CV2 Find Contours detecting the floor and not my target

Question

I am trying to detect the black tape on the floor, but whenever I try to increase the threshold to stop it from detecting the ground all it does is stop detecting the tape.

from cv2 import cv2
import numpy as np

img = cv2.imread('tape4.jpeg', cv2.IMREAD_UNCHANGED)

#convert img to grey
img_grey = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#set a thresh
thresh = 100
#get threshold image
ret,thresh_img = cv2.threshold(img_grey, thresh, 255, cv2.THRESH_BINARY)
#find contours
contours, hierarchy = cv2.findContours(thresh_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

#create an empty image for contours
img_contours = np.zeros(img.shape)
# draw the contours on the empty image
cv2.drawContours(img_contours, contours, -1, (0,255,0), 3)
#save image
cv2.imwrite('contours.png',img_contours) 

Answer 1

You may use Use cv2.THRESH_BINARY_INV instead of cv2.THRESH_BINARY for finding pixels below thresh instead of pixels above thresh.

The reason you are detecting the floor, is that cv2.threshold marks (with 255 value), the pixels above thresh .
You want to mark the dark pixels below thresh .
You can compute: thresh_img = 255 - thresh_img , or use cv2.THRESH_BINARY_INV (result is the same).

I also recommend using closing morphological operation, for removing clutter.

Code for finding the tape:

import cv2
import numpy as np

img = cv2.imread('tape4.jpeg', cv2.IMREAD_UNCHANGED)

#convert img to grey
img_grey = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#set a thresh
thresh = 20 # Set thresh to very low value (the tape is almost black).
#get threshold image
# Use cv2.THRESH_BINARY_INV instead of cv2.THRESH_BINARY for finding pixels below thresh instead of pixels above thresh
ret,thresh_img = cv2.threshold(img_grey, thresh, 255, cv2.THRESH_BINARY_INV)

# Apply closing morphological operation
thresh_img = cv2.morphologyEx(thresh_img, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (21,21)));

#find contours
contours, hierarchy = cv2.findContours(thresh_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

#create an empty image for contours
img_contours = np.zeros(img.shape)
# draw the contours on the empty image
cv2.drawContours(img_contours, contours, -1, (0,255,0), 3)
#save image
cv2.imwrite('contours.png',img_contours) 

Result:

For finding the tape, you can look for the largest contour within contours :

# Get contour with maximum area
c = max(contours, key=cv2.contourArea)
img_contours = np.zeros(img.shape)
cv2.drawContours(img_contours, [c], -1, (0,255,0), 3)

Result: