I am using the find contours method and then approximating a line by using fitline function. below is the code:
img = cv2.imread('lines.jpg')
imgray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret,dst = cv2.threshold(imgray,127,255,0)
im2,cnts, hierarchy =cv2.findContours(dst,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
rows,cols = img.shape[:2]
[vx,vy,x,y] = cv2.fitLine(cnts[0], cv2.DIST_L2,0,0.01,0.01)
lefty = int((-x*vy/vx) + y)
righty = int(((cols-x)*vy/vx)+y)
cv2.line(img,(cols-1,righty),(0,lefty),(0,255,0),2)
print img.shape[:2]
cv2.imshow('image1',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Following is the image I am getting as output
I was expecting it to detect each of the black stripes in the image whereas it is detecting only the first line from the bottom
This modified code is what you may have been looking for. I have left most of your lines and it is pretty verbose, but this might help you understand it without further explanation.
I think that you got trapped in two different of problems:
You may not have detected the lines as foreground, but the white areas, this is why I negated the images (thresh = (255-thresh))
import numpy as np
import cv2
im = cv2.imread('lines.jpg')
rows,cols = im.shape[:2]
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(imgray,125,255,0)
thresh = (255-thresh)
thresh2=thresh.copy()
im2, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cv2.imshow('image1',im)
cv2.imshow('image3',thresh2)
#cv2.drawContours(im, contours, -1, (0,255,0), 3) #draw all contours
contnumber=4
cv2.drawContours(im, contours, contnumber, (0,255,0), 3) #draw only contour contnumber
cv2.imshow('contours', im)
[vx,vy,x,y] = cv2.fitLine(contours[contnumber], cv2.DIST_L2,0,0.01,0.01)
lefty = int((-x*vy/vx) + y)
righty = int(((cols-x)*vy/vx)+y)
cv2.line(im,(cols-1,righty),(0,lefty),(0,255,255),2)
cv2.imshow('result', im)
cv2.waitKey(0)
cv2.destroyAllWindows()
Hope that helps.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With