从图像坐标转换为世界坐标

Question

I have homography matrix H which is 3x3. I have an image that only contains 0s and 1s to denote whether the pixel is occupied. I would like to take this image and transform it into world coordinates using H.

Is there an easy way to do this using cv2 in python? Otherwise, do I need to convert each pixel location using H?

EDIT:

Here's my code:

image = plt.imread('image.png')
obs = np.where(image > 0)
obs_map = np.vstack((obs[0], obs[1]))
obs_map = np.vstack((obs_map, np.ones(obs[0].shape[0])))
obs_map = np.dot(H, obs_map)
obs_map = np.dot(R, obs_map)
plt.scatter(obs_map[0, :], obs_map[1, :])
plt.show()

This seems to work but the scale seems off. What value do I need for z value?

H is

    1.1048200e-02   6.6958900e-04  -3.3295300e+00
   -1.5966000e-03   1.1632400e-02  -5.3951400e+00
    1.1190700e-04   1.3617400e-05   5.4276600e-01

and image consisting of 0s and 1s looks like this:

and my plot looks like this:

Answer 1

I think warpPerspective() might be for you.

Check it out:

OpenCV 2.4

OpenCV 3