一种快速自适应的Harris角点检测方法研究

Harris角点检测算法在图像处理中使用非常广泛,有着较高检测率,但算法运算量比较大,实时性不高.同时,该算法无法设置通用阈值处理不同图像.针对这些问题,提出一种快速自适应Harris角点检测算法.该算法先使用Fast算法,对图像进行预筛选,再使用Harris算法,并构造自适应阈值.实验结果表明,该算法可以有效克服阈值选择不当造成的角点冗余或丢失,并可大幅减少运算量.

A study of fast adaptive Harris corner detection method

Harris corner detection algorithm is widely used in image processing. It has a high detection rate, but it need much time to calculate. At the same time, the algorithm cannot set the a universal threshold. To solve these problems, this paper proposes a fast adaptive corner detection algorithm based on the Harris. The algorithm uses Fast algorithms for image pre-screening, and then uses the Harris algorithm with the constructed adaptive threshold. Experimental results show that the algorithm can effectively overcome corner redundant or missing caused by the improper setting threshold, and improve efficiency.