Color and motion-based particle filter target tracking in a network of overlapping cameras with multi-threading and GPGPU
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Universidad de Guanajuato
2013
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876487230377164800 |
|---|---|
| author | Francisco Madrigal |
| author_facet | Francisco Madrigal |
| contents | Color and motion-based particle filter target tracking in a network of overlapping cameras with multi-threading and GPGPU Francisco Madrigal Hayet Jean-Bernard Multidisciplinarias (Ciencias Sociales) multi GPGPU threading view tracking Particle filter This paper describes an efficient implementation of multiple-target multiple-view tracking in video-surveillance sequences. It takes advantage of the capabilities of multiple core Central Processing Units (CPUs) and of graphical processing units under the Compute Unifie Device Arquitecture (CUDA) framework. The principle of our algorithm is 1) in each video sequence, to perform tracking on all persons to track by independent particle filters and 2) to fuse the tracking results of all sequences. Particle filters belong to the category of recursive Bayesian filters. They update a Monte-Carlo representation of the posterior distribution over the target position and velocity. For this purpose, they combine a probabilistic motion model, i.e. prior knowledge about how targets move (e.g. constant velocity) and a likelihood model associated to the observations on targets. At this first level of single video sequences, the multi-threading library Threading Buildings Blocks (TBB) has been used to parallelize the processing of the pertarget independent particle filters. Afterwards at the higher level, we rely on General Purpose Programming on Graphical Processing Units (generally termed as GPGPU) through CUDA in order to fuse target-tracking data collected on multiple video sequences, by solving the data association problem. Tracking results are presented on various challenging tracking datasets. 2013 artículo científico 0188-6266 https://www.redalyc.org/articulo.oa?id=41626112002 en http://www.redalyc.org/revista.oa?id=416 Acta Universitaria application/pdf Universidad de Guanajuato Acta Universitaria (México) Num.1 Vol.23 |
| format | Artículo científico |
| id | redalyc_41626112002 |
| institution | Redalyc |
| language | en |
| publishDate | 2013 |
| publisher | Universidad de Guanajuato |
| spellingShingle | Color and motion-based particle filter target tracking in a network of overlapping cameras with multi-threading and GPGPU Francisco Madrigal Multidisciplinarias (Ciencias Sociales) multi GPGPU threading view tracking Particle filter Color and motion-based particle filter target tracking in a network of overlapping cameras with multi-threading and GPGPU Francisco Madrigal Hayet Jean-Bernard Multidisciplinarias (Ciencias Sociales) multi GPGPU threading view tracking Particle filter This paper describes an efficient implementation of multiple-target multiple-view tracking in video-surveillance sequences. It takes advantage of the capabilities of multiple core Central Processing Units (CPUs) and of graphical processing units under the Compute Unifie Device Arquitecture (CUDA) framework. The principle of our algorithm is 1) in each video sequence, to perform tracking on all persons to track by independent particle filters and 2) to fuse the tracking results of all sequences. Particle filters belong to the category of recursive Bayesian filters. They update a Monte-Carlo representation of the posterior distribution over the target position and velocity. For this purpose, they combine a probabilistic motion model, i.e. prior knowledge about how targets move (e.g. constant velocity) and a likelihood model associated to the observations on targets. At this first level of single video sequences, the multi-threading library Threading Buildings Blocks (TBB) has been used to parallelize the processing of the pertarget independent particle filters. Afterwards at the higher level, we rely on General Purpose Programming on Graphical Processing Units (generally termed as GPGPU) through CUDA in order to fuse target-tracking data collected on multiple video sequences, by solving the data association problem. Tracking results are presented on various challenging tracking datasets. 2013 artículo científico 0188-6266 https://www.redalyc.org/articulo.oa?id=41626112002 en http://www.redalyc.org/revista.oa?id=416 Acta Universitaria application/pdf Universidad de Guanajuato Acta Universitaria (México) Num.1 Vol.23 |
| title | Color and motion-based particle filter target tracking in a network of overlapping cameras with multi-threading and GPGPU |
| topic | Multidisciplinarias (Ciencias Sociales) multi GPGPU threading view tracking Particle filter |
| url | https://www.redalyc.org/articulo.oa?id=41626112002 |