How to detect movement within a specific area with Python Opencv?

Question

Currently I have an algorithm using Python and OpenCV that detects geometrical shapes and calculates its length (without accuracy).

But I need to make that detection within a specific area, in this case it would be inside a rectangle that I draw with the cv2.rect function but I have no idea how to do it and I couldn't find any information on how to do it on the internet.

I am using python 3.7 and OpenCV 3

Can someone help me?

Answer 1

Since images are really just arrays, you can directly select a region of interest using slices, like this:

import cv2
frame = cv2.imread(image)

use_this_smaller_frame = frame[50:100, 300:600] 

This will select a region of y ranging from 50 to 100, and x from 300 to 600, giving you a smaller image that is just the part you care about. Note image indexing is [y, x] and not [x, y] as you might expect.

Use the coordinates you use to draw the rectangle to slice the image, then do the rest of your processing on just the smaller image.

Answer 2

Since you are using Python, you can simply slice the image on the rectangle.

x, y, w, h = cv2.selectROI(window_name, image)  # or something
img_cropped = img[y:y+h, x:x+h] 

You can also check out this tutorial