Human activity recognition using skeleton data and support vector machine

15Citations
Citations of this article
28Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

In this paper, we propose a method for recognizing human activities using skeleton data by RGB-D camera, namely Kinect device. The human activity recognition is a learning in the field of computer vision. In its application, the recognition of human activity can be used for a sign language learning, human-computer interaction, surveillance of the elderly, image processing and etc. Our approach is based on skeleton data with coordinate value of each joints in human body, that will be classified using support vector machine algorithm when performing a movement to predict the activities name. Experiments were performed with a new training data that we've create manual from capturing movement while human target are doing activities. Experiments result show that the system best average accuracy is 93.75% of all activities prediction with the optimal distance of object to the devices is 2 meters.

Cite

CITATION STYLE

APA

Komang, M. G. A., Surya, M. N., & Ratna, A. N. (2019). Human activity recognition using skeleton data and support vector machine. In Journal of Physics: Conference Series (Vol. 1192). Institute of Physics Publishing. https://doi.org/10.1088/1742-6596/1192/1/012044

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free