Belief Propagation on the GPU for Stereo Vision

Authors:
Alan Brunton;Chang Shu;Gerhard Roth
Affiliations:
University of Ottawa, Canada;National Research Council of Canada;National Research Council of Canada
Venue:
CRV '06 Proceedings of the The 3rd Canadian Conference on Computer and Robot Vision
Year:
2006

Citing 0
Cited 8

Massive parallel LDPC decoding on GPU

Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming
Belief Propagation Implementation Using CUDA on an NVIDIA GTX 280

AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Optimizing and auto-tuning belief propagation on the GPU

LCPC'10 Proceedings of the 23rd international conference on Languages and compilers for parallel computing
Efficient stereo and optical flow with robust similarity measures

DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Parallelization of Belief Propagation on Cell Processors for Stereo Vision

ACM Transactions on Embedded Computing Systems (TECS)
Detecting, segmenting and tracking unknown objects using multi-label MRF inference

Computer Vision and Image Understanding
Racking focus and tracking focus on live video streams: a stereo solution

The Visual Computer: International Journal of Computer Graphics
Parking assistance using dense motion-stereo

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.