can anybody help me with the following problem using Python?
I have point cloud matrix got from a virtual camera, its dimension is 320x240x3, which indicates x,y,z coordinates of each point (points in camera view).
All values range from negative to positive. How can I convert this point cloud matrix to a 320x240x1 depth map which stores the positive depth value of each pixel? Thanks in advance.
Well, if you knew how to convert depth image to point map (that is your point cloud matrix), I guess you'll know the other way round.
Given the associated camera intrinsics, using pinhole camera model, we can recover the point map using the following python code:
import numpy as np
from imageio import imread, imwrite
# read depth image in
img = imread('depth.png')
img = np.asarray(img)
# camera intrinsics, for demonstration purposes only. change to your own.
fx, fy = 570.0, 570.0
cx, cy = 320, 240
# suppose your depth image is scaled by a factor of 1000
z = img.astype(float) / 1000.0
# convert depth image of shape to point map
# here we assume depth image is of shape (480, 640)
px, py = np.meshgrid(np.arange(640), np.arange(480)) # pixel_x, pixel_y
px, py = px.astype(float), py.astype(float)
x = ((px - cx) / fx) * z
y = ((py - cy) / fy) * z
pmap = np.concatenate([i[..., np.newaxis] for i in (x, y, z)], axis=-1)
Now back to your question.
Assuming your point map is in camera coordinate system (you haven't translated or rotated pmap), to convert point map to depth image we shall do:
# convert point map to depth image
# that is, we are only using the points' z coordinates values
depth = (pmap[:, :, 2] * 1000).astype(np.uint16)
# now we can save the depth image to disk
imwrite('output.png', depth)
Hope it helps :)