摘要
提取房屋的边缘轮廓时,区域分割的不准确通常会导致提取出的轮廓出现内凹或外凸的不规整情况,需要进一步拟合。角点检测在轮廓的边缘形状提取中具有重要作用。传统的基于边界链码的角点检测是通过计算曲线的最大曲率点方式进行的。该方法求出的角点完全依赖于轮廓的曲率变化趋势,不对轮廓自身的凹凸具有修复性,因而无法排除因区域分割不准确带来的干扰角点,导致最终提取出的多边形不准确。针对此情况,提出一种基于最小外接矩形的直角多边形拟合算法。该算法利用最小外接矩形作为轮廓外界,计算待拟合轮廓与矩形外界之间的差值,并对差值设置适当阈值取舍角点,从而拟合出多边形的直角。所提方法无需通过轮廓曲率来计算角点即可得到紧紧包络目标轮廓的直角多边形,简单高效。
In the extraction of the edge of the housing,usually due to the segmentation of the region is not accurate,resulting in the extraction of the outline appear irregularities such as concave or convex parts,which needs to further fitting.Corner detection plays an important role in contour shape extraction.The traditional corner detection is based on the calculation of the maximum curvature point.This calculation method is completely dependent on the curvature variation of the profile,and can not be used for the repair of its irregularities.So it＇s difficult in removing some of useless corner points.In this paper,a new method based on the minimum external rectangle to fit its real shape was proposed.In detail,the minimum external rectangle is used as the outline,and the difference between the fitted contour and the outer rectangle is calculated.It sets the appropriate threshold value for the difference,then chooses the right point for the polygon according the threshold.Without needing to calculate the corner points by the curvature of the contour,we can get the right-angled polygon of the object contour,which is simple and efficient.
出处
《计算机科学》
CSCD
北大核心
2017年第6期294-297,305,共5页
Computer Science
关键词
坐标系转化
角点
内外链作差
多边形拟合
Transformation of coordinate system
Corner point
Difference between inner and outer contour
Polygon fitting
