Getting uint16 info over rtsp using cv2.videocapture

Hello, I managed to get a grayscale image of (480,640) through the code below.

cap_depth = cv2.VideoCapture("rtsp://admin:admin@", cv2.CAP_GSTREAMER)
    ret2, frame_depth =
    cv2.namedWindow('kinova_depth', cv2.WINDOW_AUTOSIZE)
    cv2.setMouseCallback('kinova_depth', mouse_callback)
    if cv2.waitKey(20) & 0xFF == ord('q'):

However, the output image was in uint8 format ranging from 0 to 255, and accurate depth information could not be obtained.
I was able to get a value similar to uint16 through (pixel/255)*65535, but a lot of errors occurred because I had already brought the value of uint8.

Is there a way to get raw depth information of uint16 when streaming rtsp using opencv?

My environment is as below
python 3.7
opencv 4.1.0

please, in any case update this

and, it might work with ffmpeg

I know I need to use version 4.1.0 to use CAP_GSTREAMER.

I also looked for related links. If you use ffmpeg, you can probably use 16-bit information as input. But what I want is to get the output in 16bit.

not true. why do you think so ?

I found a way to build opencv 4.1.0 version to use CAP_GSTREAMER on window10.
However, this method is only available in Python version 3.7 and from 3.8 it is said that a different method should be used, but unfortunately that method is not possible, so we are using versions 3.7 and 4.1.0.