Accelerating active shape model using GPU for facial extraction in video

Jian Li; Yuqiang Lu; Bo Pu; Yongming Xie; Jing Qin; Wai Man Pang; Pheng Ann Heng

doi:10.1109/ICICISYS.2009.5357636

Accelerating active shape model using GPU for facial extraction in video

Jian Li
, Yuqiang Lu
, Bo Pu
, Yongming Xie
, Jing Qin
, Wai Man Pang
, Pheng Ann Heng

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

In this paper, we present a novel parallel implementation of Active Shape Model (ASM) on GPU for massive facial feature extractions in video or image sequence. With the Compute Unified Device Architecture (CUDA)-enabled GPU, the acceleration is significant and reported a 48 times performance boost comparing to a CPU implementation. We adopt the hardware built-in bilinear interpolation of texture to shorten the time for a large number of image scale transform operations. Then, a GPU-based parallel mahalanobis distance calculation is introduced in the searching process, and this enables most of the computations to be performed simultanously. As a result, we can achieve real-time performance in our video-driven 3D facial animation system.

Original language	English
Title of host publication	Proceedings - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009
Pages	522-526
Number of pages	5
Volume	4
DOIs	https://doi.org/10.1109/ICICISYS.2009.5357636
Publication status	Published - 1 Dec 2009
Externally published	Yes
Event	2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009 - Shanghai, China Duration: 20 Nov 2009 → 22 Nov 2009

Conference

Conference	2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009
Country/Territory	China
City	Shanghai
Period	20/11/09 → 22/11/09

ASJC Scopus subject areas

General Computer Science
Control and Systems Engineering

More information

10.1109/ICICISYS.2009.5357636

Cite this

@inproceedings{3ae422b0576c42bc93a97ec153af754f,

title = "Accelerating active shape model using GPU for facial extraction in video",

abstract = "In this paper, we present a novel parallel implementation of Active Shape Model (ASM) on GPU for massive facial feature extractions in video or image sequence. With the Compute Unified Device Architecture (CUDA)-enabled GPU, the acceleration is significant and reported a 48 times performance boost comparing to a CPU implementation. We adopt the hardware built-in bilinear interpolation of texture to shorten the time for a large number of image scale transform operations. Then, a GPU-based parallel mahalanobis distance calculation is introduced in the searching process, and this enables most of the computations to be performed simultanously. As a result, we can achieve real-time performance in our video-driven 3D facial animation system.",

author = "Jian Li and Yuqiang Lu and Bo Pu and Yongming Xie and Jing Qin and Pang, \{Wai Man\} and Heng, \{Pheng Ann\}",

year = "2009",

month = dec,

day = "1",

doi = "10.1109/ICICISYS.2009.5357636",

language = "English",

isbn = "9781424447541",

volume = "4",

pages = "522--526",

booktitle = "Proceedings - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009",

note = "2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009 ; Conference date: 20-11-2009 Through 22-11-2009",

}

Li, J, Lu, Y, Pu, B, Xie, Y, Qin, J, Pang, WM & Heng, PA 2009, Accelerating active shape model using GPU for facial extraction in video. in Proceedings - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009. vol. 4, 5357636, pp. 522-526, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009, Shanghai, China, 20/11/09. https://doi.org/10.1109/ICICISYS.2009.5357636

Accelerating active shape model using GPU for facial extraction in video. / Li, Jian; Lu, Yuqiang; Pu, Bo et al.
Proceedings - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009. Vol. 4 2009. p. 522-526 5357636.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Accelerating active shape model using GPU for facial extraction in video

AU - Li, Jian

AU - Lu, Yuqiang

AU - Pu, Bo

AU - Xie, Yongming

AU - Qin, Jing

AU - Pang, Wai Man

AU - Heng, Pheng Ann

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In this paper, we present a novel parallel implementation of Active Shape Model (ASM) on GPU for massive facial feature extractions in video or image sequence. With the Compute Unified Device Architecture (CUDA)-enabled GPU, the acceleration is significant and reported a 48 times performance boost comparing to a CPU implementation. We adopt the hardware built-in bilinear interpolation of texture to shorten the time for a large number of image scale transform operations. Then, a GPU-based parallel mahalanobis distance calculation is introduced in the searching process, and this enables most of the computations to be performed simultanously. As a result, we can achieve real-time performance in our video-driven 3D facial animation system.

AB - In this paper, we present a novel parallel implementation of Active Shape Model (ASM) on GPU for massive facial feature extractions in video or image sequence. With the Compute Unified Device Architecture (CUDA)-enabled GPU, the acceleration is significant and reported a 48 times performance boost comparing to a CPU implementation. We adopt the hardware built-in bilinear interpolation of texture to shorten the time for a large number of image scale transform operations. Then, a GPU-based parallel mahalanobis distance calculation is introduced in the searching process, and this enables most of the computations to be performed simultanously. As a result, we can achieve real-time performance in our video-driven 3D facial animation system.

UR - https://www.scopus.com/pages/publications/77949497086

U2 - 10.1109/ICICISYS.2009.5357636

DO - 10.1109/ICICISYS.2009.5357636

M3 - Conference article published in proceeding or book

SN - 9781424447541

VL - 4

SP - 522

EP - 526

BT - Proceedings - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009

T2 - 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009

Y2 - 20 November 2009 through 22 November 2009

ER -

Accelerating active shape model using GPU for facial extraction in video

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this