View a raw10 bit usb camera using OpenCV python

Question

I am trying to view the output of an Omnivision OV7251 camera in OpenCV 4.2.0 Python 3.5.6. The camera output is 10 bit raw greyscale data, which I believe is right aligned in 16-bit words.

When I use this OpenCV code:

import cv2

cam2 = cv2.VideoCapture(0)
cam2.set(3, 640)            # horizontal pixels
cam2.set(4, 480)            # vertical pixels

while True:
    b, frame = cam2.read()

    if b:
        cv2.imshow("Video", frame)

        k = cv2.waitKey(5)

        if k & 0xFF == 27:
            cam2.release()
            cv2.destroyAllWindows()
            break

This is the image I get:

Presumably what's happening is that OpenCV is using the wrong process to convert from 10-bit raw to RGB, believing it to be some kind of YUV or something.

Is there some way I can either:

• Tell OpenCV the camera's correct data format so that it does the conversion properly?
• Get hold of the raw camera data so that I can do the conversion manually?

Answer 1

One way to do this is to grab the raw camera data, then use numpy to correct it:

import cv2
import numpy as np

cam2 = cv2.VideoCapture(0)
cam2.set(3, 640)            # horizontal pixels
cam2.set(4, 480)            # vertical pixels

cam2.set(cv2.CAP_PROP_CONVERT_RGB, False);          # Request raw camera data

while True:
    b, frame = cam2.read()

    if b:
        frame_16 = frame.view(dtype=np.int16)       # reinterpret data as 16-bit pixels
        frame_sh = np.right_shift(frame_16, 2)      # Shift away the bottom 2 bits
        frame_8  = frame_sh.astype(np.uint8)        # Keep the top 8 bits       
        img      = frame_8.reshape(480, 640)        # Arrange them into a rectangle

        cv2.imshow("Video", img)

        k = cv2.waitKey(5)

        if k & 0xFF == 27:
            cam2.release()
            cv2.destroyAllWindows()
            break