CODEWITHSUNDEEP
pythonopencvhough-transform
Nine3KiD
Nine3KiD

Reputation: 713

How to detect less than or greater than 90 degree edges(line) in an Image

In my project, I need to detect the roof of a house plan. For that, I have to use the front elevation of the blueprint. I'm planning to use open-cv HoughLines method. Using that I need to detect the roof of the house. Below I have attached the image of the house and my code.

import cv2
import numpy as np
import matplotlib.pyplot as plt

img = cv2.imread('lol.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray,50,150,apertureSize = 3)

lines = cv2.HoughLines(edges,1,np.pi/180,100)
count =0
for rho,theta in lines[0]:
    a = np.cos(theta)
    b = np.sin(theta)
    x0 = a*rho
    y0 = b*rho
    x1 = int(x0 + 1000*(-b))
    y1 = int(y0 + 1000*(a))
    x2 = int(x0 - 1000*(-b))
    y2 = int(y0 - 1000*(a))

    if( 20 < 180*theta/np.pi < 88):
        cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 2)

    if (160 > 180 * theta / np.pi > 93):
        cv2.line(img, (x1, y1), (x2, y2), (0, 255, 0), 2)

cv2.imwrite('detectP.jpg',img)
plt.imshow(img)

House plan I used.

enter image description here

Result obtained after executing the code,

enter image description here

As you can see the detection go through the entire image. I need it to detect only the line and draw the line on top of the angle line not entire image.

Upvotes: 4

Views: 1855

Answers (1)

Muhammad Sabih
Muhammad Sabih

Reputation: 9

You can use the HoughLinesP() function which is Probabilistic Hough Line Transform. Visit https://docs.opencv.org/3.4/d9/db0/tutorial_hough_lines.html

Upvotes: 1

Related Questions