Adaptive earth movers distance‐based Bayesian multi‐target tracking
This study describes a complete system for multiple‐target tracking in image sequences. The target appearance is represented as a set of weighted clusters in colour space. This is in contrast to the more typical use of colour histograms to model target appearance. The use of clusters allows a more f...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-08-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2011.0223 |
| _version_ | 1797685223052279808 |
|---|---|
| author | Pankaj Kumar Anthony Dick |
| author_facet | Pankaj Kumar Anthony Dick |
| author_sort | Pankaj Kumar |
| collection | DOAJ |
| description | This study describes a complete system for multiple‐target tracking in image sequences. The target appearance is represented as a set of weighted clusters in colour space. This is in contrast to the more typical use of colour histograms to model target appearance. The use of clusters allows a more flexible and accurate representation of the target, which demonstrates the benefits for tracking. However, it also introduces a number of computational difficulties, as calculating and matching cluster signatures are both computationally intensive tasks. To overcome this, the authors introduce a new formulation of incremental medoid‐shift clustering that operates faster than mean shift in multi‐target tracking scenarios. This matching scheme is integrated into a Bayesian tracking framework. Particle filters, a special case of Bayesian filters where the state variables are non‐linear and non‐Gaussian, are used in this study. An adaptive model update procedure is proposed for the cluster signature representation to handle target changes with time. The model update procedure is demonstrated to work successfully on a synthetic dataset and then on real datasets. Successful tracking results are shown on public datasets. Both qualitative and quantitative evaluations have been carried out to demonstrate the improved performance of the proposed multi‐target tracking system. A higher tracking accuracy in long image sequences has been achieved compared to other standard tracking methods. |
| first_indexed | 2024-03-12T00:41:02Z |
| format | Article |
| id | doaj.art-3827d107d00c48de9d1a2c246ef7e6d0 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:41:02Z |
| publishDate | 2013-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-3827d107d00c48de9d1a2c246ef7e6d02023-09-15T07:06:38ZengWileyIET Computer Vision1751-96321751-96402013-08-017424625710.1049/iet-cvi.2011.0223Adaptive earth movers distance‐based Bayesian multi‐target trackingPankaj Kumar0Anthony Dick1School of Mathematics and StatisticsUniversity of South AustraliaAdelaideSouth AustraliaAustraliaSchool of Computer ScienceUniversity of AdelaideAdelaideSouth AustraliaAustraliaThis study describes a complete system for multiple‐target tracking in image sequences. The target appearance is represented as a set of weighted clusters in colour space. This is in contrast to the more typical use of colour histograms to model target appearance. The use of clusters allows a more flexible and accurate representation of the target, which demonstrates the benefits for tracking. However, it also introduces a number of computational difficulties, as calculating and matching cluster signatures are both computationally intensive tasks. To overcome this, the authors introduce a new formulation of incremental medoid‐shift clustering that operates faster than mean shift in multi‐target tracking scenarios. This matching scheme is integrated into a Bayesian tracking framework. Particle filters, a special case of Bayesian filters where the state variables are non‐linear and non‐Gaussian, are used in this study. An adaptive model update procedure is proposed for the cluster signature representation to handle target changes with time. The model update procedure is demonstrated to work successfully on a synthetic dataset and then on real datasets. Successful tracking results are shown on public datasets. Both qualitative and quantitative evaluations have been carried out to demonstrate the improved performance of the proposed multi‐target tracking system. A higher tracking accuracy in long image sequences has been achieved compared to other standard tracking methods.https://doi.org/10.1049/iet-cvi.2011.0223image sequencestarget appearance representationweighted clusterscolour spacecolour histogramscluster signature matching |
| spellingShingle | Pankaj Kumar Anthony Dick Adaptive earth movers distance‐based Bayesian multi‐target tracking IET Computer Vision image sequences target appearance representation weighted clusters colour space colour histograms cluster signature matching |
| title | Adaptive earth movers distance‐based Bayesian multi‐target tracking |
| title_full | Adaptive earth movers distance‐based Bayesian multi‐target tracking |
| title_fullStr | Adaptive earth movers distance‐based Bayesian multi‐target tracking |
| title_full_unstemmed | Adaptive earth movers distance‐based Bayesian multi‐target tracking |
| title_short | Adaptive earth movers distance‐based Bayesian multi‐target tracking |
| title_sort | adaptive earth movers distance based bayesian multi target tracking |
| topic | image sequences target appearance representation weighted clusters colour space colour histograms cluster signature matching |
| url | https://doi.org/10.1049/iet-cvi.2011.0223 |
| work_keys_str_mv | AT pankajkumar adaptiveearthmoversdistancebasedbayesianmultitargettracking AT anthonydick adaptiveearthmoversdistancebasedbayesianmultitargettracking |