Cargando…

Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU

The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to re...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Jinwei, Ma, Xirong, Zhu, Yuanping, Sun, Jizhou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2014
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3958704/
https://www.ncbi.nlm.nih.gov/pubmed/24723812
http://dx.doi.org/10.1155/2014/528080
_version_ 1782307923917012992
author Wang, Jinwei
Ma, Xirong
Zhu, Yuanping
Sun, Jizhou
author_facet Wang, Jinwei
Ma, Xirong
Zhu, Yuanping
Sun, Jizhou
author_sort Wang, Jinwei
collection PubMed
description The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs) that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA) on the Nvidia's GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.
format Online
Article
Text
id pubmed-3958704
institution National Center for Biotechnology Information
language English
publishDate 2014
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-39587042014-04-10 Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU Wang, Jinwei Ma, Xirong Zhu, Yuanping Sun, Jizhou ScientificWorldJournal Research Article The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs) that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA) on the Nvidia's GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures. Hindawi Publishing Corporation 2014-03-02 /pmc/articles/PMC3958704/ /pubmed/24723812 http://dx.doi.org/10.1155/2014/528080 Text en Copyright © 2014 Jinwei Wang et al. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Wang, Jinwei
Ma, Xirong
Zhu, Yuanping
Sun, Jizhou
Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title_full Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title_fullStr Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title_full_unstemmed Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title_short Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
title_sort efficient parallel implementation of active appearance model fitting algorithm on gpu
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3958704/
https://www.ncbi.nlm.nih.gov/pubmed/24723812
http://dx.doi.org/10.1155/2014/528080
work_keys_str_mv AT wangjinwei efficientparallelimplementationofactiveappearancemodelfittingalgorithmongpu
AT maxirong efficientparallelimplementationofactiveappearancemodelfittingalgorithmongpu
AT zhuyuanping efficientparallelimplementationofactiveappearancemodelfittingalgorithmongpu
AT sunjizhou efficientparallelimplementationofactiveappearancemodelfittingalgorithmongpu