"Human Motion Prediction Using Wavelet Transform" by Wafaa Shihab Ahmed and Abdulamir A. Karim

Article Title

Human Motion Prediction Using Wavelet Transform

Authors

Wafaa Shihab Ahmed, University of Technology, Baghdad, IraqFollow
Abdulamir A. Karim, University of Technology, Baghdad, IraqFollow

Document Type

Article

Abstract

The goal of prediction human motion is to analyze a subject's behaviors based on observed sequences and produced future body motions. In this work the deep neural network has been employed and proposed using wavelet transform with CNN-VAE model to analyze the input data to multi scales and extract features to encode it by CNN-VAE model, LSTM model has been used to predict encoded data and decoded it by used CNN-decoder to produce the new predicted frames. The propose system achieved best results in PSNR, MSE and SSIM and made the time of training and testing (prediction) faster. The experiments have been applied on two dataset: KTH and Weizmann and generate video of 1200 ms.

Keywords

Wavelet Transform, Convolution Neural Network, Variational Auto Encoder (VAE), Long Short Term Memory (LSTM).

Recommended Citation

Ahmed, Wafaa Shihab and Karim, Abdulamir A. (2021) "Human Motion Prediction Using Wavelet Transform," Al-Qadisiyah Journal of Pure Science: Vol. 26 : No. 4 , Article 43.
Available at: https://doi.org/10.29350/qjps.2021.26.4.1354