Paper Info
Title
Simultaneous and fast 3D tracking of multiple faces in video by GPU-based stream processing
Abstract
ABSTRACT In this work, we implement a real-time visual tracker that tar- gets the position and 3D pose of objects in video sequences, specifically faces. Using Stream Processors for performing the computations,as well as efficient Sparse-Template-based particle filtering allows us to achieve real-time processing even when tracking multiple objects simultaneously in high- resolution video frames. Stream processing is a relatively new,computing,paradigm,that permits the expression and execution of data-parallel algorithms with great efficiency and minimum,effort. Using a GPU (Graphics Processing Unit, a consumer-grade Stream Processor) and the NVIDIA CUDA, technology, we can achieve real-time performance even when tracking multiple objects in high-quality videos. Index Terms— stream processing, GPGPU, particle fil-
Year
DOI
Venue
2008
10.1109/ICASSP.2008.4517709
Las Vegas, NV
Keywords
Field
DocType
computer graphics,face recognition,image resolution,image sequences,particle filtering (numerical methods),tracking,video streaming,GPU-based stream processing,data-parallel algorithms,graphics processing unit,multiple objects tracking,objects 3D pose,real-time visual tracker,sparse-template-based particle filtering,stream processors,video frames,video sequences,GPGPU,particle filtering,real-time systems,stream processing,video tracking
Computer vision,Computer science,CUDA,Particle filter,Image processing,Real-time computing,Video tracking,Artificial intelligence,General-purpose computing on graphics processing units,Graphics processing unit,Stream processing,Computer graphics
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4244-1484-0
978-1-4244-1484-0
13
PageRank 
References 
Authors
1.01
4
2
Name
Order
Citations
PageRank
Oscar Mateo Lozano1131.01
Kazuhiro Otsuka261954.15