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
Divers modèles d'observation ont été introduits dans la communauté du suivi d'objets, et leur combinaison est devenue une direction prometteuse. Cet article propose une nouvelle approche pour estimer les niveaux de confiance de différents modèles d'observation, puis les combiner efficacement dans le cadre du filtre à particules. Dans notre approche, la distribution spatiale de la vraisemblance est représentée par trois paramètres simples mais efficaces, reflétant la similarité globale, la netteté de la distribution et le degré de multi-pics. L'équilibre de ces trois aspects conduit à une bonne estimation des confiances, ce qui permet de conserver les avantages de chaque modèle d'observation et d'augmenter encore la robustesse à l'occlusion partielle. Des expérimentations sur des séquences vidéo difficiles démontrent l’efficacité de notre approche.
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
Fan JIANG, Guijin WANG, Chang LIU, Xinggang LIN, Weiguo WU, "Robust Object Tracking via Combining Observation Models" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 3, pp. 662-665, March 2010, doi: 10.1587/transinf.E93.D.662.
Abstract: Various observation models have been introduced into the object tracking community, and combining them has become a promising direction. This paper proposes a novel approach for estimating the confidences of different observation models, and then effectively combining them in the particle filter framework. In our approach, spatial Likelihood distribution is represented by three simple but efficient parameters, reflecting the overall similarity, distribution sharpness and degree of multi peak. The balance of these three aspects leads to good estimation of confidences, which helps maintain the advantages of each observation model and further increases robustness to partial occlusion. Experiments on challenging video sequences demonstrate the effectiveness of our approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.662/_p
Copier
@ARTICLE{e93-d_3_662,
author={Fan JIANG, Guijin WANG, Chang LIU, Xinggang LIN, Weiguo WU, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Object Tracking via Combining Observation Models},
year={2010},
volume={E93-D},
number={3},
pages={662-665},
abstract={Various observation models have been introduced into the object tracking community, and combining them has become a promising direction. This paper proposes a novel approach for estimating the confidences of different observation models, and then effectively combining them in the particle filter framework. In our approach, spatial Likelihood distribution is represented by three simple but efficient parameters, reflecting the overall similarity, distribution sharpness and degree of multi peak. The balance of these three aspects leads to good estimation of confidences, which helps maintain the advantages of each observation model and further increases robustness to partial occlusion. Experiments on challenging video sequences demonstrate the effectiveness of our approach.},
keywords={},
doi={10.1587/transinf.E93.D.662},
ISSN={1745-1361},
month={March},}
Copier
TY - JOUR
TI - Robust Object Tracking via Combining Observation Models
T2 - IEICE TRANSACTIONS on Information
SP - 662
EP - 665
AU - Fan JIANG
AU - Guijin WANG
AU - Chang LIU
AU - Xinggang LIN
AU - Weiguo WU
PY - 2010
DO - 10.1587/transinf.E93.D.662
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2010
AB - Various observation models have been introduced into the object tracking community, and combining them has become a promising direction. This paper proposes a novel approach for estimating the confidences of different observation models, and then effectively combining them in the particle filter framework. In our approach, spatial Likelihood distribution is represented by three simple but efficient parameters, reflecting the overall similarity, distribution sharpness and degree of multi peak. The balance of these three aspects leads to good estimation of confidences, which helps maintain the advantages of each observation model and further increases robustness to partial occlusion. Experiments on challenging video sequences demonstrate the effectiveness of our approach.
ER -