Human Action Recognition Using Kinect

Abstract: In this paper, a general approach for human action recognition is applied for classifying human movements into action classes.
The propose method uses Kinect for capturing depth stream. The system performs preprocessing on depth information for processing cing noisy
Pixels and getting depth information in appropriate format. The background subtraction method is used for extracting region o f interest I. e.
Human. The system extracts seconds s of person. The Hu moments are extracted from users s of person for training action classifier.
Support Vector Machine (SVM) is used for classifying human activities.

 

Keywords: contours, Hu moments, Support Vector Machine

 

I personally feel pretty watery ~~

Feature: Hu margin of the extracted Contour in the Deep Image

Classifier: SVM

An action contains many frames of deep images, so its training and test data are already split.

A training sample is a matrix of features in each frame of an action. Let's guess ~~

Human Action Recognition Using Kinect