MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion (This dataset can be downloaded from http://cs.ny...

Full description

Saved in:
Bibliographic Details
Published inComputer Vision -- ACCV 2014 Vol. 9004; pp. 302 - 315
Main Authors Jain, Arjun, Tompson, Jonathan, LeCun, Yann, Bregler, Christoph
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2015
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Artificial intelligence
Convolutional Layer
Convolutional Network
Image processing
Laplacian Pyramid
Motion Feature
Optical Flow
Pattern recognition
Online AccessGet full text

Cover

More Information
Summary:In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion (This dataset can be downloaded from http://cs.nyu.edu/~ajain/accv2014/.), that extends the FLIC dataset [1] with additional motion features. We apply our architecture to this dataset and report significantly better performance than current state-of-the-art pose detection systems.
ISBN:9783319168074
331916807X
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-16808-1_21