ROI | Technology Tutorials

In this lesson we learn to become more comfortable creating Regions of Interests (ROIs). We also show some new methods to stack your windows and keep your windows organized and tightly packed. In this video lesson, we developed the following code:

import cv2
import time
from picamera2 import Picamera2
piCam = Picamera2()
W=640
H=360
tStart = time.time()
fps = 0
RES = (W,H)
piCam.preview_configuration.main.size = RES
piCam.preview_configuration.main.format = "RGB888"
piCam.preview_configuration.controls.FrameRate=60
piCam.preview_configuration.align()
piCam.configure("preview")
piCam.start()

textLowerLeft = (int(W*.01),int(H*.05))
fontFace = cv2.FONT_HERSHEY_SIMPLEX
fontThickness = int(W/425)
fontScale = H*.0015
fontColor = (0,0,255)

topBar = 65
windowWaste = 25

cv2.namedWindow("Camera", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Camera", W, H)
cv2.moveWindow("Camera",0,topBar)

cv2.namedWindow("Camera Small", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Camera Small",  int(W/2), int(H/2))
cv2.moveWindow("Camera Small",0,topBar+windowWaste+H)
    
cv2.namedWindow("Gray Small", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Gray Small", int(W/2), int(H/2))
cv2.moveWindow("Gray Small",int(W/2),topBar+windowWaste+H)

quadrants = ["upperLeft","upperRight","lowerLeft","lowerRight"]
x=0
for quadrant in quadrants:
    cv2.namedWindow(quadrant, cv2.WINDOW_GUI_NORMAL)
    cv2.resizeWindow(quadrant,int(W/4),int(H/4))
    cv2.moveWindow(quadrant,W,topBar+int(x*(windowWaste+H/4)))
    x=x+1
    
while True:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    frame= piCam.capture_array()
    frame=cv2.flip(frame,-1)
    
    print(frame[int(H/2),int(W/2)])
    frame[int(H/2):int(H/2)+10,int(W/2):int(W/2)+10] = [0,0,255]
    
    ROI = frame[int(H*.25):int(H*.75),int(W*.25):int(W*.75)].copy()

    ROI[int(.25*H*.5):int(.75*H*.5),int(.25*W*.5):int(.75*W*.5)] = [0,0,0]
    ROIgray = cv2.cvtColor(ROI,cv2.COLOR_BGR2GRAY) 
 
    frameSmall=cv2.resize(frame,(int(W/2),int(H/2)))
    
    upperLeft = frame[0:int(H/2),0:int(W/2)]
    upperRight = frame[0:int(H/2),int(W/2):W-1]
    lowerLeft = frame[int(H/2):H-1,0:int(W/2)]
    lowerRight = frame[int(H/2):H-1,int(W/2):W-1]
    
    quadDict = {
        "upperLeft" : upperLeft,
        "upperRight" : upperRight,
        "lowerLeft" : lowerLeft,
        "lowerRight" : lowerRight
        }
    
    

    myText = "FPS: "+str(round(fps,1))
    cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)
    cv2.imshow("Camera", frame)
    cv2.imshow("Camera Small",ROI)
    cv2.imshow("Gray Small",ROIgray)
    for name, image in quadDict.items():
        cv2.imshow(name,image)
    

    if cv2.waitKey(1)==ord('q'):
        break
cv2.destroyAllWindows()
print('Program Terminated')

import cv2

import time

from picamera2 import Picamera2

piCam = Picamera2()

W=640

H=360

tStart = time.time()

fps = 0

RES = (W,H)

piCam.preview_configuration.main.size = RES

piCam.preview_configuration.main.format = "RGB888"

piCam.preview_configuration.controls.FrameRate=60

piCam.preview_configuration.align()

piCam.configure("preview")

piCam.start()

textLowerLeft = (int(W*.01),int(H*.05))

fontFace = cv2.FONT_HERSHEY_SIMPLEX

fontThickness = int(W/425)

fontScale = H*.0015

fontColor = (0,0,255)

topBar = 65

windowWaste = 25

cv2.namedWindow("Camera", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Camera", W, H)

cv2.moveWindow("Camera",0,topBar)

cv2.namedWindow("Camera Small", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Camera Small", int(W/2), int(H/2))

cv2.moveWindow("Camera Small",0,topBar+windowWaste+H)

cv2.namedWindow("Gray Small", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Gray Small", int(W/2), int(H/2))

cv2.moveWindow("Gray Small",int(W/2),topBar+windowWaste+H)

quadrants = ["upperLeft","upperRight","lowerLeft","lowerRight"]

x=0

for quadrant in quadrants:

cv2.namedWindow(quadrant, cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow(quadrant,int(W/4),int(H/4))

cv2.moveWindow(quadrant,W,topBar+int(x*(windowWaste+H/4)))

x=x+1

while True:

deltaT = time.time() - tStart

tStart=time.time()

fps = fps*.95 + (1/deltaT)*.05

frame= piCam.capture_array()

frame=cv2.flip(frame,-1)

print(frame[int(H/2),int(W/2)])

frame[int(H/2):int(H/2)+10,int(W/2):int(W/2)+10] = [0,0,255]

ROI = frame[int(H*.25):int(H*.75),int(W*.25):int(W*.75)].copy()

ROI[int(.25*H*.5):int(.75*H*.5),int(.25*W*.5):int(.75*W*.5)] = [0,0,0]

ROIgray = cv2.cvtColor(ROI,cv2.COLOR_BGR2GRAY)

frameSmall=cv2.resize(frame,(int(W/2),int(H/2)))

upperLeft = frame[0:int(H/2),0:int(W/2)]

upperRight = frame[0:int(H/2),int(W/2):W-1]

lowerLeft = frame[int(H/2):H-1,0:int(W/2)]

lowerRight = frame[int(H/2):H-1,int(W/2):W-1]

quadDict = {

"upperLeft" : upperLeft,

"upperRight" : upperRight,

"lowerLeft" : lowerLeft,

"lowerRight" : lowerRight

}

myText = "FPS: "+str(round(fps,1))

cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)

cv2.imshow("Camera", frame)

cv2.imshow("Camera Small",ROI)

cv2.imshow("Gray Small",ROIgray)

for name, image in quadDict.items():

cv2.imshow(name,image)

if cv2.waitKey(1)==ord('q'):

break

cv2.destroyAllWindows()

print('Program Terminated')

Hey guys, Paul McWhorter here with TopTechBoy.com, and today we are diving into the heart of computer vision. We’ve been playing around with getting images from the camera, but have you ever stopped to actually look at what a picture is when it’s inside your computer’s memory?

If you want to be a master of AI on the Edge, you have to stop thinking about images as “pictures” and start seeing them as what they really are: a massive, organized grid of numbers.

What is a Picture, Really?

In this lesson, we are peeling back the curtain on how OpenCV and Python handle video frames. When we call piCam.capture_array(), we aren’t just taking a snapshot; we are pulling a data array into memory.

Think of it like a giant spreadsheet where every single cell is a pixel.

Dimensions: Your image has a width and a height, which correspond to the number of rows and columns in that array. It is important to remember the row designator comes first, then the column, [ R, C]
The Depth (The RGB Channels): It’s not just a flat 2D grid! Each “cell” in that grid is actually a little sub-array containing three values: Red, Green, and Blue. That is why we call it a 3D data structure.

Manipulating Data, Not Just Pixels

The magic happens when you realize you can reach into that array and change those numbers directly.

In the code we developed today, we aren’t just displaying video; we are performing data science on video frames. We explored how to:

Access individual pixels: By referencing specific coordinates in our frame array, we can pull out the color data for a single spot.
Draw shapes by modifying arrays: Notice how we don’t need a “draw square” function to put a box on the screen? We simply tell a slice of that array to equal [0, 0, 255]. We are literally changing the color values of those pixels to solid red.
Regions of Interest (ROI): This is critical for AI. You don’t always need to look at the whole frame. We learned how to “slice” the array to isolate a Region of Interest. By carving out a smaller piece of that memory, we can perform operations—like converting to grayscale—on just that section, which saves a massive amount of processing power.

Why Does This Matter?

If you want to build a robot that recognizes objects or tracks faces, you need to understand this structure. AI models don’t “see” a cat; they see a mathematical representation of that cat’s pixel values. By learning how to slice, manipulate, and convert these arrays, you are learning the fundamental language of machine learning.

We are building the foundation here, folks. Once you get comfortable with how to manipulate these arrays, we are going to start doing some really cool stuff with image processing and filtering.

Dive into that code, change those array values, and see what happens when you mess with the dimensions! Don’t just run it—experiment with it.

I’ll see you guys in the next lesson!

In this lesson we developed the following code:

import cv2
import time
from picamera2 import Picamera2
piCam = Picamera2()
W=640
H=360
tStart = time.time()
fps = 0
RES = (W,H)
piCam.preview_configuration.main.size = RES
piCam.preview_configuration.main.format = "RGB888"
piCam.preview_configuration.controls.FrameRate=60
piCam.preview_configuration.align()
piCam.configure("preview")
piCam.start()

textLowerLeft = (int(W*.01),int(H*.05))
fontFace = cv2.FONT_HERSHEY_SIMPLEX
fontThickness = int(W/425)
fontScale = H*.0015
fontColor = (0,0,255)

topBar = 65
windowWaste = 25

cv2.namedWindow("Camera", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Camera", W, H)
cv2.moveWindow("Camera",0,topBar)

cv2.namedWindow("Camera Small", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Camera Small",  int(W/2), int(H/2))
cv2.moveWindow("Camera Small",0,topBar+windowWaste+H)
    
cv2.namedWindow("Gray Small", cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow("Gray Small", int(W/2), int(H/2))
cv2.moveWindow("Gray Small",int(W/2),topBar+windowWaste+H)


while True:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    frame= piCam.capture_array()
    frame=cv2.flip(frame,-1)
    
    print(frame[int(H/2),int(W/2)])
    frame[int(H/2):int(H/2)+10,int(W/2):int(W/2)+10] = [0,0,255]
    
    ROI = frame[int(H*.25):int(H*.75),int(W*.25):int(W*.75)].copy()

    ROI[int(.25*H*.5):int(.75*H*.5),int(.25*W*.5):int(.75*W*.5)] = [0,0,0]
    ROIgray = cv2.cvtColor(ROI,cv2.COLOR_BGR2GRAY) 
 
    frameSmall=cv2.resize(frame,(int(W/2),int(H/2)))
    

    myText = "FPS: "+str(round(fps,1))
    cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)
    cv2.imshow("Camera", frame)
    cv2.imshow("Camera Small",ROI)
    cv2.imshow("Gray Small",ROIgray)

    if cv2.waitKey(1)==ord('q'):
        break
cv2.destroyAllWindows()
print('Program Terminated')

import cv2

import time

from picamera2 import Picamera2

piCam = Picamera2()

W=640

H=360

tStart = time.time()

fps = 0

RES = (W,H)

piCam.preview_configuration.main.size = RES

piCam.preview_configuration.main.format = "RGB888"

piCam.preview_configuration.controls.FrameRate=60

piCam.preview_configuration.align()

piCam.configure("preview")

piCam.start()

textLowerLeft = (int(W*.01),int(H*.05))

fontFace = cv2.FONT_HERSHEY_SIMPLEX

fontThickness = int(W/425)

fontScale = H*.0015

fontColor = (0,0,255)

topBar = 65

windowWaste = 25

cv2.namedWindow("Camera", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Camera", W, H)

cv2.moveWindow("Camera",0,topBar)

cv2.namedWindow("Camera Small", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Camera Small", int(W/2), int(H/2))

cv2.moveWindow("Camera Small",0,topBar+windowWaste+H)

cv2.namedWindow("Gray Small", cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow("Gray Small", int(W/2), int(H/2))

cv2.moveWindow("Gray Small",int(W/2),topBar+windowWaste+H)

while True:

deltaT = time.time() - tStart

tStart=time.time()

fps = fps*.95 + (1/deltaT)*.05

frame= piCam.capture_array()

frame=cv2.flip(frame,-1)

print(frame[int(H/2),int(W/2)])

frame[int(H/2):int(H/2)+10,int(W/2):int(W/2)+10] = [0,0,255]

ROI = frame[int(H*.25):int(H*.75),int(W*.25):int(W*.75)].copy()

ROI[int(.25*H*.5):int(.75*H*.5),int(.25*W*.5):int(.75*W*.5)] = [0,0,0]

ROIgray = cv2.cvtColor(ROI,cv2.COLOR_BGR2GRAY)

frameSmall=cv2.resize(frame,(int(W/2),int(H/2)))

myText = "FPS: "+str(round(fps,1))

cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)

cv2.imshow("Camera", frame)

cv2.imshow("Camera Small",ROI)

cv2.imshow("Gray Small",ROIgray)

if cv2.waitKey(1)==ord('q'):

break

cv2.destroyAllWindows()

print('Program Terminated')

Making The World a Better Place One High Tech Project at a Time. Enjoy!

Technology Tutorials

Tag Archives: ROI

AI on the Edge LESSON 23: Creating Regions of Interest (ROI) in OpenCV with Slicing

AI on the Edge LESSON 22: Understanding Pictures and Video Frames as a Data Structure

What is a Picture, Really?

Manipulating Data, Not Just Pixels

Why Does This Matter?

Making The World a Better Place One High Tech Project at a Time. Enjoy!