使用Opencv Python检测角点

Question

I am trying to find the corners of the 4 pillars which are of yellow in colour and also detecting extreme corners of the board which is of white in colour.

Basically i want to calculate the area of whole space after subtracting the area of each pillar. For that first am trying to identifying the corner of pillars to find the area of each pillar.

Here is the code which I tried, I am almost half way through it.

import numpy as np
import cv2

img = cv2.imread('Corner_0.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
gray = np.float32(gray)

corners = cv2.goodFeaturesToTrack(gray, 100, 0.01, 10)
corners = np.int0(corners)

for corner in corners:
    x,y = corner.ravel()
    cv2.circle(img,(x,y),3,255,-1)

cv2.imwrite('Detected_Corner_0.jpg',img)

I would like to detect corner and calculating the area of the pillar.

When I use Grabcut I am able to apply for one pillar, does this make sense?

Answer 1

Corner detectors often cannot be relied on. The show extra corners and miss the ones you expect. What's more, you have to identify an regroup them.

You obtain interesting results by computing a saturation image (S in LSH). Then by binarization and blob analysis, you can easily find the areas.