Python opencv color tracking

Question

Below is my Python code for tracking white objects.
It works - but only for a few seconds, and then the whole screen turns black, and in some cases it does not work.
I experimented with blue and it works, but white and green create problems for me:

import cv2 import numpy as np cap = cv2.VideoCapture(0) while(1): _, frame = cap.read() hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV) # define range of white color in HSV # change it according to your need ! sensitivity = 15 lower_white = np.array([0,0,255-sensitivity]) upper_white = np.array([255,sensitivity,255]) # Threshold the HSV image to get only white colors mask = cv2.inRange(hsv, lower_white, upper_white) # Bitwise-AND mask and original image res = cv2.bitwise_and(frame,frame, mask= mask) cv2.imshow('frame',frame) cv2.imshow('mask',mask) cv2.imshow('res',res) k = cv2.waitKey(5) & 0xFF if k == 27: break cv2.destroyAllWindows() 

Answer 1

Well, firstly, you need to know what color space you are using. Just a little guide on color spaces in OpenCV for Mat type CV_8UC3 . (Images from Wikipedia)

Hsv

In the HSV color space (hue, saturation, value), H gives the color the dominant color, S the color saturation, V the lightness. In OpenCV, the ranges are different. S, V are in [0.255], and H in [0, 180]. Usually, H is in the range [0.360] (full circle), but in order to fit in a byte (256 different values), its value is halved.

In the HSV space, it is easier to separate one color, since you can simply set the correct range for H and just make sure that S is not too small (it will be almost white) and V is not too small (it will be dark).

So, for example, if you need almost blue colors, you need H to be around the value 120 (for example, in [110, 130]), and S, V is not too small (for example, in [100,255]).

White is not a hue (the rainbow does not have white in it), but is a combination of color.

In HSV you need to take the whole range of H (H at [0, 180]), very small S values ​​(for example, S in [0, 25]) and very high V values ​​(for example V in [230, 255]). This basically corresponds to the top of the central axis of the cone.

---

So, to track white objects in HSV space, you need to:

 lower_white = np.array([0, 0, 230]) upper_white = np.array([180, 25, 255]) 

Or, since you have defined a sensitivity value, for example:

 sensitivity = 15 lower_white = np.array([0, 0, 255-sensitivity]) upper_white = np.array([180, sensitivity, 255]) 

For other colors:

 green = 60; blue = 120; yellow = 30; ... sensitivity = 15 // Change color with your actual color lower_color = np.array([color - sensitivity, 100, 100]) upper_color = np.array([color + sensitivity, 255, 255]) 

The value of Red H is 0, so you need to take two ranges and "OR" together:

 sensitivity = 15 lower_red_0 = np.array([0, 100, 100]) upper_red_0 = np.array([sensitivity, 255, 255]) lower_red_1 = np.array([180 - sensitivity, 100, 100]) upper_red_1 = np.array([180, 255, 255]) mask_0 = cv2.inRange(hsv, lower_red_0 , upper_red_0); mask_1 = cv2.inRange(hsv, lower_red_1 , upper_red_1 ); mask = cv2.bitwise_or(mask1, mask2) 

Now you can track any color!