BROWSE
Detail
Conference Paper
Optimized Multi-Threading for Fast Depth-Map Estimation
Cited - time in 
Share 
Share
- Authors
- Chil-Suk Cho, Ji-In Jun, Hyon-Gon Choo, Jong-Il Park
- Issue Date
- 2012-06
- Citation
- International Conference on 3D Systems and Applications (3DSA) 2012, pp.1-4
- Language
- English
- Type
- Conference Paper
- Abstract
- A depth map can be obtained by projecting/capturing patterns of stripes using a projector-camera system and analyzing the geometric relationship between the projected patterns and the captured patterns. This is usually called structured light technique. In this paper, we propose a new multithreading scheme for accelerating a conventional structured light technique. On CPUs and GPUs, multithreading can be implemented by using OpenMP and CUDA, respectively. However, the problem is that their performance changes according to the computational conditions of partial processes of a structured light technique. In other words, OpenMP (using multiple CPUs) outperformed CUDA (using multiple GPUs) in partial processes such as pattern decoding and depth estimation. In contrast, CUDA outperformed OpenMP in partial processes such as rectification and pattern segmentation. Therefore, we carefully analyze the computational conditions where each outperforms the other and do use the better one in the related conditions. As a result, the proposed method can estimate a depth map in a speed of over 25 fps on 1280 x 800 images.
- KSP Keywords
- Depth Map, Depth estimation, MAP estimation, Multiple GPUs, Performance changes, Projector-camera System, Structured light, multi-threading, pattern decoding