AI Vision Academy

Access the code of this tutorial, computer vision courses and an exclusive community on AI Vision Academy

• Access to over 50+ source codes from Pysource.com/blog
• Dedicated video courses about computer vision
• Access to an exclusive community of professionals
• Real-World AI Projects – Get hands-on experience building practical AI Computer Vision solutions with a structured path.
• Monthly Coaching Calls – get support and any of your questions answered

Subscribe to our newsletter to learn more

❌

What we will learn in this tutorial:

• What is HSV
• How to object recognition by color works

What is HSV

HSV (Hue Saturation Value) is a color format that describes colors in terms of their shade (saturation) and brightness (value). 

How to object recognition by color works

In this tutorial I explained how to create an HSV mask with opencv and python for identifying objects simply by color.

If this is one of your first opencv projects you will be surprised by the simplicity and effectiveness of the result. Follow me and I guarantee you will immediately become a master.

In my case I used two highlighters, one green and one blue and we will be able to detach them from the screen with Opencv and an HSV mask.

As always, to start with our Object detection project using HSV Color space we need to call the Opencv library, then we create a mask HSV.

cv2.createTrackbar("L - H", "Trackbars", 0, 179, nothing)
cv2.createTrackbar("L - S", "Trackbars", 0, 255, nothing)
cv2.createTrackbar("L - V", "Trackbars", 0, 255, nothing)
cv2.createTrackbar("U - H", "Trackbars", 179, 179, nothing)
cv2.createTrackbar("U - S", "Trackbars", 255, 255, nothing)
cv2.createTrackbar("U - V", "Trackbars", 255, 255, nothing)

With these bars we can choose which color to hide and which to leave enabled.

If you simply want to use it in real-time it will be enough to put everything in a loop. Like the piece of code in the example.

while True:
    _, frame = cap.read()
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    
    l_h = cv2.getTrackbarPos("L - H", "Trackbars")
    l_s = cv2.getTrackbarPos("L - S", "Trackbars")
    l_v = cv2.getTrackbarPos("L - V", "Trackbars")
    u_h = cv2.getTrackbarPos("U - H", "Trackbars")
    u_s = cv2.getTrackbarPos("U - S", "Trackbars")
    u_v = cv2.getTrackbarPos("U - V", "Trackbars")
    
    lower_blue = np.array([l_h, l_s, l_v])
    upper_blue = np.array([u_h, u_s, u_v])
    mask = cv2.inRange(hsv, lower_blue, upper_blue)
    
    result = cv2.bitwise_and(frame, frame, mask=mask)
    
    cv2.imshow("frame", frame)
    cv2.imshow("mask", mask)
    cv2.imshow("result", result)

Object detection project

I hope the project has been helpful to you and I recommend that you download the complete to have a fully functional example.

If you need to create a real object detection project, I suggest you evaluate the purchase of my Object detection with OpenCV & deep learning course.