Multimodal Deep Autoencoder for Human Pose Recovery

Video-based human pose recovery is usually conducted by retrieving relevant poses using image features. In the retrieving process, the mapping between 2D images and 3D poses is assumed to be linear in most of the traditional methods. However, their relationships are inherently non-linear, which limi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 24; no. 12; pp. 5659 - 5670
Main Authors: Hong, Chaoqun, Yu, Jun, Wan, Jian, Tao, Dacheng, Wang, Meng
Format: Journal Article
Language:English
Published: United States IEEE 01.12.2015
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Artificial Intelligence
Back propagation
deep learning
Electronic mail
Feature extraction
Female
Graphs
Hidden Markov models
Human
Human pose recovery
Humans
hypergraph
Image Processing, Computer-Assisted - methods
Machine learning
Male
Mapping
multi-modal learning
Neural networks
Nonlinearity
Posture - physiology
Recovery
Three dimensional
Three-dimensional displays
Two dimensional
Visualization
deep learning
hypergraph
Human pose recovery
multi-modal learning
back propagation
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video-based human pose recovery is usually conducted by retrieving relevant poses using image features. In the retrieving process, the mapping between 2D images and 3D poses is assumed to be linear in most of the traditional methods. However, their relationships are inherently non-linear, which limits recovery performance of these methods. In this paper, we propose a novel pose recovery method using non-linear mapping with multi-layered deep neural network. It is based on feature extraction with multimodal fusion and back-propagation deep learning. In multimodal fusion, we construct hypergraph Laplacian with low-rank representation. In this way, we obtain a unified feature description by standard eigen-decomposition of the hypergraph Laplacian matrix. In back-propagation deep learning, we learn a non-linear mapping from 2D images to 3D poses with parameter fine-tuning. The experimental results on three data sets show that the recovery error has been reduced by 20%-25%, which demonstrates the effectiveness of the proposed method.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2015.2487860