Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters
In recent years, visual object tracking has been widely used in military guidance, human-computer interaction, road traffic, scene monitoring and many other fields. The tracking algorithms based on correlation filters have shown good performance in terms of accuracy and tracking speed. However, thei...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/17/11/2626 |
| _version_ | 1828116769345110016 |
|---|---|
| author | Fan Li Sirou Zhang Xiaoya Qiao |
| author_facet | Fan Li Sirou Zhang Xiaoya Qiao |
| author_sort | Fan Li |
| collection | DOAJ |
| description | In recent years, visual object tracking has been widely used in military guidance, human-computer interaction, road traffic, scene monitoring and many other fields. The tracking algorithms based on correlation filters have shown good performance in terms of accuracy and tracking speed. However, their performance is not satisfactory in scenes with scale variation, deformation, and occlusion. In this paper, we propose a scene-aware adaptive updating mechanism for visual tracking via a kernel correlation filter (KCF). First, a low complexity scale estimation method is presented, in which the corresponding weight in five scales is employed to determine the final target scale. Then, the adaptive updating mechanism is presented based on the scene-classification. We classify the video scenes as four categories by video content analysis. According to the target scene, we exploit the adaptive updating mechanism to update the kernel correlation filter to improve the robustness of the tracker, especially in scenes with scale variation, deformation, and occlusion. We evaluate our tracker on the CVPR2013 benchmark. The experimental results obtained with the proposed algorithm are improved by 33.3%, 15%, 6%, 21.9% and 19.8% compared to those of the KCF tracker on the scene with scale variation, partial or long-time large-area occlusion, deformation, fast motion and out-of-view. |
| first_indexed | 2024-04-11T13:03:22Z |
| format | Article |
| id | doaj.art-ffc96d6f877d4ec89d16261f59eec24a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:03:22Z |
| publishDate | 2017-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ffc96d6f877d4ec89d16261f59eec24a2022-12-22T04:22:52ZengMDPI AGSensors1424-82202017-11-011711262610.3390/s17112626s17112626Scene-Aware Adaptive Updating for Visual Tracking via Correlation FiltersFan Li0Sirou Zhang1Xiaoya Qiao2Department of Information and Communication Engineering, School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaDepartment of Information and Communication Engineering, School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaDepartment of Information and Communication Engineering, School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaIn recent years, visual object tracking has been widely used in military guidance, human-computer interaction, road traffic, scene monitoring and many other fields. The tracking algorithms based on correlation filters have shown good performance in terms of accuracy and tracking speed. However, their performance is not satisfactory in scenes with scale variation, deformation, and occlusion. In this paper, we propose a scene-aware adaptive updating mechanism for visual tracking via a kernel correlation filter (KCF). First, a low complexity scale estimation method is presented, in which the corresponding weight in five scales is employed to determine the final target scale. Then, the adaptive updating mechanism is presented based on the scene-classification. We classify the video scenes as four categories by video content analysis. According to the target scene, we exploit the adaptive updating mechanism to update the kernel correlation filter to improve the robustness of the tracker, especially in scenes with scale variation, deformation, and occlusion. We evaluate our tracker on the CVPR2013 benchmark. The experimental results obtained with the proposed algorithm are improved by 33.3%, 15%, 6%, 21.9% and 19.8% compared to those of the KCF tracker on the scene with scale variation, partial or long-time large-area occlusion, deformation, fast motion and out-of-view.https://www.mdpi.com/1424-8220/17/11/2626visual object trackingscene-classificationadaptive updating mechanismocclusion |
| spellingShingle | Fan Li Sirou Zhang Xiaoya Qiao Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters Sensors visual object tracking scene-classification adaptive updating mechanism occlusion |
| title | Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters |
| title_full | Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters |
| title_fullStr | Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters |
| title_full_unstemmed | Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters |
| title_short | Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters |
| title_sort | scene aware adaptive updating for visual tracking via correlation filters |
| topic | visual object tracking scene-classification adaptive updating mechanism occlusion |
| url | https://www.mdpi.com/1424-8220/17/11/2626 |
| work_keys_str_mv | AT fanli sceneawareadaptiveupdatingforvisualtrackingviacorrelationfilters AT sirouzhang sceneawareadaptiveupdatingforvisualtrackingviacorrelationfilters AT xiaoyaqiao sceneawareadaptiveupdatingforvisualtrackingviacorrelationfilters |