Real-time Geometric Calibration on graphics processing unit with CUDA

Geometric Calibration of digital camera and video is useful for experimental work, such as video surveillance, virtual endoscope etc. High-performance computing holds the key to making biologically relevant calculations tractable without compromise. In this paper we present a new approach to high performance GC algorithm on graphics processing units. Using modern graphics processing units for high performance computing is facilitated by their enhanced programmability and motivated by their attractive price/performance ratio and incredible growth in speed. To derive an efficient mapping onto this type of architecture, we have used the Compute Unified Device Architecture (CUDA) to design and implement a new parallel algorithm. Experiments show the significant runtime savings on computer graphics card, which achieve real-time (30 fps) calibration of High Definition images with 1920 × 1080 resolutions.