CODEWITHSUNDEEP
pythonopencv
LeThrill
LeThrill

Reputation: 1

Is there a method to detect white pixels from video that has undergone background subtraction

So I'm writing a program that does background subtraction and plays an audio file if it detects movement(the white pixels) and I can't find a method to get the program to detect the pixels. Here's the code

import cv2
import numpy as np

cameraRecord = cv2.VideoCapture(1)
fgbg = cv2.createBackgroundSubtractorMOG2()

while True:
    ret, frame = cameraRecord.read()
    fgmask = fgbg.apply(frame)
    fgmask.nonzero()
    cv2.imshow("Original", frame)
    cv2.imshow("Fg", fgmask)

    k = cv2.waitKey(30) & 0xff
    if k == 27:
        break

cameraRecord.release()
cv2.destroyAllWindows()

Upvotes: 0

Views: 187

Answers (1)

J.D.
J.D.

Reputation: 4561

You can use numpy to sum (docs) all the values in the image, if any white pixels are present the result will be higher than 0. 

result = np.sum(fgmask)

You should check the result against a threshold value to prevent false positives when 1 pixel is white.

The numbers can get very high real fast, so you might find it easier to divide the result to get a smaller number. If you divide by the number of pixels, the result will be between 0 and 255.

Upvotes: 1

Related Questions