摘要
提出了一种鲁棒的快速角点检测算法,以解决现有基于点到弦距离累加的角点检测算法存在的缺陷,即角点定位低、算法时间复杂度高等问题。该算法结合了‘单尺度’和‘多尺度’的优势,首先在‘单尺度’下获取候选角点集合,保留了邻近角点,并使得后续计算量大大降低,然后在‘多尺度’下计算候选角点的特征值,使之有效地去除伪角点。实验表明,所提算法的时间复杂度降低了,并且保持了算法的鲁棒性,角点定位精度也得到了提升。
To solve the disadvantages of the corner detector based on chord-to-point distance accumulation,low location accuracy,high detector time complexity and so on,a fast robust corner detector was proposed.This detector combines the advantages of ‘single scale＇ and ‘multi-scale＇.Firstly,it obtains the candidate corner under single scale,keeping the adjacent corner,and reducing following calculation greatly.Then,it calculates the eigenvalues of the candidate comers under multi-scale,eliminates false corners effectively.The experiment result shows that the detector reduces time complexity,keeps the robustness of the detector and the accuracy of corner location is also improved.
出处
《计算机科学》
CSCD
北大核心
2014年第4期306-308,313,共4页
Computer Science
基金
国家自然科学基金项目(61070043)
"十二五"国家科技支撑计划(2012BAD10B01)
浙江省自然科学基金(LQ12F03011)资助
关键词
点到弦距离累加
快速
角点检测
角点定位
时间复杂度
Chord-to-point distance accumulation
Fast
Corner detection
Corner location
Time complexity
