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

Effect of Fresh Air Fraction on Heating Performance of Modified Ground-water Heat Pump

In order to solve the problem that the energy consumption of air conditioning ( AC) system was increased with the increase of fresh air ratio, a groundwater source heat pump air-conditioning system with a fresh air prehe...

Oxidation Removal Experiment of As2O3 in Flue Gas

Taking Fenton reagent as the absorbents, the removal of As2O3 in flue gas by Fenton oxidation reaction was studied in the self-designed bubbling reactor. The effects of reaction temperature and simulative flue gas compos...

Impedance Matching Technology Based on Radio Frequency Power Amplifier

The input and output impedance of the transistor used in radio frequency (RF) power amplifier was smaller than the standard impedance of the RF system.If they were directly connected, the power was not effectively transm...

Analysis and Simulation of Steering Performance of Six-Wheeled Articulated Vehicle

A rear wheel steering six-wheeled swing-arm articulated vehicle was designed to improve the low space utilization of articulated vehicles during articulated steering. Meanwhile,a mechanical model for the steering of arti...

Download PDF file
  • EP ID EP468434
  • DOI -
  • Views 103
  • Downloads 0

How To Cite

Qingfeng CHEN, Shimin FENG, Enjie DING (2018). Human Action Recognition Method Based on Multi-feature Multi-classifier Fusion. 河南科技大学学报(自然科学版), 39(6), -. https://europub.co.uk/articles/-A-468434