Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity
We address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. We first select features with low-rank representation within a number of initial frames to obtain subspace basis. Next, the features represented by the low-ran...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Abstract and Applied Analysis |
| Online Access: | http://dx.doi.org/10.1155/2014/147353 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832556732114534400 |
|---|---|
| author | Hyuncheol Kim Joonki Paik |
| author_facet | Hyuncheol Kim Joonki Paik |
| author_sort | Hyuncheol Kim |
| collection | DOAJ |
| description | We address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. We first select features with low-rank representation within a number of initial frames to obtain subspace basis. Next, the features represented by the low-rank and sparse property are learned using a modified joint sparsity-based multitask feature learning framework. Both the features and sparse errors are then optimally updated using a novel incremental alternating direction method. The low-rank minimization problem for learning multitask features can be achieved by a few sequences of efficient closed form update process. Since the proposed method attempts to perform the feature learning problem in both multitask and low-rank manner, it can not only reduce the dimension but also improve the tracking performance without drift. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art tracking methods for tracking objects in challenging image sequences. |
| format | Article |
| id | doaj-art-2df764c40f79473d9a8ce8e897f1484f |
| institution | Kabale University |
| issn | 1085-3375 1687-0409 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Abstract and Applied Analysis |
| spelling | doaj-art-2df764c40f79473d9a8ce8e897f1484f2025-02-03T05:44:26ZengWileyAbstract and Applied Analysis1085-33751687-04092014-01-01201410.1155/2014/147353147353Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint SparsityHyuncheol Kim0Joonki Paik1Department of Image, Chung-Ang University, Seoul 156-756, Republic of KoreaDepartment of Image, Chung-Ang University, Seoul 156-756, Republic of KoreaWe address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. We first select features with low-rank representation within a number of initial frames to obtain subspace basis. Next, the features represented by the low-rank and sparse property are learned using a modified joint sparsity-based multitask feature learning framework. Both the features and sparse errors are then optimally updated using a novel incremental alternating direction method. The low-rank minimization problem for learning multitask features can be achieved by a few sequences of efficient closed form update process. Since the proposed method attempts to perform the feature learning problem in both multitask and low-rank manner, it can not only reduce the dimension but also improve the tracking performance without drift. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art tracking methods for tracking objects in challenging image sequences.http://dx.doi.org/10.1155/2014/147353 |
| spellingShingle | Hyuncheol Kim Joonki Paik Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity Abstract and Applied Analysis |
| title | Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity |
| title_full | Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity |
| title_fullStr | Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity |
| title_full_unstemmed | Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity |
| title_short | Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity |
| title_sort | low rank representation based object tracking using multitask feature learning with joint sparsity |
| url | http://dx.doi.org/10.1155/2014/147353 |
| work_keys_str_mv | AT hyuncheolkim lowrankrepresentationbasedobjecttrackingusingmultitaskfeaturelearningwithjointsparsity AT joonkipaik lowrankrepresentationbasedobjecttrackingusingmultitaskfeaturelearningwithjointsparsity |