Visual tracking based on stacked Denoising Autoencoder network with genetic algorithm optimization

Visual object tracking in dynamic environments with severe appearance variations is a significant problem in the computer vision field. This paper proposes a novel visual tracking algorithm that exploits the multiple level features learning ability of SDAE. There are two training stages for the SDAE...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications Vol. 77; no. 4; pp. 4253 - 4269
Main Authors: Hua, Weixin, Mu, Dejun, Guo, Dawei, Liu, Hang
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2018
Springer Nature B.V
Subjects:
Back propagation
Computer Communication Networks
Computer Science
Computer vision
Data Structures and Information Theory
Genetic algorithms
Machine learning
Multimedia Information Systems
Neural networks
Noise reduction
Optical tracking
Special Purpose and Application-Based Systems
Training
Tuning
Sparsity dictionary encode
Object tracking
Stacked denoising autoencoder
Genetic algorithm
ISSN:1380-7501, 1573-7721
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Visual object tracking in dynamic environments with severe appearance variations is a significant problem in the computer vision field. This paper proposes a novel visual tracking algorithm that exploits the multiple level features learning ability of SDAE. There are two training stages for the SDAE network: Layer-wise pre-training and fine-tuning. In the pre-training stage, a two-layer sparse-coded method is used to represent the input image, then a multi-level image feature descriptor is obtained. In the fine-tuning stage, the connection weights and bias terms for back propagation are gathered via genetic algorithm. A logistic classification layer is added at the top of the encoder network to enable tracking within the well-established particle filter network. Experimental results confirm, both qualitatively and quantitatively, that the proposed method performs well in comparison against eight other state-of-the-art methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-017-4702-1