CV2 Find Contours 检测地板而不是我的目标

Question

我正在尝试检测地板上的黑色胶带，但是每当我尝试增加阈值以阻止它检测到地面时，它所做的就是停止检测胶带。

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

您可以使用使用cv2.THRESH_BINARY_INV而不是cv2.THRESH_BINARY来查找低于thresh值的像素而不是高于阈值的像素。

您检测地板的原因是cv2.threshold标记（具有255值），高于thresh的像素。
您想要标记低于thresh的暗像素。
您可以计算： thresh_img = 255 - thresh_img ，或使用cv2.THRESH_BINARY_INV （结果相同）。

我还建议使用关闭形态学操作来消除混乱。

查找磁带的代码：

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) 

结果：

为了找到磁带，您可以在 contours 中查找最大的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)

结果：