Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters
Accurate scale estimation and occlusion handling is a challenging problem in visual tracking. Recently, correlation filter-based trackers have shown impressive results in terms of accuracy, robustness, and speed. However, the model is not robust to scale variation and occlusion. In this paper, we ad...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/17/3/433 |
| _version_ | 1797999899921350656 |
|---|---|
| author | Soowoong Jeong Guisik Kim Sangkeun Lee |
| author_facet | Soowoong Jeong Guisik Kim Sangkeun Lee |
| author_sort | Soowoong Jeong |
| collection | DOAJ |
| description | Accurate scale estimation and occlusion handling is a challenging problem in visual tracking. Recently, correlation filter-based trackers have shown impressive results in terms of accuracy, robustness, and speed. However, the model is not robust to scale variation and occlusion. In this paper, we address the problems associated with scale variation and occlusion by employing a scale space filter and multi-block scheme based on a kernelized correlation filter (KCF) tracker. Furthermore, we develop a more robust algorithm using an appearance update model that approximates the change of state of occlusion and deformation. In particular, an adaptive update scheme is presented to make each process robust. The experimental results demonstrate that the proposed method outperformed 29 state-of-the-art trackers on 100 challenging sequences. Specifically, the results obtained with the proposed scheme were improved by 8% and 18% compared to those of the KCF tracker for 49 occlusion and 64 scale variation sequences, respectively. Therefore, the proposed tracker can be a robust and useful tool for object tracking when occlusion and scale variation are involved. |
| first_indexed | 2024-04-11T11:11:59Z |
| format | Article |
| id | doaj.art-9d4022087db74991ae3d531b1cc4cea9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:11:59Z |
| publishDate | 2017-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9d4022087db74991ae3d531b1cc4cea92022-12-22T04:27:26ZengMDPI AGSensors1424-82202017-02-0117343310.3390/s17030433s17030433Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation FiltersSoowoong Jeong0Guisik Kim1Sangkeun Lee2Graduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University, Seoul 06974, KoreaGraduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University, Seoul 06974, KoreaGraduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University, Seoul 06974, KoreaAccurate scale estimation and occlusion handling is a challenging problem in visual tracking. Recently, correlation filter-based trackers have shown impressive results in terms of accuracy, robustness, and speed. However, the model is not robust to scale variation and occlusion. In this paper, we address the problems associated with scale variation and occlusion by employing a scale space filter and multi-block scheme based on a kernelized correlation filter (KCF) tracker. Furthermore, we develop a more robust algorithm using an appearance update model that approximates the change of state of occlusion and deformation. In particular, an adaptive update scheme is presented to make each process robust. The experimental results demonstrate that the proposed method outperformed 29 state-of-the-art trackers on 100 challenging sequences. Specifically, the results obtained with the proposed scheme were improved by 8% and 18% compared to those of the KCF tracker for 49 occlusion and 64 scale variation sequences, respectively. Therefore, the proposed tracker can be a robust and useful tool for object tracking when occlusion and scale variation are involved.http://www.mdpi.com/1424-8220/17/3/433computer visionvisual trackingscale variationcorrelation filtermulti-block methodadaptive learning rateillumination variationpartial occlusion |
| spellingShingle | Soowoong Jeong Guisik Kim Sangkeun Lee Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters Sensors computer vision visual tracking scale variation correlation filter multi-block method adaptive learning rate illumination variation partial occlusion |
| title | Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters |
| title_full | Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters |
| title_fullStr | Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters |
| title_full_unstemmed | Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters |
| title_short | Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters |
| title_sort | effective visual tracking using multi block and scale space based on kernelized correlation filters |
| topic | computer vision visual tracking scale variation correlation filter multi-block method adaptive learning rate illumination variation partial occlusion |
| url | http://www.mdpi.com/1424-8220/17/3/433 |
| work_keys_str_mv | AT soowoongjeong effectivevisualtrackingusingmultiblockandscalespacebasedonkernelizedcorrelationfilters AT guisikkim effectivevisualtrackingusingmultiblockandscalespacebasedonkernelizedcorrelationfilters AT sangkeunlee effectivevisualtrackingusingmultiblockandscalespacebasedonkernelizedcorrelationfilters |