HSV Colour Segmentation

HSV (Hue–Saturation–Value) colour space makes it easier to isolate objects by colour under varying lighting conditions.

HSV Ranges for Common Colours

Colour	H min	H max	S min	V min
Red (low)	0	10	100	100
Red (high)	160	180	100	100
Green	40	80	50	50
Blue	100	130	50	50
Yellow	20	35	100	100

Code

import cv2
import numpy as np

cap = cv2.VideoCapture(0)

while True:
    _, frame = cap.read()
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # Detect green
    lower = np.array([40, 50, 50])
    upper = np.array([80, 255, 255])
    mask = cv2.inRange(hsv, lower, upper)

    # Find contours
    contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    for cnt in contours:
        if cv2.contourArea(cnt) > 500:
            x, y, w, h = cv2.boundingRect(cnt)
            cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)

    cv2.imshow("Mask", mask)
    cv2.imshow("Frame", frame)
    if cv2.waitKey(1) == ord('q'):
        break

TIP

Use the HSV trackbar to tune thresholds live before hardcoding them. See the OpenCV docs.