Loading...
Please wait, while we are loading the content...
Simultaneous Real-time 3D Visual Tracking of Multiple Objects using a Stream Processor
| Content Provider | Semantic Scholar |
|---|---|
| Author | Lozano, Oscar Mateo Otsuka, Kazuhiro |
| Copyright Year | 2007 |
| Abstract | In this work, we present an implementation of a real-time visual tracker of the position and 3D pose of objects in video sequences. The use of Stream Processors for the computation and an efficient Sparse-Template-based particle filtering allows us to achieve real-timeness even with tracking multiple objects simultaneously in high-resolution video frames. Stream processing is a relatively new computing paradigm that allows parallel computing at never-before-seen efficiency. Using a GPU (Graphics Processing Unit, a consumer-grade stream processor) and the NVIDIA CUDA technology, we are capable of achieving performance improvements as large as 10x compared to a similar CPU-only tracker. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.kecl.ntt.co.jp/people/otsuka.kazuhiro/MIRU2007_oscar_paper.pdf |
| Alternate Webpage(s) | http://www.brl.ntt.co.jp/people/otsuka/MIRU2007_oscar_paper.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |