Fast deformable structure regression tracking
Visual object tracking is a challenging task because designing an effective and efficient appearance model is difficult. Current online tracking algorithms treat tracking as a classification task and use labelled samples to update appearance model. However, it is not clear to evaluate instance confi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-03-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2014.0315 |
| _version_ | 1827817204432764928 |
|---|---|
| author | Xian Yang Shoujue Wang |
| author_facet | Xian Yang Shoujue Wang |
| author_sort | Xian Yang |
| collection | DOAJ |
| description | Visual object tracking is a challenging task because designing an effective and efficient appearance model is difficult. Current online tracking algorithms treat tracking as a classification task and use labelled samples to update appearance model. However, it is not clear to evaluate instance confidence belongs to the object. In this study, the authors propose a simple and efficient tracking algorithm with a deformable structure appearance. In their method, model updates with continuous labelled samples which are dense sampling. To improve the accuracy, they introduce a coupled‐layer regression model which prevents negative background from impacting on the model learning rather than traditional classification. The proposed deformable structure regression tracker runs in real time and performs favourably against state‐of‐the‐art trackers on various challenging sequences. |
| first_indexed | 2024-03-12T00:31:05Z |
| format | Article |
| id | doaj.art-485e2733a7214383aaf6d91999cb50f0 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:31:05Z |
| publishDate | 2016-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-485e2733a7214383aaf6d91999cb50f02023-09-15T10:15:40ZengWileyIET Computer Vision1751-96321751-96402016-03-0110211512310.1049/iet-cvi.2014.0315Fast deformable structure regression trackingXian Yang0Shoujue Wang1Laboratory of Artificial Neural NetworksInstitute of SemiconductorsCASBeijingPeople's Republic of ChinaLaboratory of Artificial Neural NetworksInstitute of SemiconductorsCASBeijingPeople's Republic of ChinaVisual object tracking is a challenging task because designing an effective and efficient appearance model is difficult. Current online tracking algorithms treat tracking as a classification task and use labelled samples to update appearance model. However, it is not clear to evaluate instance confidence belongs to the object. In this study, the authors propose a simple and efficient tracking algorithm with a deformable structure appearance. In their method, model updates with continuous labelled samples which are dense sampling. To improve the accuracy, they introduce a coupled‐layer regression model which prevents negative background from impacting on the model learning rather than traditional classification. The proposed deformable structure regression tracker runs in real time and performs favourably against state‐of‐the‐art trackers on various challenging sequences.https://doi.org/10.1049/iet-cvi.2014.0315fast deformable structure regression trackingvisual object trackingeffective appearance modelefficient appearance modelclassification taskdense sampling |
| spellingShingle | Xian Yang Shoujue Wang Fast deformable structure regression tracking IET Computer Vision fast deformable structure regression tracking visual object tracking effective appearance model efficient appearance model classification task dense sampling |
| title | Fast deformable structure regression tracking |
| title_full | Fast deformable structure regression tracking |
| title_fullStr | Fast deformable structure regression tracking |
| title_full_unstemmed | Fast deformable structure regression tracking |
| title_short | Fast deformable structure regression tracking |
| title_sort | fast deformable structure regression tracking |
| topic | fast deformable structure regression tracking visual object tracking effective appearance model efficient appearance model classification task dense sampling |
| url | https://doi.org/10.1049/iet-cvi.2014.0315 |
| work_keys_str_mv | AT xianyang fastdeformablestructureregressiontracking AT shoujuewang fastdeformablestructureregressiontracking |