OpenCV egg count python

Question

I did an egg counting using openCV and python and I did get help from here egg detection

while True:

 (grabbed, frame) = cap.read()  
 hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
 th, bw = cv2.threshold(hsv[:, :, 2], 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
 kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
 morph = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)
 dist = cv2.distanceTransform(morph, cv2.DIST_L2, cv2.DIST_MASK_PRECISE)
 .....

And I get the coordinates and draw an ellipse on the egg.

x, y, w, h = cv2.boundingRect(contours[i])
_, mx, _, mxloc = cv2.minMaxLoc(dist[y:y+h, x:x+w], peaks8u[y:y+h, x:x+w])
cv2.circle(im, (int(mxloc[0]+x), int(mxloc[1]+y)), int(mx), (255, 0, 0), 2)
cv2.rectangle(im, (x, y), (x+w, y+h), (0, 255, 255), 2)
cv2.drawContours(im, contours, i, (0, 0, 255), 2)

I created a line and count the eggs one by one.

cv2.line(frame40, (0,coordYEntranceLine), (width,coordYEntranceLine), (255, 0, 0), 2)

def CheckEntranceLineCrossing(coordYContour, coordYEntranceLine):
   absDistance = abs(coordYContour - coordYEntranceLine)

   if ((coordYContour >= coordYEntranceLine) and (absDistance <= 3)):
     return 1
   else:
     return 0

if CheckEntranceLineCrossing(coordYContour, coordYEntranceLine, area):
   eggCount += 1

The problem begins here. According to the logic if the egg past the line and distance <3 is counting, but the conveyor belt is stopped and the distance <3 is counting the egg again, and will perceive as too many eggs.The event I want is not to detect the detected egg again.

The whole code is roughly in this way:

def CheckEntranceLineCrossing(coordYContour, coordYEntranceLine):
   absDistance = abs(coordYContour - coordYEntranceLine)

   if ((coordYContour >= coordYEntranceLine) and (absDistance <= 3)):
      return 1
   else:
      return 0

def getDistance(coordYEgg1,coordYEgg2):
   dist = abs(coordYEgg1 - coordYEgg2)

   return dist

cap = cv2.VideoCapture('20180910_144521.mp4')

while True:

(grabbed, frame) = cap.read()

hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
th, bw = cv2.threshold(hsv[:, :, 2], 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
......

flag = False
egg_list = [[]]
egg_index = 0

for i in range(len(contours)):
    (x, y, w, h) = cv2.boundingRect(contours[i])
    #_, mx, _, mxloc = cv2.minMaxLoc(dist[y:y+h, x:x+w], peaks8u[y:y+h, x:x+w])

    egg_list.append([x, y, flag])

    for i in range(len(egg_list)):
        egg_index = i

        egg_new_X = x
        egg_new_Y = y

        if len(egg_list[egg_index]) >= 1:
            dist = getDistance(egg_new_Y, egg_list[egg_index][1])

            if dist > 50:
                egg_list.append([egg_new_X, egg_new_Y, flag])




    if CheckEntranceLineCrossing(egg_list[i][1], coordYEntranceLine) and not egg_list[i][2]:
        eggCount += 1
        egg_list[i][2] = True

Is there a method you can suggest in this regard? Do I have the chance to put the detected contour into an array and control it or something else?

You need to keep track of the eggs in every frame.

yapws87
– yapws87

2018-09-17 09:38:36 +00:00
Commented Sep 17, 2018 at 9:38 — yapws87
– yapws87, Commented Sep 17, 2018 at 9:38

yapws87 · Accepted Answer · 2018-09-17 10:00:43Z

1

You need to keep track of the eggs in every frame.
1) Lets say you have 5 eggs in frame 1. Store the position and a flag of the eggs in an array, egg_list.

flag = False
egg_list = [[]]
for contour in contours:
   ellipse = cv2.fitEllipse(contour)
   (x, y, w, h) = cv2.boundingRect(contour)
   egg_list.append([x, y , flag])

2) Then find all the eggs in the second frame and compare it with the egg_list. if the distance is below some predefined value, consider them as the same egg. Else add the new egg to the egg_list.

 for contour in contours:
 ellipse = cv2.fitEllipse(contour)
       (x, y, w, h) = cv2.boundingRect(contour)

       ....       

       for i in egg_list:
           dist = getdist(egg_new,egg_list[i])
           if dist > dist_thresh :
              egg_list.append([egg_new[0],egg_new[1],flag])

3) When an egg crosses the line, mark that egg with a flag in the egg_list and increment the count. Then when the same egg is detected to cross the line, you can ignore it.

egg_index = 0
for contour in contours:
   if CheckEntranceLineCrossing(egg_list[egg_index,2], coordYEntranceLine) & ~egg_list[egg_index,2]:
      eggCount += 1
      egg_list[egg_list,2] = true;

By keeping track of all your eggs in a list, you will be able to count only the eggs that matters.

answered Sep 17, 2018 at 10:00

yapws87

1,84910 silver badges16 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Harun Özdemir Over a year ago

Thanks for your reply but I didn't understand getdist () ?

yapws87 Over a year ago

Create a function to calculate the distance between the 2 eggs

Collectives™ on Stack Overflow

OpenCV egg count python

1 Answer 1

2 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related