OpenCv Python Color Detection

Question

I am trying to keep track of red objects using opencv in python. Here is the code I have so far:

#Identify red objects in an image

#import OpenCV
import cv2
#Import numpy
import numpy as np

#open webcam
imgcap=cv2.VideoCapture(0)

while(1):

    #view the image from the webcam
    _, frame=imgcap.read()
    #convert the image to HSV
    hsv=cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    #lower threshold for red
    lower_red=np.array([0, 100, 75])
    #upper threshold for red
    upper_red=np.array([5, 76, 100])

    mask=cv2.inRange(hsv, lower_red, upper_red)

When I run this, the error that comes up is the following:

OpenCV Error: Sizes of input arguments do not match (The lower bounary is             neither an array of the same size and same type as src, nor a scalar) in       cv::inRange, file ..\..\..\opencv-2.4.12\modules\core\src\arithm.cpp, line 2703
Traceback (most recent call last):
  File "red.py", line 23, in <module>
    mask=cv2.inRange(hsv, lower_red, upper_red)
cv2.error: ..\..\..\opencv-2.4.12\modules\core\src\arithm.cpp:2703: error: (-209) The lower bounary is neither an array of the same size and same type as src, nor a scalar in function cv::inRange

Can someone please tell me what I am doing wrong? I have tried

lower_red=np.array([0, 100, 75], dtype=np.uint8) 

as well, but that didn't work either.

Answer 1

I guess the error is in line hsv=cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) , as per the variable naming I am assuming that you want a HSV image but you have mistakenly used cv2.COLOR_BGR2GRAY in place of cv2.COLOR_BGR2HSV .

As cv2.COLOR_BGR2GRAY converts the image to grayscale and returns a single channel image so applying mask=cv2.inRange(hsv, lower_red, upper_red) where hsv is a single channel image(while using cv2.COLOR_BGR2GRAY ) and lower_red , upper_red both have 3 elements which results in the error.