Real time motion estimation using a neural architecture implemented on GPUs

This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network a...

Full description

Saved in:
Bibliographic Details
Published in:Journal of real-time image processing 2016-04, Vol.11 (4), p.731-749
Main Authors: Garcia-Rodriguez, Jose, Orts-Escolano, Sergio, Angelopoulou, Anastassia, Psarrou, Alexandra, Azorin-Lopez, Jorge, Garcia-Chamizo, Juan Manuel
Format: Article
Language:English
Subjects:
Agents (artificial intelligence)
Algorithms
Computer architecture
Computer Graphics
Computer Science
Computer vision
Formability
Graphics processing units
Image Processing and Computer Vision
Image segmentation
Motion simulation
Moving object recognition
Multimedia Information Systems
Neural networks
Pattern Recognition
Representations
Signal,Image and Speech Processing
Special Issue Paper
Tracking
Video compression
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network architecture allows for the simultaneous estimation of global and local motion and the representation of deformable objects. This architecture also avoids the problem of finding corresponding features while tracking moving objects. Due to the parallel nature of neural networks, the architecture has been implemented on GPUs that allows the system to meet a set of requirements such as: time constraints management, robustness, high processing speed and re-configurability. Experiments are presented that demonstrate the validity of our architecture to solve problems of mobile agents tracking and motion analysis.
ISSN:1861-8200
1861-8219
DOI:10.1007/s11554-014-0417-y