Human Action Recognition Method Based on Multi-feature Multi-classifier Fusion
Journal Title: 河南科技大学学报（自然科学版） - Year 2018, Vol 39, Issue 6
Abstract
A human behavior recognition method based on multi-feature and multi-classifier fusion was proposed. For the three-dimensional skeleton motion sequence extracted by the Kinect sensor, the human body motion was described by using the relative geometric features of the body part, the relative position characteristics of the joint points and the absolute position characteristics of the joint points. The support vector machine and the random forest classifier were used as member classifiers to train and test the three kinds of action features respectively. The classifier fusion algorithm was used to make fusion decision for the classification results and achieve the final classification. The verification was performed on the existing human motion dataset. The experimental results show that the method can achieve 95% recognition rate.
Authors and Affiliations
Qingfeng CHEN, Shimin FENG, Enjie DING
Keywords
Related Articles
- EP ID EP468434
- DOI -
- Views 100
- Downloads 0
Improvement and Analysis of Oncolytic Virotherapy Kinetic Model
An improved kinetic model of tumor therapy with oncolytic virus was investigated. The boundedness and positivity of solutions were obtained by analyzing the model. The instability of zero equilibrium,the global stability...
Effects of Sasobit on High Viscosity Asphalt and Asphalt Mixture Performance
To study the effects of Sasobit on high viscosity asphalt and its mixture performance,the effects of Sasobit on high viscosity asphalt performance under different dosage were researched. The optimum dosage of Sasobit was...
Motor Control of Pure Electric Vehicle Based on BP Fuzzy Neural Network Control
A proportional integral( PI) controller was designed based on back propagation( BP) fuzzy neural network to solve the problem that traditional PI control could not reach good control effect of the motor. Driver operation...
Stress Model Test of Anti-Sliding Micropile Groups
The model test was carried out to analyze the stress performance of anti-sliding micropile groups and the function of connecting beam. The results shows that the maximum shearing force of the piles occurs around the slip...
Development of Fault Diagnosis System for Automatic Lubrication of Power Flat Transport
In view of the shortcomings of the existing automatic lubrication system,such as high failure rate and backward diagnosis technology,a fault diagnosis method of lubrication system based on fault tree analysis combined wi...