Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision
Multiple-object tracking (MOT) has received an increasing attention due to the rapid development of autonomous driving. However, the MOT problem is still challenging mainly due to the occlusion and scale variation. Motivated by the fact that the discriminative correlation filters-based (DCFB) tracki...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8418354/ |
| _version_ | 1818877465756434432 |
|---|---|
| author | Chenglong Wu Hao Sun Hongqi Wang Kun Fu Guangluan Xu Wenkai Zhang Xian Sun |
| author_facet | Chenglong Wu Hao Sun Hongqi Wang Kun Fu Guangluan Xu Wenkai Zhang Xian Sun |
| author_sort | Chenglong Wu |
| collection | DOAJ |
| description | Multiple-object tracking (MOT) has received an increasing attention due to the rapid development of autonomous driving. However, the MOT problem is still challenging mainly due to the occlusion and scale variation. Motivated by the fact that the discriminative correlation filters-based (DCFB) tracking algorithms can tackle these problems and significantly improve the accuracy of single object tracking, how to exploit the DCFB tracking algorithms for MOT is worthy studying. Moreover, the corrupted training samples due to the occlusion make DCFB tracking methods to update the appearance model of target uncorrected and result in tracking drift. In this paper, we exploit Markov decision process to integrate the DCFB tracking method into our MOT framework and address the update problem of the appearance model in DCFB tracking method. Moreover, in order to overcome the challenges of occlusion and scale variation, to prevent target drift during tracking, we use two DCFB trackers with different update frequencies and a novel update strategy to predict the location of targets. The part-based method is used to extract robust features to tackling the challenges of occlusion and scale change. In order to verify the efficiency of our algorithm, experiments are performed based on KITTI tracking benchmark. The results demonstrate that our method achieves state-of-the-art performance and outperforms the state-of-the-art algorithms in road scenarios. |
| first_indexed | 2024-12-19T13:58:43Z |
| format | Article |
| id | doaj.art-08616f01990049059e36fb90982d7061 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:58:43Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-08616f01990049059e36fb90982d70612022-12-21T20:18:31ZengIEEEIEEE Access2169-35362018-01-016434994351210.1109/ACCESS.2018.28588538418354Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making DecisionChenglong Wu0https://orcid.org/0000-0003-2452-2746Hao Sun1Hongqi Wang2Kun Fu3Guangluan Xu4Wenkai Zhang5Xian Sun6Chinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaChinese Academy of Sciences, Institute of Electronics, Beijing, ChinaMultiple-object tracking (MOT) has received an increasing attention due to the rapid development of autonomous driving. However, the MOT problem is still challenging mainly due to the occlusion and scale variation. Motivated by the fact that the discriminative correlation filters-based (DCFB) tracking algorithms can tackle these problems and significantly improve the accuracy of single object tracking, how to exploit the DCFB tracking algorithms for MOT is worthy studying. Moreover, the corrupted training samples due to the occlusion make DCFB tracking methods to update the appearance model of target uncorrected and result in tracking drift. In this paper, we exploit Markov decision process to integrate the DCFB tracking method into our MOT framework and address the update problem of the appearance model in DCFB tracking method. Moreover, in order to overcome the challenges of occlusion and scale variation, to prevent target drift during tracking, we use two DCFB trackers with different update frequencies and a novel update strategy to predict the location of targets. The part-based method is used to extract robust features to tackling the challenges of occlusion and scale change. In order to verify the efficiency of our algorithm, experiments are performed based on KITTI tracking benchmark. The results demonstrate that our method achieves state-of-the-art performance and outperforms the state-of-the-art algorithms in road scenarios.https://ieeexplore.ieee.org/document/8418354/Multiple object trackingMarkov decision processdiscriminative correlation filterspart-based method |
| spellingShingle | Chenglong Wu Hao Sun Hongqi Wang Kun Fu Guangluan Xu Wenkai Zhang Xian Sun Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision IEEE Access Multiple object tracking Markov decision process discriminative correlation filters part-based method |
| title | Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision |
| title_full | Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision |
| title_fullStr | Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision |
| title_full_unstemmed | Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision |
| title_short | Online Multi-Object Tracking via Combining Discriminative Correlation Filters With Making Decision |
| title_sort | online multi object tracking via combining discriminative correlation filters with making decision |
| topic | Multiple object tracking Markov decision process discriminative correlation filters part-based method |
| url | https://ieeexplore.ieee.org/document/8418354/ |
| work_keys_str_mv | AT chenglongwu onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT haosun onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT hongqiwang onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT kunfu onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT guangluanxu onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT wenkaizhang onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision AT xiansun onlinemultiobjecttrackingviacombiningdiscriminativecorrelationfilterswithmakingdecision |