적당한 선으로 채우기 fitLine

fitLine

Fits a line to a 2D or 3D point set.

C++: void fitLine(InputArray points, OutputArray line, int distType, double param, double reps, double aeps)

Python: cv2.fitLine(points, distType, param, reps, aeps[, line]) → line

C: void cvFitLine(const CvArr* points, int dist_type, double param, double reps, double aeps, float* line)

Python: cv.FitLine(points, dist_type, param, reps, aeps) → line

Parameters:

points – Input vector of 2D or 3D points, stored in std::vector<> or Mat. line – Output line parameters. In case of 2D fitting, it should be a vector of 4 elements (like Vec4f) - (vx, vy,x0, y0), where (vx, vy) is a normalized vector collinear to the line and (x0, y0) is a point on the line. In case of 3D fitting, it should be a vector of 6 elements (like Vec6f) - (vx, vy, vz, x0, y0, z0), where (vx, vy, vz) is a normalized vector collinear to the line and (x0, y0, z0) is a point on the line. distType – Distance used by the M-estimator (see the discussion below). param – Numerical parameter ( C ) for some types of distances. If it is 0, an optimal value is chosen. reps – Sufficient accuracy for the radius (distance between the coordinate origin and the line). aeps – Sufficient accuracy for the angle. 0.01 would be a good default value for reps and aeps.

The function fitLine fits a line to a 2D or 3D point set by minimizing  where  is a distance between the  point, the line and  is a distance function, one of the following:

• distType=CV_DIST_L2

  

• distType=CV_DIST_L1

  

• distType=CV_DIST_L12

  

• distType=CV_DIST_FAIR

  

• distType=CV_DIST_WELSCH

  

• distType=CV_DIST_HUBER

  

The algorithm is based on the M-estimator ( http://en.wikipedia.org/wiki/M-estimator ) technique that iteratively fits the line using the weighted least-squares algorithm. After each iteration the weights  are adjusted to be inversely proportional to