A hybrid particle swarm optimization with cooperative method for multi-object tracking
In the fields of computer vision, multiple object tracking is an active research area. It is a challenging problem mainly due to the frequent occlusions and interactions that happen between the multiple targets. We formulate the multiple interaction problem as an optimization problem and explore Par...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/96729 http://hdl.handle.net/10220/12005 |
| _version_ | 1824455792999268352 |
|---|---|
| author | Zhang, Zheng Seah, Hock Soon Sun, Jixiang |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Zhang, Zheng Seah, Hock Soon Sun, Jixiang |
| author_sort | Zhang, Zheng |
| collection | NTU |
| description | In the fields of computer vision, multiple object tracking is an active research area. It is a challenging problem mainly due to the frequent occlusions and interactions that happen between the multiple targets. We formulate the multiple interaction problem as an optimization problem and explore Particle Swarm Optimization (PSO) algorithm for the optimal solution. To tackle the problem of premature convergence, we present a new hybrid PSO that incorporates a differential evolution mutation operation with a Gaussian based PSO. Furthermore, by exploiting the specific structure of multiple object interactions, we introduce a cooperative strategy into the proposed PSO for more efficient searching and for conquering the curse of dimensionality. With patch-based observation models, our method can robustly handle significant occlusions and interactions. |
| first_indexed | 2025-02-19T03:43:51Z |
| format | Conference Paper |
| id | ntu-10356/96729 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:43:51Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/967292020-05-28T07:17:54Z A hybrid particle swarm optimization with cooperative method for multi-object tracking Zhang, Zheng Seah, Hock Soon Sun, Jixiang School of Computer Engineering IEEE Congress on Evolutionary Computation (2012 : Brisbane, Australia) DRNTU::Engineering::Computer science and engineering In the fields of computer vision, multiple object tracking is an active research area. It is a challenging problem mainly due to the frequent occlusions and interactions that happen between the multiple targets. We formulate the multiple interaction problem as an optimization problem and explore Particle Swarm Optimization (PSO) algorithm for the optimal solution. To tackle the problem of premature convergence, we present a new hybrid PSO that incorporates a differential evolution mutation operation with a Gaussian based PSO. Furthermore, by exploiting the specific structure of multiple object interactions, we introduce a cooperative strategy into the proposed PSO for more efficient searching and for conquering the curse of dimensionality. With patch-based observation models, our method can robustly handle significant occlusions and interactions. 2013-07-23T02:06:29Z 2019-12-06T19:34:20Z 2013-07-23T02:06:29Z 2019-12-06T19:34:20Z 2012 2012 Conference Paper Zhang, Z., Seah, H. S., & Sun, J. (2012). A hybrid Particle Swarm Optimization with cooperative method for multi-object tracking. 2012 IEEE Congress on Evolutionary Computation (CEC). https://hdl.handle.net/10356/96729 http://hdl.handle.net/10220/12005 10.1109/CEC.2012.6256414 en © 2012 IEEE. |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Zhang, Zheng Seah, Hock Soon Sun, Jixiang A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title | A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title_full | A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title_fullStr | A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title_full_unstemmed | A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title_short | A hybrid particle swarm optimization with cooperative method for multi-object tracking |
| title_sort | hybrid particle swarm optimization with cooperative method for multi object tracking |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/96729 http://hdl.handle.net/10220/12005 |
| work_keys_str_mv | AT zhangzheng ahybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking AT seahhocksoon ahybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking AT sunjixiang ahybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking AT zhangzheng hybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking AT seahhocksoon hybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking AT sunjixiang hybridparticleswarmoptimizationwithcooperativemethodformultiobjecttracking |