GPU implementation of phase-based stereo correspondence and its application
- Resource Type
- Conference
- Authors
- Miura, Mamoru; Fudano, Kinya; Ito, Koichi; Aoki, Takafumi; Takizawa, Hiroyuki; Kobayashi, Hiroaki
- Source
- 2012 19th IEEE International Conference on Image Processing Image Processing (ICIP), 2012 19th IEEE International Conference on. :1697-1700 Sep, 2012
- Subject
- Signal Processing and Analysis
Components, Circuits, Devices and Systems
Communication, Networking and Broadcast Technologies
Computing and Processing
Graphics processing units
Stereo vision
Kernel
Cameras
Real-time systems
Face
Correlation
stereo vision
stereo correspondence
phaseonly correlation
GPU
real-time 3D measurement
- Language
- ISSN
- 1522-4880
2381-8549
This paper proposes a Graphics Processing Unit (GPU) implementation of the stereo correspondence matching using Phase-Only Correlation (POC). The use of high-accuracy stereo correspondence matching based on POC makes it possible to measure accurate 3D shape of the object using stereo vision, while the drawback of POC-based approach is its high computational cost. Addressing this problem, we propose a GPU implementation of POC-based correspondence matching. Through a set of experiments using a variety of GPUs, we demonstrate that the proposed implementation is high-speed and high-efficiency compared with the CPU implementation. We also apply the proposed approach to a real-time 3D measurement system.