1

I'm trying to detect object by color, and get some "information" about the object - like size and position. So far I just did this

import cv2
import numpy

vd1 = cv2.VideoCapture(0)

while True:
    ret, frame = vd1.read()
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    lower_blue = numpy.array([110, 50, 50])
    upper_blue = numpy.array([130, 255, 255])
    mask = cv2.inRange(hsv, lower_blue, upper_blue)
    res = cv2.bitwise_and(frame, frame, mask= mask)
    cv2.imshow("frame", frame)
    cv2.imshow("mask", mask)
    cv2.imshow("res", res)
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

vd1.release()

so I see just the blue objects, but I don't know how I can refer to them like an objects. (so I can get information about the object, or changing the pixels - for example)

How can I do this ? Thanks in advance

noam
  • 11
  • 2
  • You now have the blue objects, so take the binary image of this such that the blue objects alone are white. Now you can use contour properties to obtain things like shape, size, etc. – Jeru Luke Jan 14 '17 at 22:16

0 Answers0