opencv background subtraction

Question

I'm using background subtraction and I'm using python to do this but when I use the code it just seams to give me a black and white feed of what the camera is seeing. To my knowledge if nothing in front of the camera moves everything should go black, however this is a image of what I am getting.

Screenshot of problem:

This is the code that I am using.

import numpy as np
import cv2
import time

cap = cv2.VideoCapture(0)

kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))
fgbg = cv2.BackgroundSubtractorMOG()

while(1):
    ret, frame = cap.read()

    fgmask = fgbg.apply(frame)
    fgmask = cv2.morphologyEx(fgmask, cv2.MORPH_OPEN, kernel)

    cv2.imshow('frame',fgmask)
    k = cv2.waitKey(30) & 0xff
    if k == 27:
        break

cap.release()
cv2.destroyAllWindows()

What am i doing wrong?

Answer 1

First of all, you should perform background subtraction to grayscale images. What you, basically, should do is saving a frame as reference in the first place, then subtract it from following frames.

You would like to apply some kind of blurring beforehand, and a dilation operation afterward to reduce noise.

This is the most basic background subtraction operation you can do with basic algebra. What you need is a subtraction and a couple of morphological operation.

import numpy as np
import cv2
import time

cap = cv2.VideoCapture(0)
ret, first = cap.read()

# Save the first image as reference
first_gray = cv2.cvtColor(first, cv2.COLOR_BGR2GRAY)
first_gray = cv2.GaussianBlur(first_gray, (21, 21), 0)

while True:
    ret, frame = cap.read()

    if not ret:
        break

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (21, 21), 0)

    # In each iteration, calculate absolute difference between current frame and reference frame
    difference = cv2.absdiff(gray, first_gray)

    # Apply thresholding to eliminate noise
    thresh = cv2.threshold(difference, 25, 255, cv2.THRESH_BINARY)[1]
    thresh = cv2.dilate(thresh, None, iterations=2)

    cv2.imshow("thresh", thresh)
    key = cv2.waitKey(1) & 0xFF

    # if the `q` key is pressed, break from the lop
    if key == ord("q"):
        break

cap.release()
cv2.destroyAllWindows()