Analyze an image in specific area and determine if it's red using Opencv Python

Question

I'm using Opencv python in raspberry pi, to analize a heatmap, i'm looking for color red, which represents the highest temperature, i need to detect if in an specific area exist red color, in case it does i can use this information to activate a condition, i'm using a heatmap like this:

for the red color detection i'm using this code:

import cv2
import numpy as np

while(1):

    # Take each frame

    frame = cv2.imread('heatmap.png')

    # Convert BGR to HSV
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    # define range of blue color in HSV
    lower_red = np.array([-20, 100, 100])
    upper_red = np.array([13, 255, 255])

    # Threshold the HSV image to get only blue colors
    mask = cv2.inRange(hsv, lower_red, upper_red)


    # Bitwise-AND mask and original image
    res = cv2.bitwise_and(frame,frame, mask= mask)

    cv2.imshow('heatmap',frame)
    cv2.imshow('mask',mask)
    cv2.imshow('res',res)
    k = cv2.waitKey(5) & 0xFF
    if k == 27:
        break

cv2.destroyAllWindows()

the code above give me al the pixels in red, but i need to determine if the heatmap contour is red, i mean the image contour or border would be a red color not permited area, does anyone how i can do that?

Answer 1

Your HSV range is not right. For red, (0,20,20)~(8,255,255), (170,20,20) ~ (180,255,255) .

---

Here is my result:

---

The code:

#!/usr/bin/python3
# 2018/05/16 13:54:09 
import cv2
import numpy as np

img = cv2.imread('heatmap.png')
# Convert BGR to HSV
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
mask1 = cv2.inRange(hsv, (0,20,20), (8,255,255))
mask2 = cv2.inRange(hsv, (170,20,20), (180,255,255))
mask = cv2.bitwise_or(mask1, mask2)
dst  = cv2.bitwise_and(img, img, mask=mask)
cv2.imshow("dst", dst)
cv2.imwrite("__.png", dst)
cv2.waitKey()

Some useful links:

1. Choosing the correct upper and lower HSV boundaries for color detection with`cv::inRange` (OpenCV)
2. How to define a threshold value to detect only green colour objects in an image :Opencv