CODEWITHSUNDEEP
pythonopencvlineobject-detectiondetection
LuGibs
LuGibs

Reputation: 190

OpenCV - Detect only a particular line in an image

I'm trying to isolate a single line in the following image, I know of a few methods such as CannyEdge Detection that can detect all lines in an image but am struggling on how to get just the line I'm interested in.

Any information on tools in OpenCV that could help with this would be much appreciated.enter image description here

The goal is to detect the top red out-line of the court (which I've outlined in blue)

enter image description here

Upvotes: 0

Views: 2990

Answers (1)

fmw42
fmw42

Reputation: 53202

In Python/OpenCV, you can threshold on the red color of the line, then get the biggest contour or on contours larger than some threshold in area, which is what I show below..

Input:

enter image description here

import cv2
import numpy as np

# read image as grayscale
img = cv2.imread('red_line.png')

# threshold on red color
lowcolor = (0,0,75)
highcolor = (50,50,135)
thresh = cv2.inRange(img, lowcolor, highcolor)


# apply morphology close
kernel = np.ones((5,5), np.uint8)
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)

# get contours and filter on area
result = img.copy()
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result = img.copy()
for c in contours:
    area = cv2.contourArea(c)
    if area > 5000:
        cv2.drawContours(result, [c], -1, (0, 255, 0), 2)


# show thresh and result    
cv2.imshow("thresh", thresh)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

# save resulting images
cv2.imwrite('red_line_thresh.png',thresh)
cv2.imwrite('red_line_extracted.png',result)


Thresholded Image:

enter image description here

Resulting Contour:

enter image description here

Upvotes: 3

Related Questions