An optimized high-speed high-accuracy image matching system based on FPGA

Accuracy and real-time performance are the main factors that determine the practical value of image matching system. To implement a high-speed high-accuracy low-source consumption image matching system, the improved formula of gray-correlation-based algorithm is selected, a pipeline-based highly-parallel structure is carefully designed and many optimization methods are adopted. Experimental results on the Altera Stratix II EP2S130F780 platform show that the system is much faster than other similar systems while retaining the accuracy no less than 10−5 and supporting a maximum of 600*600 reference image.