基于可编程GPU的多源图像融合

针对可编程GPU模型,提出了基于CPU-GPU的并行边缘强度加权融合算法,利用CPU和GPU协同工作模式达到图像融合的目的,其中CPU负责串行任务,而GPU负责并行任务。实验结果表明,并行边缘强度加权融合算法得到的融合图像有着较好的视觉效果,信息熵和QAB/F这两个评价指标均高于文中对比算法的相应指标;从运行时间上分析,基于CPU-GPU的融合方法所需要的运行时间远低于基于CPU方法所需要的运行时间,并且图像尺寸越大,加速比越高。

Multi-source Image Fusion Based on Programmable GPU

Recently,Programmable Graphics Processing Unit（PGPU）has been greatly improved,and it is widely used in various fields .In this paper ,a novel fusion algorithm which is based on weight of edge in-tensity based on PGPU is proposed .The CPU is serial processing ,and GPU is responsible for parallel pro-cessing .The essay researches on selecting GPU memories and dividing blocks and threads of GPU kernel functions.Experiment shows that the proposed algorithm has faster calculation velocity and higher evalua -tion accuracy,and the entropy and QAB/F parameters are superior in performance to algorithms com-pared.Meanwhile,the speed based on CPU-GPU is faster than that of the CPU-based implementation .