Title :
Real time stereo vision using exponential step cost aggregation on GPU
Author :
Yu, Wei ; Chen, Tsuhan ; Hoe, James C.
Author_Institution :
Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
In this paper, we propose a local cost aggregation approach for real time stereo vision on a graphics processing unit (GPU). Recent research shows that local approaches based on carefully designed cost aggregation strategies can outperform many global approaches. Among those local aggregation approaches, adaptive-weight window produces the best quality disparity map under real-time constraint, but it is slower than other local approaches. We propose a very fast adaptive-weight aggregation method based on exponential step information propagation. The basic idea is to propagate information from long distance pixels within a few iterations. We also discuss important techniques of efficient implementation on GPU platform, which result in 10.5Ã speed up than a straightforward implementation. Compared to existing real time adaptive-weight approach, our technique reduces the computation time by more than half at improved accuracy. Detailed experimental results show that our technique is Pareto-optimal among existing real time or near real time stereo algorithms in the accuracy-speed trade-off space.
Keywords :
computer graphic equipment; real-time systems; stereo image processing; GPU; adaptive-weight aggregation; exponential step cost aggregation; exponential step information propagation; graphics processing unit; realtime stereo vision; Belief propagation; Central Processing Unit; Computer vision; Constraint optimization; Cost function; Dynamic programming; Graphics; Parallel processing; Real time systems; Stereo vision; GPU; adaptive-weight; real time stereo;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5413693