The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous avons développé un nouveau système de suivi du visage humain qui fonctionne en temps réel à une fréquence d'images vidéo sans nécessiter de matériel spécial. L'approche est basée sur l'utilisation de l'algèbre de Lie et utilise des points caractéristiques tridimensionnels sur le visage humain ciblé. On suppose que le modèle facial grossièrement estimé (coordonnées relatives des points caractéristiques tridimensionnels) est connu. Tout d’abord, les positions initiales des caractéristiques du visage sont déterminées à l’aide d’une technique d’ajustement de modèle. Ensuite, le suivi est effectué selon la séquence suivante : (1) capturer la nouvelle image vidéo et restituer les points caractéristiques sur le plan de l'image ; (2) rechercher de nouvelles positions des points caractéristiques sur le plan image ; (3) obtenir la matrice euclidienne à partir du vecteur mobile et les informations tridimensionnelles pour les points ; et (4) faire pivoter et déplacer les points caractéristiques à l'aide de la matrice euclidienne, et restituer les nouveaux points sur le plan de l'image. L'algorithme clé de ce tracker consiste à estimer la matrice euclidienne en utilisant une technique des moindres carrés basée sur l'algèbre de Lie. Le tracker résultant s’est très bien comporté dans la tâche de suivi d’un visage humain.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Akira INOUE, Tom DRUMMOND, Roberto CIPOLLA, "Real Time Feature-Based Facial Tracking Using Lie Algebras" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 12, pp. 1733-1738, December 2001, doi: .
Abstract: We have developed a novel human facial tracking system that operates in real time at a video frame rate without needing any special hardware. The approach is based on the use of Lie algebra, and uses three-dimensional feature points on the targeted human face. It is assumed that the roughly estimated facial model (relative coordinates of the three-dimensional feature points) is known. First, the initial feature positions of the face are determined using a model fitting technique. Then, the tracking is operated by the following sequence: (1) capture the new video frame and render feature points to the image plane; (2) search for new positions of the feature points on the image plane; (3) get the Euclidean matrix from the moving vector and the three-dimensional information for the points; and (4) rotate and translate the feature points by using the Euclidean matrix, and render the new points on the image plane. The key algorithm of this tracker is to estimate the Euclidean matrix by using a least square technique based on Lie algebra. The resulting tracker performed very well on the task of tracking a human face.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_12_1733/_p
Copier
@ARTICLE{e84-d_12_1733,
author={Akira INOUE, Tom DRUMMOND, Roberto CIPOLLA, },
journal={IEICE TRANSACTIONS on Information},
title={Real Time Feature-Based Facial Tracking Using Lie Algebras},
year={2001},
volume={E84-D},
number={12},
pages={1733-1738},
abstract={We have developed a novel human facial tracking system that operates in real time at a video frame rate without needing any special hardware. The approach is based on the use of Lie algebra, and uses three-dimensional feature points on the targeted human face. It is assumed that the roughly estimated facial model (relative coordinates of the three-dimensional feature points) is known. First, the initial feature positions of the face are determined using a model fitting technique. Then, the tracking is operated by the following sequence: (1) capture the new video frame and render feature points to the image plane; (2) search for new positions of the feature points on the image plane; (3) get the Euclidean matrix from the moving vector and the three-dimensional information for the points; and (4) rotate and translate the feature points by using the Euclidean matrix, and render the new points on the image plane. The key algorithm of this tracker is to estimate the Euclidean matrix by using a least square technique based on Lie algebra. The resulting tracker performed very well on the task of tracking a human face.},
keywords={},
doi={},
ISSN={},
month={December},}
Copier
TY - JOUR
TI - Real Time Feature-Based Facial Tracking Using Lie Algebras
T2 - IEICE TRANSACTIONS on Information
SP - 1733
EP - 1738
AU - Akira INOUE
AU - Tom DRUMMOND
AU - Roberto CIPOLLA
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2001
AB - We have developed a novel human facial tracking system that operates in real time at a video frame rate without needing any special hardware. The approach is based on the use of Lie algebra, and uses three-dimensional feature points on the targeted human face. It is assumed that the roughly estimated facial model (relative coordinates of the three-dimensional feature points) is known. First, the initial feature positions of the face are determined using a model fitting technique. Then, the tracking is operated by the following sequence: (1) capture the new video frame and render feature points to the image plane; (2) search for new positions of the feature points on the image plane; (3) get the Euclidean matrix from the moving vector and the three-dimensional information for the points; and (4) rotate and translate the feature points by using the Euclidean matrix, and render the new points on the image plane. The key algorithm of this tracker is to estimate the Euclidean matrix by using a least square technique based on Lie algebra. The resulting tracker performed very well on the task of tracking a human face.
ER -