search

etiennedub / pyk4a

Python 3 wrapper for Azure-Kinect-Sensor-SDK
MIT License
287 stars 81 forks source link

why the coordinate of the depth camera is the opposite of the RGB? #161

Closed hlyf-xs closed 2 years ago

hlyf-xs commented 2 years ago

I confused that the coordinate of the depth camera is the opposite of the RGB, for example, the depth value of the coordinate color[x][y] is depth[y][x].

rajkundu commented 2 years ago

I think it could just be a coincidence. In general, to access the values of pixel (x, y) in an image, use image[y][x] (or, equivalently, image[y,x]). If you print out color.shape (assuming color is a numpy array), you should see that its shape is (height, width, 4). So, to access each of the 4 B/G/R/A values at pixel (x, y) of the color image, usecolor[y][x] or color[y,x].

To get the depth value at that pixel, you must first transform the depth image into the frame of the color image. To do this, pyk4a conveniently provides capture.transformed_depth, allowing you to get the raw depth data at color pixel (x, y) using the expression capture.transformed_depth[y,x]. However, you will need to use other transformations/functions to get the 3D X, Y, and Z coordinates of color pixel (x, y).