Tracker_HSV

Manually putting values for HSV model can be quite frustrating. Easiest way to deal with it is make a openCV based trackbars which allow us to adjust the values manually using a trackbar. So with the help of this, we can able to adjust different combination of values in one go.

Installation

Use the package manager pip to install Tracker_HSV

pip install Tracker_HSV

Samples

• 

• 

• 

• 

---

Tip: Blurring a image can make a significant imporvement.

• 

• 

• 

• 

---

Documents

Let’s take a look at it,

import Tracker_HSV as tr
tr.tracker(filename)

• file_name : This is everything this function need, you can pass a full path of the file or a variable in which image is stored, it can work in both ways, of some fonts

This program returns

return lower_hue, lower_sat, lower_val, upper hue, upper_sat, upper_val

• llower_hue, lower_sat, lower_val: As the name suggests, its a lower value of Hue, Saturation, Value(Brightness)
• upper_hue, upper_sat, upper_val: Similarly, its an upper value of Hue, Saturation, Value(Brightness).

If anytime you forgot the which come after which then just type

import Tracker_HSV as tr
tr.help()

and it will bring you these lines below

<pre class="wp-block-syntaxhighlighter-code">For full code Explanation, please visit 
<blockquote class="wp-embedded-content" data-secret="zvlaQRfHxf"><a href="https://py2py.com/tracker-for-hsv-model-overview-and-explanation/">Tracker for HSV model: Overview and Explanation</a></blockquote><iframe class="wp-embedded-content" sandbox="allow-scripts" security="restricted" style="position: absolute; clip: rect(1px, 1px, 1px, 1px);" src="https://py2py.com/tracker-for-hsv-model-overview-and-explanation/embed/#?secret=zvlaQRfHxf" data-secret="zvlaQRfHxf" width="600" height="338" title="&#8220;Tracker for HSV model: Overview and Explanation&#8221; &#8212; Py2py" frameborder="0" marginwidth="0" marginheight="0" scrolling="no"></iframe>
Github: https://github.com/Pushkar-Singh-14/Tracker_HSV
PyPI: https://pypi.org/project/Tracker-HSV/
</pre>

Explanation

Allow me to explain this module so that we can understand its working better. This is a very simple module which uses the cv2.createTrackbar() function to make a slide bar, which we can use to adjust the values

I am adding the full code here, if you want to understand the specific function or specific line then just navigate to the particular line in the explaination

import cv2
import numpy as np


def tracker(filename):

    if isinstance(filename,str):
        file_name=cv2.imread(filename)
    else:
        file_name=filename
        


    def Null_Value(x):
        return None

    cv2.namedWindow("Trackbars")
     
    cv2.createTrackbar("L - H", "Trackbars", 0, 179, Null_Value)
    cv2.createTrackbar("L - S", "Trackbars", 0, 255, Null_Value)
    cv2.createTrackbar("L - V", "Trackbars", 0, 255, Null_Value)
    cv2.createTrackbar("U - H", "Trackbars", 179, 179, Null_Value)
    cv2.createTrackbar("U - S", "Trackbars", 255, 255, Null_Value)
    cv2.createTrackbar("U - V", "Trackbars", 255, 255, Null_Value)
     
    while True:
        
        hsv = cv2.cvtColor(file_name, 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 = np.array([l_h, l_s, l_v])
        upper = np.array([u_h, u_s, u_v])
        
        
        mask = cv2.inRange(hsv, lower, upper)
        result = cv2.bitwise_and(file_name, file_name, mask=mask)

        cv2.namedWindow('frame',cv2.WINDOW_NORMAL)
        cv2.resizeWindow('frame',(500,500))
        cv2.namedWindow('mask',cv2.WINDOW_NORMAL)
        cv2.resizeWindow('mask',(500,500))
        cv2.namedWindow('result',cv2.WINDOW_NORMAL)
        cv2.resizeWindow('result',(500,500))
        cv2.imshow("frame", file_name)
        cv2.imshow("mask", mask)
        cv2.imshow("result", result)
        key=cv2.waitKey(1)
        if key==27:
            lower_hue=l_h
            lower_sat=l_s
            lower_val=l_v
            upper_hue=u_h
            upper_sat=u_s
            upper_val=u_v
            break

    cv2.destroyAllWindows()
    return lower_hue,lower_sat,lower_val,upper_hue,upper_sat,upper_val


def help():
    print(""" For more information please visit
py2py: https://py2py.com/Tracker-for-HSV-model-Overview-and-Explanation
Github: https://github.com/Pushkar-Singh-14/Tracker_HSV
PyPI: https://pypi.org/project/Tracker-HSV/

""")

---

First of all we are importing the necessary packages

import cv2
import numpy as np

and here is our function

def tracker(filename):

Since the file name can be a full path or a variable in which an image is stored so we are using if-else statement.

if the file is string then its a path, so we open the file and save the variable name.

if its a variable name then we just transfer this variable name to module variable name for file.

    if isinstance(filename,str):
        file_name=cv2.imread(filename)
    else:
        file_name=filename

This null_value() function returns the NULL value, we need this null value in the later step. I will explain why.

def Null_Value(x):
        return None

Here in the 17th line, we create a window in which we paste our images, In the next line, we create the trackbar using cv2.createTrackbar() function, and its attributes are

cv.CreateTrackbar(trackbarName, windowName, value, count, onChange)

• trackbarName:  Name of the created trackbar.
• windowName: Name of the window that will be used as a parent of the created trackbar.
• value: Initial value of pointer, this is the value where tracker is set by default.
• count: Maximal position of the slider. The minimal position is always 0.

and the reason why we need Null operaton

• onChange – Pointer to the function to be called every time the slider changes position. . If the callback is the NULL pointer, no callbacks are called, but only value is updated.

    cv2.namedWindow("Trackbars")
     
    cv2.createTrackbar("L - H", "Trackbars", 0, 179, Null_Value)
    cv2.createTrackbar("L - S", "Trackbars", 0, 255, Null_Value)
    cv2.createTrackbar("L - V", "Trackbars", 0, 255, Null_Value)
    cv2.createTrackbar("U - H", "Trackbars", 179, 179, Null_Value)
    cv2.createTrackbar("U - S", "Trackbars", 255, 255, Null_Value)
    cv2.createTrackbar("U - V", "Trackbars", 255, 255, Null_Value)

Here the image is converted to HSV as HSV is best suited for color detection if you want to understand why then I suggest you, read my article “We already have RGB so why we need HSV ?”

In the next bunch of lines, we store the Tracker position using cv2.getTrackbarPos and save it to respective variables

    while True:
        
        hsv = cv2.cvtColor(file_name, 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")

here we are creating a list for lower value of color and upper value of color as

• lower(hue, saturation, value)
• upper(hue,saturation, value)

        lower = np.array([l_h, l_s, l_v])
        upper = np.array([u_h, u_s, u_v])

we use the inRange function to search the color that we specify in lower and upper values, the function attribute is

then we use bitwise_and operation to mask out selected image, if the mask is inverted then we can use bitwise_not(mask) to invert the mask colors.

        mask = cv2.inRange(hsv, lower, upper)
        result = cv2.bitwise_and(file_name, file_name, mask=mask)

here we are showing the frame, mask and result

then we use the condition that if key==27(esc key) then store the values in other variables and exit the windows.

    cv2.namedWindow('frame',cv2.WINDOW_NORMAL)
    cv2.resizeWindow('frame',(500,500))
    cv2.namedWindow('mask',cv2.WINDOW_NORMAL)
    cv2.resizeWindow('mask',(500,500))
    cv2.namedWindow('result',cv2.WINDOW_NORMAL)
    cv2.resizeWindow('result',(500,500))
    cv2.imshow("frame", file_name)
    cv2.imshow("mask", mask)
    cv2.imshow("result", result)
    key=cv2.waitKey(1)
    if key==27:
        lower_hue=l_h
        lower_sat=l_s
        lower_val=l_v
        upper_hue=u_h
        upper_sat=u_s
        upper_val=u_v
        break

cv2.destroyAllWindows()

Here we are returnign the calues which is required to select the specific color in a HSV image.

    return lower_hue,lower_sat,lower_val,upper_hue,upper_sat,upper_val

Here if you need and help about the program itself then you can type

import Tracker_HSV as tr
 tr.help()

this will show the link of this page and, github and PyPI pages as well

def help():
    print(""" For more information please visit
py2py: https://py2py.com/Tracker-for-HSV-model-Overview-and-Explanation
Github: https://github.com/Pushkar-Singh-14/Tracker_HSV
PyPI: https://pypi.org/project/Tracker-HSV/

""")

So this is all from my side, hope this module will help you someday.

If you have any doubts the please ask in the comments and I will be more then happy to clear them.

---