摘要
针对Harris角点检测精度和检测速度问题,利用现代图形处理器(GPU)对角点检测算法进行改进,提出一种基于GPU的快速亚像素Harris角点检测算法,该算法利用了GPU的并行处理能力和亚像素Harris角点检测算法的并行性特点。实验结果表明,对于分辨率为720×720的24bit视频图像,该算法能够实现实时的亚像素级Harris角点检测。
In order to increase precision and efficiency of Harris comer detection algorithm, this paper takes advantage of the modem Graphics Processing Unit(GPU) to improve Harris comer detection algorithm by parallelizing. A fast sub-pixel Harris comer detection algorithm is presented based on GPU. This fast algorithm combines the parallel characteristics of GPU with Harris comer algorithm. Experimental result shows that GPU can implement the real-time sub-pixel Harris comer detection for 24 bit 720×720 video images.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第12期213-215,共3页
Computer Engineering
关键词
亚像素
角点检测
图形处理器
sub-pixel
comer detection
Graphics Processing Unit(GPU)