Efficient initialization schemes for real-time 3D camera tracking using image sequences

2011 ◽  
Author(s):  
Fakhreddine Ababsa ◽  
Imane Zendjebil ◽  
Jean-Yves Didier ◽  
M. Mallem
Keyword(s):  
Real Time ◽  
Image Sequences ◽  
Camera Tracking ◽  
3D Camera

Real-time depth camera tracking with geometrically stable weight algorithm

2017 ◽  
Vol 56 (3) ◽  
pp. 033104 ◽  
Author(s):  
Xingyin Fu ◽  
Feng Zhu ◽  
Feng Qi ◽  
Mingming Wang
Keyword(s):  
Real Time ◽  
Depth Camera ◽  
Camera Tracking

Direct estimation of articulatory kinematics from real-time magnetic resonance image sequences

2011 ◽  
Author(s):  
Michael Proctor ◽  
Adam Lammert ◽  
Athanasios Katsamanis ◽  
Louis Goldstein ◽  
Christina Hagedorn ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Magnetic Resonance Image ◽  
Image Sequences ◽  
Direct Estimation

scholarly journals On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences

2011 ◽  
Vol 2011 ◽  
pp. 1-15 ◽  
Author(s):  
Jeyarajan Thiyagalingam ◽  
Daniel Goodman ◽  
Julia A. Schnabel ◽  
Anne Trefethen ◽  
Vicente Grau
Keyword(s):  
Motion Estimation ◽  
Real Time ◽  
Three Dimensional ◽  
Basic Research ◽  
Estimation Algorithm ◽  
Image Sequences ◽  
Multicore Architectures ◽  
Gpu Architectures ◽  
Access Patterns ◽  
Performance Gains

Images are ubiquitous in biomedical applications from basic research to clinical practice. With the rapid increase in resolution, dimensionality of the images and the need for real-time performance in many applications, computational requirements demand proper exploitation of multicore architectures. Towards this, GPU-specific implementations of image analysis algorithms are particularly promising. In this paper, we investigate the mapping of an enhanced motion estimation algorithm to novel GPU-specific architectures, the resulting challenges and benefits therein. Using a database of three-dimensional image sequences, we show that the mapping leads to substantial performance gains, up to a factor of 60, and can provide near-real-time experience. We also show how architectural peculiarities of these devices can be best exploited in the benefit of algorithms, most specifically for addressing the challenges related to their access patterns and different memory configurations. Finally, we evaluate the performance of the algorithm on three different GPU architectures and perform a comprehensive analysis of the results.

Sign in / Sign up

Export Citation Format

Share Document