Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/628373
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDawei Duen_US
dc.contributor.authorHonggang Qien_US
dc.contributor.authorWenbo Lien_US
dc.contributor.authorLongyin Wenen_US
dc.contributor.authorQingming Huangen_US
dc.contributor.authorSiwei Lyuen_US
dc.date.accessioned2020-05-20T09:40:31Z-
dc.date.available2020-05-20T09:40:31Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2570556en_US
dc.identifier.urihttp://localhost/handle/Hannan/152280en_US
dc.identifier.urihttp://localhost/handle/Hannan/628373-
dc.description.abstractRecent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in multiple frames, making them less effective in handling large deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. We construct a structure-aware hyper-graph to capture such higher order dependences, and solve the tracking problem by searching dense subgraphs on it. Furthermore, we also describe a new evaluating data set for online deformable object tracking (the Deform-SOT data set), which includes 50 challenging sequences with full annotations that represent realistic tracking challenges, such as large deformations and severe occlusions. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking methods.en_US
dc.publisherIEEEen_US
dc.relation.haspart7471473.pdfen_US
dc.subjectOnline tracking|deformable object tracking|structure-aware hyper-graph|dense subgraph searching|part-based modelen_US
dc.titleOnline Deformable Object Tracking Based on Structure-Aware Hyper-Graphen_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue8en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7471473.pdf6.5 MBAdobe PDFThumbnail
Preview File
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDawei Duen_US
dc.contributor.authorHonggang Qien_US
dc.contributor.authorWenbo Lien_US
dc.contributor.authorLongyin Wenen_US
dc.contributor.authorQingming Huangen_US
dc.contributor.authorSiwei Lyuen_US
dc.date.accessioned2020-05-20T09:40:31Z-
dc.date.available2020-05-20T09:40:31Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2570556en_US
dc.identifier.urihttp://localhost/handle/Hannan/152280en_US
dc.identifier.urihttp://localhost/handle/Hannan/628373-
dc.description.abstractRecent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in multiple frames, making them less effective in handling large deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. We construct a structure-aware hyper-graph to capture such higher order dependences, and solve the tracking problem by searching dense subgraphs on it. Furthermore, we also describe a new evaluating data set for online deformable object tracking (the Deform-SOT data set), which includes 50 challenging sequences with full annotations that represent realistic tracking challenges, such as large deformations and severe occlusions. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking methods.en_US
dc.publisherIEEEen_US
dc.relation.haspart7471473.pdfen_US
dc.subjectOnline tracking|deformable object tracking|structure-aware hyper-graph|dense subgraph searching|part-based modelen_US
dc.titleOnline Deformable Object Tracking Based on Structure-Aware Hyper-Graphen_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue8en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7471473.pdf6.5 MBAdobe PDFThumbnail
Preview File
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDawei Duen_US
dc.contributor.authorHonggang Qien_US
dc.contributor.authorWenbo Lien_US
dc.contributor.authorLongyin Wenen_US
dc.contributor.authorQingming Huangen_US
dc.contributor.authorSiwei Lyuen_US
dc.date.accessioned2020-05-20T09:40:31Z-
dc.date.available2020-05-20T09:40:31Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2570556en_US
dc.identifier.urihttp://localhost/handle/Hannan/152280en_US
dc.identifier.urihttp://localhost/handle/Hannan/628373-
dc.description.abstractRecent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. However, previous methods usually consider only the pairwise structural dependences of target parts in two consecutive frames rather than the higher order constraints in multiple frames, making them less effective in handling large deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. We construct a structure-aware hyper-graph to capture such higher order dependences, and solve the tracking problem by searching dense subgraphs on it. Furthermore, we also describe a new evaluating data set for online deformable object tracking (the Deform-SOT data set), which includes 50 challenging sequences with full annotations that represent realistic tracking challenges, such as large deformations and severe occlusions. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking methods.en_US
dc.publisherIEEEen_US
dc.relation.haspart7471473.pdfen_US
dc.subjectOnline tracking|deformable object tracking|structure-aware hyper-graph|dense subgraph searching|part-based modelen_US
dc.titleOnline Deformable Object Tracking Based on Structure-Aware Hyper-Graphen_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue8en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7471473.pdf6.5 MBAdobe PDFThumbnail
Preview File