一种自适应Harris角点检测算法

摘要

When the target detection result is not ideal,Harris corner detection algorithm based on self-adapting non-maximal suppression strategy is proposed;Ranked local maximum of corner response function and a suppression radius for each corner is set up,corners are extracted through the suppression radius continuously decreasing.The problem of corner clustering and the difficulty of threshold selection is effectively avoided.The experimental result shows that this method is superior to the traditional harris corner algorithm,and can be used in practical.%针对传统算法检测效果不理想的问题，提出了一种基于自适应非最大抑制策略的Harris角点检测算法；通过设置抑制半径与角点响应函数的局部最大值关联，减小抑制半径获取角点。算法有效解决了阈值选取和“聚簇”的问题。实验表明，该算法检测出的角点均匀分布，能很好地适应特征匹配等实际应用。