichannel 3D convolutional neural network is proposed, and the multiple information extracted by the network is fused to form an output recognizer. Experimental results show that the algorithm in this paper significantly improves the recognition rate of multicategory actions and effectively reduces the computational complexity and running time of the recognition algorithm. |
url |
http://dx.doi.org/10.1155/2021/7646813 |
work_keys_str_mv |
AT yangju studyofhumanmotionrecognitionalgorithmbasedonmultichannel3dconvolutionalneuralnetwork |
_version_ |
1721393111378165760 |