Multi-Feature Fusion Human Behavior Recognition Algorithm Based on Convolutional Neural Network and Long Short Term Memory Neural Network

Table 1. Comparison of accuracy of different algorithms on KTH dataset
View table
Table 1. Comparison of accuracy of different algorithms on KTH dataset
Algorithm Accuracy /%
Method in Ref. [4] 93.7
Method in Ref. [3] 90.2
Method in Ref. [13] 90.2
Method in Ref. [14] 93.7
Model without concat 93.3
Proposed method 94.2

Table 2. Comparison of accuracy of different algorithms on UCF Sports dataset
View table
Table 2. Comparison of accuracy of different algorithms on UCF Sports dataset
Algorithm Accuracy /%
Method in Ref. [18] 88.0
Method in Ref. [19] 88.4
Proposed method 88.89

Table 3. Behavior recognition confusion matrix based on KTH dataset

View table

Table 3. Behavior recognition confusion matrix based on KTH dataset

Actual classification	Model prediction
Actual classification	Walking	Jogging	Running	Boxing	Hand waving	Hand clapping
Walking	0.95	0.05	0.00	0.00	0.00	0.00
Jogging	0.10	0.85	0.05	0.00	0.00	0.00
Running	0.00	0.10	0.90	0.00	0.00	0.00
Boxing	0.00	0.00	0.00	1.00	0.00	0.00
Hand waving	0.00	0.00	0.00	0.00	1.00	0.00
Hand clapping	0.00	0.00	0.00	0.00	0.05	0.95

Tools

Get Citation

Copy Citation Text

Youwen Huang, Chaolun Wan, Heng Feng. Multi-Feature Fusion Human Behavior Recognition Algorithm Based on Convolutional Neural Network and Long Short Term Memory Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(7): 071505

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites