Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/656260
Title: Occlusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency
Authors: Chong Sun;Dong Wang;Huchuan Lu
subject: visual tracking|spatial-temporal consistency|fragment-based appearance model|occlusion model
Year: 2016
Publisher: IEEE
Abstract: In this paper, we present a robust tracking method by exploiting a fragment-based appearance model with consideration of both temporal continuity and discontinuity information. From the perspective of probability theory, the proposed tracking algorithm can be viewed as a two-stage optimization problem. In the first stage, by adopting the estimated occlusion state as a prior, the optimal state of the tracked object can be obtained by solving an optimization problem, where the objective function is designed based on the classification score, occlusion prior, and temporal continuity information. In the second stage, we propose a discriminative occlusion model, which exploits both foreground and background information to detect the possible occlusion, and also models the consistency of occlusion labels among different frames. In addition, a simple yet effective training strategy is introduced during the model training (and updating) process, with which the effects of spatial-temporal consistency are properly weighted. The proposed tracker is evaluated by using the recent benchmark data set, on which the results demonstrate that our tracker performs favorably against other state-of-the-art tracking algorithms.
URI: http://localhost/handle/Hannan/151127
http://localhost/handle/Hannan/656260
ISSN: 1057-7149
1941-0042
volume: 25
issue: 8
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7490397.pdf3.95 MBAdobe PDFThumbnail
Preview File
Title: Occlusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency
Authors: Chong Sun;Dong Wang;Huchuan Lu
subject: visual tracking|spatial-temporal consistency|fragment-based appearance model|occlusion model
Year: 2016
Publisher: IEEE
Abstract: In this paper, we present a robust tracking method by exploiting a fragment-based appearance model with consideration of both temporal continuity and discontinuity information. From the perspective of probability theory, the proposed tracking algorithm can be viewed as a two-stage optimization problem. In the first stage, by adopting the estimated occlusion state as a prior, the optimal state of the tracked object can be obtained by solving an optimization problem, where the objective function is designed based on the classification score, occlusion prior, and temporal continuity information. In the second stage, we propose a discriminative occlusion model, which exploits both foreground and background information to detect the possible occlusion, and also models the consistency of occlusion labels among different frames. In addition, a simple yet effective training strategy is introduced during the model training (and updating) process, with which the effects of spatial-temporal consistency are properly weighted. The proposed tracker is evaluated by using the recent benchmark data set, on which the results demonstrate that our tracker performs favorably against other state-of-the-art tracking algorithms.
URI: http://localhost/handle/Hannan/151127
http://localhost/handle/Hannan/656260
ISSN: 1057-7149
1941-0042
volume: 25
issue: 8
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7490397.pdf3.95 MBAdobe PDFThumbnail
Preview File
Title: Occlusion-Aware Fragment-Based Tracking With Spatial-Temporal Consistency
Authors: Chong Sun;Dong Wang;Huchuan Lu
subject: visual tracking|spatial-temporal consistency|fragment-based appearance model|occlusion model
Year: 2016
Publisher: IEEE
Abstract: In this paper, we present a robust tracking method by exploiting a fragment-based appearance model with consideration of both temporal continuity and discontinuity information. From the perspective of probability theory, the proposed tracking algorithm can be viewed as a two-stage optimization problem. In the first stage, by adopting the estimated occlusion state as a prior, the optimal state of the tracked object can be obtained by solving an optimization problem, where the objective function is designed based on the classification score, occlusion prior, and temporal continuity information. In the second stage, we propose a discriminative occlusion model, which exploits both foreground and background information to detect the possible occlusion, and also models the consistency of occlusion labels among different frames. In addition, a simple yet effective training strategy is introduced during the model training (and updating) process, with which the effects of spatial-temporal consistency are properly weighted. The proposed tracker is evaluated by using the recent benchmark data set, on which the results demonstrate that our tracker performs favorably against other state-of-the-art tracking algorithms.
URI: http://localhost/handle/Hannan/151127
http://localhost/handle/Hannan/656260
ISSN: 1057-7149
1941-0042
volume: 25
issue: 8
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7490397.pdf3.95 MBAdobe PDFThumbnail
Preview File