据我所知,OpenCV使用RANSAC来解决findhomograph
的问题,并返回一些有用的参数,如homograph_mask
。但是,如果我只想估计2D转换,这意味着一个仿射矩阵,有没有办法使用findHomography
使用RANSAC并返回该掩码的相同方法逻辑?
答案 0 :(得分:5)
estimateRigidTransform在内部使用RANSAC,虽然参数目前是固定的 - 请参阅此处的代码 - https://github.com/opencv/opencv/blob/master/modules/video/src/lkpyramid.cpp
public class BasicDesign extends AppCompatActivity
implements det.OnViewChangedListener {
//...
// Implement the interface in the activity.
@Override
public void onViewChanged(String value) {
// Use the retrieved value, e.g. save this to a local
// that you can show when you click your button.
}
}
答案 1 :(得分:2)
您可以直接使用estimateAffinePartial2D: https://docs.opencv.org/4.0.0/d9/d0c/group__calib3d.html#gad767faff73e9cbd8b9d92b955b50062d
cv::Mat cv::estimateAffinePartial2D (
InputArray from,
InputArray to,
OutputArray inliers = noArray(),
int method = RANSAC,
double ransacReprojThreshold = 3,
size_t maxIters = 2000,
double confidence = 0.99,
size_t refineIters = 10
)
例如:
src_pts = np.float32([pic1.key_points[m.queryIdx].pt for m in matches]).reshape(-1, 1, 2)
dst_pts = np.float32([pic2.key_points[m.trainIdx].pt for m in matches]).reshape(-1, 1, 2)
# Find the transformation between points, standard RANSAC
transformation_matrix, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
# Compute a rigid transformation (without depth, only scale + rotation + translation) and RANSAC
transformation_rigid_matrix, rigid_mask = cv2.estimateAffinePartial2D(src_pts, dst_pts)