• Journal of Internet Computing and Services
    ISSN 2287 - 1136 (Online) / ISSN 1598 - 0170 (Print)
    https://jics.or.kr/

CNN-based Gesture Recognition using Motion History Image


Youjin Koh, Taewon Kim, Min Hong, Yoo-Joo Choi, Journal of Internet Computing and Services, Vol. 21, No. 5, pp. 67-73, Oct. 2020
10.7472/jksii.2020.21.5.67, Full Text:
Keywords: Gesture Recognition, Neural Network, Convolutional Neural Network, motion history image

Abstract

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left,shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 x 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Koh, Y., Kim, T., Hong, M., & Choi, Y. (2020). CNN-based Gesture Recognition using Motion History Image. Journal of Internet Computing and Services, 21(5), 67-73. DOI: 10.7472/jksii.2020.21.5.67.

[IEEE Style]
Y. Koh, T. Kim, M. Hong, Y. Choi, "CNN-based Gesture Recognition using Motion History Image," Journal of Internet Computing and Services, vol. 21, no. 5, pp. 67-73, 2020. DOI: 10.7472/jksii.2020.21.5.67.

[ACM Style]
Youjin Koh, Taewon Kim, Min Hong, and Yoo-Joo Choi. 2020. CNN-based Gesture Recognition using Motion History Image. Journal of Internet Computing and Services, 21, 5, (2020), 67-73. DOI: 10.7472/jksii.2020.21.5.67.