OpenCV：norm-范数求解函数( 二 ) _2410

1-范数:║x║1=│x1│+│x2│+…+│xn│//标的目的量中的绝对值乞降
2-范数:║x║2=(│x1│2+│x2│2+…+│xn│2)^1/2 //欧几里得距离
∞-范数:║x║∞=max(│x1│,│x2│, … ,│xn│) //标的目的量中的max

4OpenCV：norm范数求解函数
三种格局：
①double norm(InputArray src1,
int normType=NORM_L2,
InputArray mask=noArray() )
②double norm(InputArray src1,
InputArray src2,
int normType=NORM_L2,
InputArray mask=noArray())
③double norm(const SparseMat& src, int normType)

5应用实例：用于评估相机标定的表里参质量
法式如下：
cout << "每幅图像的标定误差：" << l;
for (int i = 0; i<image_count; i++)
{
    vector<Point3f> tempPointSet = object_Points[i];
    /*object_Points是图像棋盘格角点宿世界坐标的容器，其是三通道的XYZ ，此中Z通道为0 。棋盘格以左上角为原点，方块大小是12mm和12mm*/
/*依据摄像机表里参数，对空间的三维点进行重投影计较；
tempPointSet为12mm*12mm的棋盘格标定板角点宿世界坐标，
image_points2是重投影后的图像像素角点坐标*/
projectPoints(tempPointSet,
rotation_vectors[i],
translation_vectors[i],
intrinsic_matrix,
distortion_coeffs,
image_points2);

/*图像亚像素角点坐标tempImagePoint */
/*image_points2和tempImagePoint进行误差计较，评估出其表里参的质量*/
    vector<Point2f> tempImagePoint = corners_Seq[i];

//界说双通道的Mat矩阵，每个点暗示两个数据，别离为棋盘格角点的x和y//
    Mat tempImagePointMat = Mat(1, tempImagePoint.size(), CV_32FC2);
    Mat image_points2Mat = Mat(1, image_points2.size(), CV_32FC2);
    for (int j = 0; j < tempImagePoint.size(); j++)
    {
        image_points2Mat.at<Vec2f>(0, j) = Vec2f(image_points2[j].x, image_points2[j].y); //两个通道赋值
        tempImagePointMat.at<Vec2f>(0, j) = Vec2f(tempImagePoint[j].x, tempImagePoint[j].y);
    }
    err = norm(image_points2Mat, tempImagePointMat, NORM_L2);//2范数
    total_err += err /= point_counts[i];
    cout << "第" << i + 1 << "幅图像的平均误差：" << err << "像素" << l;
}
cout << "总体平均误差：" << total_err / image_count << "像素" << l;
cout << "评价完当作！" << l;
【注】：OpenCV的norm函数是将两个通道分隔计较(X1-X2)^2的值，然后同一乞降，开根号；即2范数；

OpenCV：norm-范数求解函数( 二 )

猜你喜欢