Prediction of human body motion from video sequences

Zhuoheng Huang, Yue Yu, Xiangru Chen, Wei Wei

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Learning to predict human body motion has emerged as a meaningful research in computer vision and artificial intelligence. This paper presents the study on predicting human body motion from video sequences. We propose a human body motion prediction network integrating the recent advanced 2D feature extraction and video sequences prediction. Based on the temporal characteristics extracted from video sequences, our network realizes the prediction of the human motion. We train the network using the video based human pose datasets and demonstrate good performance of our network on 2D human body motion prediction through quantitative and qualitative results. Experimental results prove the feasibility of our method.

Original languageEnglish
Title of host publication2018 18th IEEE International Conference on Communication Technology, ICCT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1227-1231
Number of pages5
ISBN (Electronic)9781538676349
DOIs
Publication statusPublished - 2 Jan 2019
Event2018 18th IEEE International Conference on Communication Technology, ICCT 2018 - Chongqing, China
Duration: 8 Oct 201811 Oct 2018

Publication series

NameInternational Conference on Communication Technology Proceedings, ICCT
Volume2019-October

Conference

Conference2018 18th IEEE International Conference on Communication Technology, ICCT 2018
Country/TerritoryChina
CityChongqing
Period8/10/1811/10/18

Keywords

  • Convolutional neural network
  • Human body motion prediction
  • Recurrent neural networks
  • Video analysis

Fingerprint

Dive into the research topics of 'Prediction of human body motion from video sequences'. Together they form a unique fingerprint.

Cite this