Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy
Many modern visual tracking algorithms incorporate spatial pooling, max pooling, or average pooling, which is to achieve invariance to feature transformations and better robustness to occlusion, illumination change, and position variation. In this paper, max-average pooling method and Weight-selecti...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2014/828907 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832565840408477696 |
|---|---|
| author | Suguo Zhu Junping Du |
| author_facet | Suguo Zhu Junping Du |
| author_sort | Suguo Zhu |
| collection | DOAJ |
| description | Many modern visual tracking algorithms incorporate spatial pooling, max pooling, or average pooling, which is to achieve invariance to feature transformations and better robustness to occlusion, illumination change, and position variation. In this paper, max-average pooling method and Weight-selection strategy are proposed with a hybrid framework, which is combined with sparse representation and particle filter, to exploit the spatial information of an object and make good compromises to ensure the correctness of the results in this framework. Challenges can be well considered by the proposed algorithm. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm compared with the state-of-the-art methods on challenging sequences. |
| format | Article |
| id | doaj-art-1a9a94419d6b41389f7662a8078fc740 |
| institution | Kabale University |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-1a9a94419d6b41389f7662a8078fc7402025-02-03T01:06:35ZengWileyJournal of Applied Mathematics1110-757X1687-00422014-01-01201410.1155/2014/828907828907Visual Tracking Using Max-Average Pooling and Weight-Selection StrategySuguo Zhu0Junping Du1Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaBeijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaMany modern visual tracking algorithms incorporate spatial pooling, max pooling, or average pooling, which is to achieve invariance to feature transformations and better robustness to occlusion, illumination change, and position variation. In this paper, max-average pooling method and Weight-selection strategy are proposed with a hybrid framework, which is combined with sparse representation and particle filter, to exploit the spatial information of an object and make good compromises to ensure the correctness of the results in this framework. Challenges can be well considered by the proposed algorithm. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm compared with the state-of-the-art methods on challenging sequences.http://dx.doi.org/10.1155/2014/828907 |
| spellingShingle | Suguo Zhu Junping Du Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy Journal of Applied Mathematics |
| title | Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy |
| title_full | Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy |
| title_fullStr | Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy |
| title_full_unstemmed | Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy |
| title_short | Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy |
| title_sort | visual tracking using max average pooling and weight selection strategy |
| url | http://dx.doi.org/10.1155/2014/828907 |
| work_keys_str_mv | AT suguozhu visualtrackingusingmaxaveragepoolingandweightselectionstrategy AT junpingdu visualtrackingusingmaxaveragepoolingandweightselectionstrategy |