Skip to content
Back to outputs

A fusion method for robust face tracking

Research output: Contribution to journalArticlepeer-review

Standard

A fusion method for robust face tracking. / Jiang, Xiaodong; Yu, Hui; Lu, Yang; Liu, Honghai.

In: Multimedia Tools and Applications, Vol. 75, No. 19, 10.2016, p. 11801-11813.

Research output: Contribution to journalArticlepeer-review

Harvard

Jiang, X, Yu, H, Lu, Y & Liu, H 2016, 'A fusion method for robust face tracking', Multimedia Tools and Applications, vol. 75, no. 19, pp. 11801-11813. https://doi.org/10.1007/s11042-015-2659-5

APA

Jiang, X., Yu, H., Lu, Y., & Liu, H. (2016). A fusion method for robust face tracking. Multimedia Tools and Applications, 75(19), 11801-11813. https://doi.org/10.1007/s11042-015-2659-5

Vancouver

Jiang X, Yu H, Lu Y, Liu H. A fusion method for robust face tracking. Multimedia Tools and Applications. 2016 Oct;75(19):11801-11813. https://doi.org/10.1007/s11042-015-2659-5

Author

Jiang, Xiaodong ; Yu, Hui ; Lu, Yang ; Liu, Honghai. / A fusion method for robust face tracking. In: Multimedia Tools and Applications. 2016 ; Vol. 75, No. 19. pp. 11801-11813.

Bibtex

@article{de9f33feb2d84572a46b4e113cee8380,
title = "A fusion method for robust face tracking",
abstract = "Face tracking often encounters drifting problems, especially when a significant face appearance variation occurs. Many trackers suffer from the difficulty of facial feature extraction during a wide range of face turning, occlusion, and even invisibleness. In this paper, we propose a novel yet efficient fusion strategy for robust face tracking. A Supervised Descent Method (SDM) and a Compressive Tracking method (CT) are employed at the same time. SDM is used to correct drifting errors of CT continuously during frontal face tracking. However, when the face orientation changes to the angle orthogonal to the view line, it results in tracking failure for the SDM method. CT is then adopted to keep face region being tracked until SDM detects and tracks the face again. In the experiments, we test the proposed method for real-time tracking using several challenging sequences from recent literatures. The fusion strategy has achieved encouraging performance in terms of efficiency and reliability.",
author = "Xiaodong Jiang and Hui Yu and Yang Lu and Honghai Liu",
year = "2016",
month = oct,
doi = "10.1007/s11042-015-2659-5",
language = "English",
volume = "75",
pages = "11801--11813",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "19",

}

RIS

TY - JOUR

T1 - A fusion method for robust face tracking

AU - Jiang, Xiaodong

AU - Yu, Hui

AU - Lu, Yang

AU - Liu, Honghai

PY - 2016/10

Y1 - 2016/10

N2 - Face tracking often encounters drifting problems, especially when a significant face appearance variation occurs. Many trackers suffer from the difficulty of facial feature extraction during a wide range of face turning, occlusion, and even invisibleness. In this paper, we propose a novel yet efficient fusion strategy for robust face tracking. A Supervised Descent Method (SDM) and a Compressive Tracking method (CT) are employed at the same time. SDM is used to correct drifting errors of CT continuously during frontal face tracking. However, when the face orientation changes to the angle orthogonal to the view line, it results in tracking failure for the SDM method. CT is then adopted to keep face region being tracked until SDM detects and tracks the face again. In the experiments, we test the proposed method for real-time tracking using several challenging sequences from recent literatures. The fusion strategy has achieved encouraging performance in terms of efficiency and reliability.

AB - Face tracking often encounters drifting problems, especially when a significant face appearance variation occurs. Many trackers suffer from the difficulty of facial feature extraction during a wide range of face turning, occlusion, and even invisibleness. In this paper, we propose a novel yet efficient fusion strategy for robust face tracking. A Supervised Descent Method (SDM) and a Compressive Tracking method (CT) are employed at the same time. SDM is used to correct drifting errors of CT continuously during frontal face tracking. However, when the face orientation changes to the angle orthogonal to the view line, it results in tracking failure for the SDM method. CT is then adopted to keep face region being tracked until SDM detects and tracks the face again. In the experiments, we test the proposed method for real-time tracking using several challenging sequences from recent literatures. The fusion strategy has achieved encouraging performance in terms of efficiency and reliability.

UR - http://link.springer.com/article/10.1007%2Fs11042-015-2659-5

U2 - 10.1007/s11042-015-2659-5

DO - 10.1007/s11042-015-2659-5

M3 - Article

VL - 75

SP - 11801

EP - 11813

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 19

ER -

ID: 3038915