Parallel algorithm implementation for multi‐object tracking and surveillance
A recently developed sparse representation algorithm, has been proved to be useful for multi‐object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descript...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-04-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2015.0115 |
| _version_ | 1797684933289836544 |
|---|---|
| author | Mohamed Elbahri Nasreddine Taleb Kidiyo Kpalma Joseph Ronsin |
| author_facet | Mohamed Elbahri Nasreddine Taleb Kidiyo Kpalma Joseph Ronsin |
| author_sort | Mohamed Elbahri |
| collection | DOAJ |
| description | A recently developed sparse representation algorithm, has been proved to be useful for multi‐object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descriptor containing its appearance features and its position feature. Any detected object is classified and indexed according to the sparse solution obtained by an orthogonal matching pursuit (OMP) algorithm. For a real‐time tracking, the visual information needs to be processed very fast without reducing the results accuracy. However, both the large size of the descriptor and the growth of the dictionary after each detection, slow down the system process. In this work, a novel accelerating OMP algorithm implementation on a graphics processing unit is proposed. Experimental results demonstrate the efficiency of the parallel implementation of the used algorithm by significantly reducing the computation time. |
| first_indexed | 2024-03-12T00:36:59Z |
| format | Article |
| id | doaj.art-36b9c7e5816c43499b4bfc220165d882 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:36:59Z |
| publishDate | 2016-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-36b9c7e5816c43499b4bfc220165d8822023-09-15T09:27:05ZengWileyIET Computer Vision1751-96321751-96402016-04-0110320221110.1049/iet-cvi.2015.0115Parallel algorithm implementation for multi‐object tracking and surveillanceMohamed Elbahri0Nasreddine Taleb1Kidiyo Kpalma2Joseph Ronsin3Department of Computer ScienceDjillali Liabes UniversitySidi Bel‐AbbesAlgeriaRCAM LaboratoryDepartment of ElectronicsDjillali Liabes UniversitySidi Bel‐AbbesAlgeriaDépartement Image et AutomatiqueUEB INSA IETR35708RennesFranceDépartement Image et AutomatiqueUEB INSA IETR35708RennesFranceA recently developed sparse representation algorithm, has been proved to be useful for multi‐object tracking and this study is a proposal for developing its parallelisation. An online dictionary learning is used for object recognition. After detection, each moving object is represented by a descriptor containing its appearance features and its position feature. Any detected object is classified and indexed according to the sparse solution obtained by an orthogonal matching pursuit (OMP) algorithm. For a real‐time tracking, the visual information needs to be processed very fast without reducing the results accuracy. However, both the large size of the descriptor and the growth of the dictionary after each detection, slow down the system process. In this work, a novel accelerating OMP algorithm implementation on a graphics processing unit is proposed. Experimental results demonstrate the efficiency of the parallel implementation of the used algorithm by significantly reducing the computation time.https://doi.org/10.1049/iet-cvi.2015.0115parallel algorithmmultiobject trackingmultiobject surveillancesparse representation algorithmonline dictionary learningobject recognition |
| spellingShingle | Mohamed Elbahri Nasreddine Taleb Kidiyo Kpalma Joseph Ronsin Parallel algorithm implementation for multi‐object tracking and surveillance IET Computer Vision parallel algorithm multiobject tracking multiobject surveillance sparse representation algorithm online dictionary learning object recognition |
| title | Parallel algorithm implementation for multi‐object tracking and surveillance |
| title_full | Parallel algorithm implementation for multi‐object tracking and surveillance |
| title_fullStr | Parallel algorithm implementation for multi‐object tracking and surveillance |
| title_full_unstemmed | Parallel algorithm implementation for multi‐object tracking and surveillance |
| title_short | Parallel algorithm implementation for multi‐object tracking and surveillance |
| title_sort | parallel algorithm implementation for multi object tracking and surveillance |
| topic | parallel algorithm multiobject tracking multiobject surveillance sparse representation algorithm online dictionary learning object recognition |
| url | https://doi.org/10.1049/iet-cvi.2015.0115 |
| work_keys_str_mv | AT mohamedelbahri parallelalgorithmimplementationformultiobjecttrackingandsurveillance AT nasreddinetaleb parallelalgorithmimplementationformultiobjecttrackingandsurveillance AT kidiyokpalma parallelalgorithmimplementationformultiobjecttrackingandsurveillance AT josephronsin parallelalgorithmimplementationformultiobjecttrackingandsurveillance |