CODEWITHSUNDEEP
pythonimagenumpyopencv
Mischef9
Mischef9

Reputation: 47

How to detect Pixel Location of Object given Mask - OpenCV Python

I was trying to make a mini-aimbot for my own recreational purposes (in my own game), and have decided to use OpenCV and Numpy to attempt this. What I have done is that I have gotten a mask of the targets, and now want the pixel location of the white color from the mask - so I can move my mouse and click the target.

This is the Mask In question

Basically, I want to get the pixel location of each white shape, and be able to move the mouse to the location. I do not know how to get the pixel location yet, so any help is appreciated!

Upvotes: 0

Views: 2792

Answers (1)

Clinton Bradfield
Clinton Bradfield

Reputation: 226

During image segmentation, you should be able to find the center pixel of a given blob of signal with cv2.moments(contour_object). Segmenting objects from one another can be done with watershed algoritms and cv2.findcountours(image) does a pretty good job finding contours in the image. Signal dilation and contraction may be useful for your segmentation purposes if it doesn't work first shot, but yours is a pretty simple image, so have hope.

Below is a boiler from learnopencv.com that should perform in your case:

# read image through command line
img = cv2.imread(args["ipimage"])

# convert the image to grayscale
gray_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# convert the grayscale image to binary image
ret,thresh = cv2.threshold(gray_image,127,255,0)

# find contours in the binary image
im2, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
for c in contours:
   # calculate moments for each contour
   M = cv2.moments(c)

   # calculate x,y coordinate of center
   cX = int(M["m10"] / M["m00"])
   cY = int(M["m01"] / M["m00"])
   cv2.circle(img, (cX, cY), 5, (255, 255, 255), -1)
   cv2.putText(img, "centroid", (cX - 25, cY - 25),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)

   # display the image
   cv2.imshow("Image", img)
   cv2.waitKey(0)

Upvotes: 4

Related Questions