一种新的快速鲁棒性角点检测算法

A New Fast and Robust Corner Detection Algorithm

对现有的角点检测算法进行了综述,着重分析了SUSAN算法和MIC算法的实现原理以及检测性能的优劣,提出了一种基于像素亮度变化的快速角点检测算法。对模拟图像和真实图像的角点进行了实验,并与目前应用比较广泛的Harris、MIC以及SUSAN角点检测子进行了比较。实验结果和数据分析表明了算法在计算效率、定位精度和鲁棒性等到方面具有良好性能。

This paper first presents a thorough survey on recent corner detection algorithm. It makes a deeply research on the principle of SUSAN and MIC algorithm, and analyses their performance respectively. It suggests a fast and robust corner detector based on pixel intensity change. The new algorithm, and other popular corner detectors, are evaluated and compared on the basis of their performance using simulative image and real image. It finds that the algorithm performs better than other algorithms on consistency, accuracy and speed.