Long-term tracking with fast scale estimation and efficient re-detection
In long-term tracking applications, occlusion and scale variation are common attributes which cause performance degradation. Existing solutions use heavy calculation to deal with these problems, without considering the real-time implementation. Therefore, the authors propose a novel long-term tracke...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-09-01
|
| Series: | The Journal of Engineering |
| Subjects: | |
| Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0236 |
| _version_ | 1818622195145900032 |
|---|---|
| author | Zhang Zengshuo Tang Linbo Han Yuqi Nan Jinghong Zhao Baojun |
| author_facet | Zhang Zengshuo Tang Linbo Han Yuqi Nan Jinghong Zhao Baojun |
| author_sort | Zhang Zengshuo |
| collection | DOAJ |
| description | In long-term tracking applications, occlusion and scale variation are common attributes which cause performance degradation. Existing solutions use heavy calculation to deal with these problems, without considering the real-time implementation. Therefore, the authors propose a novel long-term tracker with fast scale estimation and efficient re-detection scheme to maintain real-time speed and favourable accuracy. Specifically, the authors integrate a distance metric method into correlation filter-based tracker to realise fast translation calculation and scale estimation. In addition, the authors advocate a keypoint-matching based confidence indicator to verify the tracking result and activate the re-detection module when the occlusion happens. The authors test our approach on challenging sequences with scale variation and occlusion. Experiments demonstrate that our proposed tracker procures preferable effect than state-of-the-art methods in the aspect of both speed and accuracy. |
| first_indexed | 2024-12-16T18:21:18Z |
| format | Article |
| id | doaj.art-3066c94e51e44ff296c99fca8a287a99 |
| institution | Directory Open Access Journal |
| issn | 2051-3305 |
| language | English |
| last_indexed | 2024-12-16T18:21:18Z |
| publishDate | 2019-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Engineering |
| spelling | doaj.art-3066c94e51e44ff296c99fca8a287a992022-12-21T22:21:32ZengWileyThe Journal of Engineering2051-33052019-09-0110.1049/joe.2019.0236JOE.2019.0236Long-term tracking with fast scale estimation and efficient re-detectionZhang Zengshuo0Tang Linbo1Han Yuqi2Nan Jinghong3Zhao Baojun4School of Information and Electronic, Beijing Institute of TechnologySchool of Information and Electronic, Beijing Institute of TechnologySchool of Information and Electronic, Beijing Institute of TechnologySchool of Information and Electronic, Beijing Institute of TechnologySchool of Information and Electronic, Beijing Institute of TechnologyIn long-term tracking applications, occlusion and scale variation are common attributes which cause performance degradation. Existing solutions use heavy calculation to deal with these problems, without considering the real-time implementation. Therefore, the authors propose a novel long-term tracker with fast scale estimation and efficient re-detection scheme to maintain real-time speed and favourable accuracy. Specifically, the authors integrate a distance metric method into correlation filter-based tracker to realise fast translation calculation and scale estimation. In addition, the authors advocate a keypoint-matching based confidence indicator to verify the tracking result and activate the re-detection module when the occlusion happens. The authors test our approach on challenging sequences with scale variation and occlusion. Experiments demonstrate that our proposed tracker procures preferable effect than state-of-the-art methods in the aspect of both speed and accuracy.https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0236image sequencesobject detectionobject trackingimage matchinglong-term trackerperformance degradationlong-term tracking applicationsfast scale estimationscale variationre-detection modulekeypoint-matching based confidence indicatorfast translation calculationcorrelation filter-based trackerdistance metric methodreal-time speedefficient re-detection scheme |
| spellingShingle | Zhang Zengshuo Tang Linbo Han Yuqi Nan Jinghong Zhao Baojun Long-term tracking with fast scale estimation and efficient re-detection The Journal of Engineering image sequences object detection object tracking image matching long-term tracker performance degradation long-term tracking applications fast scale estimation scale variation re-detection module keypoint-matching based confidence indicator fast translation calculation correlation filter-based tracker distance metric method real-time speed efficient re-detection scheme |
| title | Long-term tracking with fast scale estimation and efficient re-detection |
| title_full | Long-term tracking with fast scale estimation and efficient re-detection |
| title_fullStr | Long-term tracking with fast scale estimation and efficient re-detection |
| title_full_unstemmed | Long-term tracking with fast scale estimation and efficient re-detection |
| title_short | Long-term tracking with fast scale estimation and efficient re-detection |
| title_sort | long term tracking with fast scale estimation and efficient re detection |
| topic | image sequences object detection object tracking image matching long-term tracker performance degradation long-term tracking applications fast scale estimation scale variation re-detection module keypoint-matching based confidence indicator fast translation calculation correlation filter-based tracker distance metric method real-time speed efficient re-detection scheme |
| url | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0236 |
| work_keys_str_mv | AT zhangzengshuo longtermtrackingwithfastscaleestimationandefficientredetection AT tanglinbo longtermtrackingwithfastscaleestimationandefficientredetection AT hanyuqi longtermtrackingwithfastscaleestimationandefficientredetection AT nanjinghong longtermtrackingwithfastscaleestimationandefficientredetection AT zhaobaojun longtermtrackingwithfastscaleestimationandefficientredetection |