Tag Archives: Artificial intelligence

OK guys, you spoke, and I listened. You all are asking for a lesson on how to do object detection on a Pi 5 using YOLO and an IP Camera. Well, you are about to get what you asked for. We will make this work, or we will DIE TRYING. Never fear, once you watch the video you will both understand and be able to do it on your own. First, I am assuming you watched our previous lesson where I showed you how to do the basic install and setup of YOLO. If not, never fear, I have the commands below. NOTE: This tutorial is geared towards bookworm OS. I strongly suggest you start with a fresh bookworm SC card, as there are many dependencies, and it is most likely to work if you start exactly where I am starting . . . with a fresh OS. Thes these are the commands I shared last week to get YOLO up and working: (just open a terminal, and paste these commands one at a time)

# 1. Configure X11 (manual steps required)
sudo raspi-config
# → Go to Advanced Options → X11 → Enable X11
# → Finish and reboot when prompted

# 5. Update system and install OpenCV
sudo apt update
sudo apt full-upgrade -y
sudo apt install python3-opencv -y

# Verify OpenCV
python3 -c "import cv2; print('OpenCV version:', cv2.__version__)"
# Expected output: something like "OpenCV version: 4.6.0" or higher

# Create and activate virtual environment for YOLO11 (Ultralytics)
python3 -m venv --system-site-packages YOLO
source YOLO/bin/activate

# You are now inside the (YOLO) virtual environment
# Install Ultralytics YOLO11 inside it
pip install "numpy<2.0" ultralytics

# Now create a Pi friendly YOLO11 model
yolo export model=yolo11n.pt format=ncnn

# Optional: Verify YOLO installation
python -c "from ultralytics import YOLO; print('Ultralytics YOLO ready')"

# When finished working with YOLO, you can deactivate with:
# deactivate

#Now open Thonny, and you need to point thonny to the virtual environment you 
#just created. Open tools- options, select 'interpreter' tab, then click they Python
#executable, selecting ... and navigate from home directory, 
#to YOLO, to bin, and then select python

# 1. Configure X11 (manual steps required)

sudo raspi-config

# → Go to Advanced Options → X11 → Enable X11

# → Finish and reboot when prompted

# 5. Update system and install OpenCV

sudo apt update

sudo apt full-upgrade -y

sudo apt install python3-opencv -y

# Verify OpenCV

python3 -c "import cv2; print('OpenCV version:', cv2.__version__)"

# Expected output: something like "OpenCV version: 4.6.0" or higher

# Create and activate virtual environment for YOLO11 (Ultralytics)

python3 -m venv --system-site-packages YOLO

source YOLO/bin/activate

# You are now inside the (YOLO) virtual environment

# Install Ultralytics YOLO11 inside it

pip install "numpy<2.0" ultralytics

# Now create a Pi friendly YOLO11 model

yolo export model=yolo11n.pt format=ncnn

# Optional: Verify YOLO installation

python -c "from ultralytics import YOLO; print('Ultralytics YOLO ready')"

# When finished working with YOLO, you can deactivate with:

# deactivate

#Now open Thonny, and you need to point thonny to the virtual environment you

#just created. Open tools- options, select 'interpreter' tab, then click they Python

#executable, selecting ... and navigate from home directory,

#to YOLO, to bin, and then select python

Now, I will explain this code, and will help you configure it for your cameras, but you will need to open up thonny, and paste in the following code as a start. IMPORTANT, as mentioned above, you need to set interpreter in thonny to the virtual environment set up in the process above. If this is not familiar to you, go back and watch last weeks lesson (click previous at the bottom of this post). Without further adue, here is the code we will work with today:

import cv2
from ultralytics import YOLO
#import secret
import threading
import time

W=1280
H=720
#Now, as eplained in the video, edit the line below where 
#you put your wifi user name in place of user, and your 
#wifi password in place of password, and you put in your 
#IP address
RTSP_URL = "rtsp://user:password@192.168.88.44:554/cam/realmonitor?channel=1&subtype=0"
#RTSP_URL = secret.RTSP_URL1
#I have put my wifi credentials in a secret file so no
#one sees my credentials. You will just use the RTSP_URL line above. 
# Load the exported NCNN model (replace with your model path)
model = YOLO("/home/pjm/yolo11n_ncnn_model/", task="detect")
lock = threading.Lock()
running = True
def frameGrabber(url):
    global ipFrame, running
    cap = cv2.VideoCapture(url, cv2.CAP_FFMPEG)
    cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)
    cap.set(cv2.CAP_PROP_POS_FRAMES, 0)  # Reset frame position
    while running:
        ret, frame = cap.read()
        if ret:
            with lock:
                #frame = cv2.resize(frame, (W, H))
                ipFrame = frame.copy()
    cap.release()
    print("Thread Terminated")
thread = threading.Thread(target=frameGrabber, args=(RTSP_URL,), daemon=True)
thread.start()
tStart=time.time()
time.sleep(2)
fps=0
cnt=0
# Set resolution for faster processing (optional, adjust based on your needs)
while True:
    deltaT=time.time()-tStart
    fps= fps*.9 + .1/deltaT
    tStart=time.time()
    with lock:
        ipFrameShow=ipFrame.copy()
    results = model(ipFrameShow, conf=0.25, verbose=False)[0]  # conf: confidence threshold; adjust as needed

    # Annotate the frame with detections (boxes, labels, scores)
    annotatedFrame = results.plot()
    annotatedFrame=cv2.resize(annotatedFrame, (W,H))
    cv2.putText(annotatedFrame, "FPS: "+str(round(fps,1)), (int(W*.01), int(H*.075)), 
            cv2.FONT_HERSHEY_SIMPLEX, H*.002, (0, 0, 255), 3)
    cv2.imshow("IP Camera", annotatedFrame)
    #cv2.moveWindow("IP Camera",100,100)
    if cv2.waitKey(1)==ord('q'):
        break
running=False
thread.join()  # Wait for thread to fully exit
time.sleep(1)
cv2.destroyAllWindows()
import gc
gc.collect()  # Force garbage collection to reclaim memory/connections
#Make Extra sure all processes are killed
import os
os._exit(0)
print("Program Terminated")

import cv2

from ultralytics import YOLO

#import secret

import threading

import time

W=1280

H=720

#Now, as eplained in the video, edit the line below where

#you put your wifi user name in place of user, and your

#wifi password in place of password, and you put in your

#IP address

RTSP_URL = "rtsp://user:password@192.168.88.44:554/cam/realmonitor?channel=1&subtype=0"

#RTSP_URL = secret.RTSP_URL1

#I have put my wifi credentials in a secret file so no

#one sees my credentials. You will just use the RTSP_URL line above.

# Load the exported NCNN model (replace with your model path)

model = YOLO("/home/pjm/yolo11n_ncnn_model/", task="detect")

lock = threading.Lock()

running = True

def frameGrabber(url):

global ipFrame, running

cap = cv2.VideoCapture(url, cv2.CAP_FFMPEG)

cap.set(cv2.CAP_PROP_BUFFERSIZE, 1)

cap.set(cv2.CAP_PROP_POS_FRAMES, 0) # Reset frame position

while running:

ret, frame = cap.read()

if ret:

with lock:

#frame = cv2.resize(frame, (W, H))

ipFrame = frame.copy()

cap.release()

print("Thread Terminated")

thread = threading.Thread(target=frameGrabber, args=(RTSP_URL,), daemon=True)

thread.start()

tStart=time.time()

time.sleep(2)

fps=0

cnt=0

# Set resolution for faster processing (optional, adjust based on your needs)

while True:

deltaT=time.time()-tStart

fps= fps*.9 + .1/deltaT

tStart=time.time()

with lock:

ipFrameShow=ipFrame.copy()

results = model(ipFrameShow, conf=0.25, verbose=False)[0] # conf: confidence threshold; adjust as needed

# Annotate the frame with detections (boxes, labels, scores)

annotatedFrame = results.plot()

annotatedFrame=cv2.resize(annotatedFrame, (W,H))

cv2.putText(annotatedFrame, "FPS: "+str(round(fps,1)), (int(W*.01), int(H*.075)),

cv2.FONT_HERSHEY_SIMPLEX, H*.002, (0, 0, 255), 3)

cv2.imshow("IP Camera", annotatedFrame)

#cv2.moveWindow("IP Camera",100,100)

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

break

running=False

thread.join() # Wait for thread to fully exit

time.sleep(1)

cv2.destroyAllWindows()

import gc

gc.collect() # Force garbage collection to reclaim memory/connections

#Make Extra sure all processes are killed

import os

os._exit(0)

print("Program Terminated")

The video explains everything, please watch it!

OpenCV, Python

AI FOR EVERYONE HOMEWORK SOLUTION: Face Recognition with Live Video in OpenCV

October 23, 2021 admin

In this video lesson we show you how to recognize faces in live video from your WEBcam. It is the homework solution for lesson #16. This builds on the earlier video lessons in this series, so if any of this does not make sense, go back and check out some of the earlier lessons.

import cv2
import face_recognition as FR
font=cv2.FONT_HERSHEY_SIMPLEX
width=640
height=360
cam=cv2.VideoCapture(0,cv2.CAP_DSHOW)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT,height)
cam.set(cv2.CAP_PROP_FPS, 30)
cam.set(cv2.CAP_PROP_FOURCC,cv2.VideoWriter_fourcc(*'MJPG'))

paulFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Paul McWhorter.jpg')
faceLoc=FR.face_locations(paulFace)[0]
paulFaceEncode=FR.face_encodings(paulFace)[0]

gavFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Gavriella Joy.jpg')
faceLoc=FR.face_locations(gavFace)[0]
gavFaceEncode=FR.face_encodings(gavFace)[0]

knownEncodings=[paulFaceEncode,gavFaceEncode]
names=['Paul McWhorter','Gavriella Joy']

while True:
    ignore,  unknownFace = cam.read()

    unknownFaceRGB=cv2.cvtColor(unknownFace,cv2.COLOR_RGB2BGR)
    faceLocations=FR.face_locations(unknownFaceRGB)
    unknownEncodings=FR.face_encodings(unknownFaceRGB,faceLocations)

    for faceLocation,unknownEncoding in zip(faceLocations,unknownEncodings):
        top,right,bottom,left=faceLocation
        print(faceLocation)
        cv2.rectangle(unknownFace,(left,top),(right,bottom),(255,0,0),3)
        name='Unknown Person'
        matches=FR.compare_faces(knownEncodings,unknownEncoding)
        print(matches)
        if True in matches:
            matchIndex=matches.index(True)
            print(matchIndex)
            print(names[matchIndex])
            name=names[matchIndex]
        cv2.putText(unknownFace,name,(left,top),font,.75,(0,0,255),2)

    cv2.imshow('My Faces',unknownFace)
    if cv2.waitKey(1) & 0xff ==ord('q'):
        break
cam.release()
cv2.destroyAllWindows()

import cv2

import face_recognition as FR

font=cv2.FONT_HERSHEY_SIMPLEX

width=640

height=360

cam=cv2.VideoCapture(0,cv2.CAP_DSHOW)

cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)

cam.set(cv2.CAP_PROP_FRAME_HEIGHT,height)

cam.set(cv2.CAP_PROP_FPS, 30)

cam.set(cv2.CAP_PROP_FOURCC,cv2.VideoWriter_fourcc(*'MJPG'))

paulFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Paul McWhorter.jpg')

faceLoc=FR.face_locations(paulFace)[0]

paulFaceEncode=FR.face_encodings(paulFace)[0]

gavFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Gavriella Joy.jpg')

faceLoc=FR.face_locations(gavFace)[0]

gavFaceEncode=FR.face_encodings(gavFace)[0]

knownEncodings=[paulFaceEncode,gavFaceEncode]

names=['Paul McWhorter','Gavriella Joy']

while True:

ignore, unknownFace = cam.read()

unknownFaceRGB=cv2.cvtColor(unknownFace,cv2.COLOR_RGB2BGR)

faceLocations=FR.face_locations(unknownFaceRGB)

unknownEncodings=FR.face_encodings(unknownFaceRGB,faceLocations)

for faceLocation,unknownEncoding in zip(faceLocations,unknownEncodings):

top,right,bottom,left=faceLocation

print(faceLocation)

cv2.rectangle(unknownFace,(left,top),(right,bottom),(255,0,0),3)

name='Unknown Person'

matches=FR.compare_faces(knownEncodings,unknownEncoding)

print(matches)

if True in matches:

matchIndex=matches.index(True)

print(matchIndex)

print(names[matchIndex])

name=names[matchIndex]

cv2.putText(unknownFace,name,(left,top),font,.75,(0,0,255),2)

cv2.imshow('My Faces',unknownFace)

if cv2.waitKey(1) & 0xff ==ord('q'):

break

cam.release()

cv2.destroyAllWindows()

OpenCV, Python

AI for Everyone LESSON 16: Face Recognition with OpenCV

October 19, 2021 admin

Guys in this lesson we learn how to not only detect faces in an image, but also recognize who the person is. We start by training our model with known faces, and then find and identify those faces in other pictures. For your convenience, I include the code developed in this lesson below.

import cv2
import face_recognition as FR
font=cv2.FONT_HERSHEY_SIMPLEX

donFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Donald Trump.jpg')
faceLoc=FR.face_locations(donFace)[0]
donFaceEncode=FR.face_encodings(donFace)[0]


nancyFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Nancy Pelosi.jpg')
faceLoc=FR.face_locations(nancyFace)[0]
nancyFaceEncode=FR.face_encodings(nancyFace)[0]

penceFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Mike Pence.jpg')
faceLoc=FR.face_locations(penceFace)[0]
penceFaceEncode=FR.face_encodings(penceFace)[0]

knownEncodings=[donFaceEncode,nancyFaceEncode,penceFaceEncode]
names=['Donald Trump','Nancy Pelosi','Mike Pence']

unknownFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/unknown/u1.jpg')
unknownFaceBGR=cv2.cvtColor(unknownFace,cv2.COLOR_RGB2BGR)
faceLocations=FR.face_locations(unknownFace)
unknownEncodings=FR.face_encodings(unknownFace,faceLocations)

for faceLocation,unknownEncoding in zip(faceLocations,unknownEncodings):
    top,right,bottom,left=faceLocation
    print(faceLocation)
    cv2.rectangle(unknownFaceBGR,(left,top),(right,bottom),(255,0,0),3)
    name='Unknown Person'
    matches=FR.compare_faces(knownEncodings,unknownEncoding)
    print(matches)
    if True in matches:
        matchIndex=matches.index(True)
        print(matchIndex)
        print(names[matchIndex])
        name=names[matchIndex]
    cv2.putText(unknownFaceBGR,name,(left,top),font,.75,(0,0,255),2)

cv2.imshow('My Faces',unknownFaceBGR)

cv2.waitKey(10000)

import cv2

import face_recognition as FR

font=cv2.FONT_HERSHEY_SIMPLEX

donFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Donald Trump.jpg')

faceLoc=FR.face_locations(donFace)[0]

donFaceEncode=FR.face_encodings(donFace)[0]

nancyFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Nancy Pelosi.jpg')

faceLoc=FR.face_locations(nancyFace)[0]

nancyFaceEncode=FR.face_encodings(nancyFace)[0]

penceFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/known/Mike Pence.jpg')

faceLoc=FR.face_locations(penceFace)[0]

penceFaceEncode=FR.face_encodings(penceFace)[0]

knownEncodings=[donFaceEncode,nancyFaceEncode,penceFaceEncode]

names=['Donald Trump','Nancy Pelosi','Mike Pence']

unknownFace=FR.load_image_file('C:/Users/Valued Customer/Documents/Python/demoImages/unknown/u1.jpg')

unknownFaceBGR=cv2.cvtColor(unknownFace,cv2.COLOR_RGB2BGR)

faceLocations=FR.face_locations(unknownFace)

unknownEncodings=FR.face_encodings(unknownFace,faceLocations)

for faceLocation,unknownEncoding in zip(faceLocations,unknownEncodings):

top,right,bottom,left=faceLocation

print(faceLocation)

cv2.rectangle(unknownFaceBGR,(left,top),(right,bottom),(255,0,0),3)

name='Unknown Person'

matches=FR.compare_faces(knownEncodings,unknownEncoding)

print(matches)

if True in matches:

matchIndex=matches.index(True)

print(matchIndex)

print(names[matchIndex])

name=names[matchIndex]

cv2.putText(unknownFaceBGR,name,(left,top),font,.75,(0,0,255),2)

cv2.imshow('My Faces',unknownFaceBGR)

cv2.waitKey(10000)

OpenCV, Python

Using Contours in OpenCV to Track an Object of Interest

October 5, 2021 admin

In this lesson we showed how to track on object in openCV based on color, create contours for the object of interests, and then track the object of interest by drawing a bounding box around it. For your convenience, the code is included below.

import numpy as np
import cv2
print(cv2.__version__)
hueLow=90
hueHigh=100

hueLow2=90
hueHigh2=100

satLow=20
satHigh=200
valLow=20
valHigh=200
def onTrack1(val):
    global hueLow
    hueLow=val
    print('Low Hue: ',val)
def onTrack2(val):
    global hueHigh
    hueHigh=val
    print('High Hue: ',val)
def onTrack3(val):
    global satLow
    satLow=val
    print('Low Sat: ',val)
def onTrack4(val):
    global satHigh
    satHigh=val
    print('High Sat: ',val)
def onTrack5(val):
    global valLow
    valLow=val
    print('Low Val: ',val)
def onTrack6(val):
    global valHigh
    valHigh=val
    print('High Val: ',val)


def onTrack7(val):
    global hueLow2
    hueLow2=val
    print('Low Hue2: ',val)
def onTrack8(val):
    global hueHigh2
    hueHigh2=val
    print('High Hue2: ',val)


width=960
height=540
cam=cv2.VideoCapture(0)
cam.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG')) 
cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
cv2.namedWindow('myTracker')
cv2.moveWindow('myTracker',width,0)
cv2.resizeWindow('myTracker',400,500)
cv2.createTrackbar('Hue Low','myTracker',15,180,onTrack1)
cv2.createTrackbar('Hue High','myTracker',30,180,onTrack2)

cv2.createTrackbar('Hue Low2','myTracker',50,180,onTrack7)
cv2.createTrackbar('Hue High2','myTracker',60,180,onTrack8)

cv2.createTrackbar('Sat Low','myTracker',10,255,onTrack3)
cv2.createTrackbar('Sat High','myTracker',255,255,onTrack4)
cv2.createTrackbar('Val Low','myTracker',10,255,onTrack5)
cv2.createTrackbar('Val High','myTracker',255,255,onTrack6)


while True:
    ignore,  frame = cam.read()
    frameHSV=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)

    lowerBound=np.array([hueLow,satLow,valLow])
    upperBound=np.array([hueHigh,satHigh,valHigh])

    lowerBound2=np.array([hueLow2,satLow,valLow])
    upperBound2=np.array([hueHigh2,satHigh,valHigh])

    myMask=cv2.inRange(frameHSV,lowerBound,upperBound)
    myMask2=cv2.inRange(frameHSV,lowerBound2,upperBound2)

    myMask=myMask | myMask2
    #myMask=cv2.add(myMask,myMask2)
    #myMask=np.logical_or(myMask,myMask2)
    contours,junk=cv2.findContours(myMask,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
    #cv2.drawContours(frame,contours,-1,(255,0,0),3)
    
    for contour in contours:
        area=cv2.contourArea(contour)
        if area>=200:
            #cv2.drawContours(frame,[contour],0,(255,0,0),3)
            x,y,w,h=cv2.boundingRect(contour)
            cv2.rectangle(frame,(x,y),(x+w,y+h),(0,0,255),3)
    
    #myMask=cv2.bitwise_not(myMask)
    myMaskSmall=cv2.resize(myMask,(int(width/2),int(height/2)))
    mySelection=cv2.bitwise_and(frame,frame, mask=myMask)
    mySelection=cv2.resize(mySelection,(int(width/2),int(height/2)))
    cv2.imshow('My Selection', mySelection)
    cv2.moveWindow('My Selection',int(width/2),height)

    cv2.imshow('My Mask', myMaskSmall)
    cv2.moveWindow('My Mask',0,height)
    cv2.imshow('my WEBcam',frame)
    cv2.moveWindow('my WEBcam',0,0)
    if cv2.waitKey(1) & 0xff ==ord('q'):
        break
cam.release()

100

101

102

103

104

105

106

107

108

109

110

import numpy as np

import cv2

print(cv2.__version__)

hueLow=90

hueHigh=100

hueLow2=90

hueHigh2=100

satLow=20

satHigh=200

valLow=20

valHigh=200

def onTrack1(val):

global hueLow

hueLow=val

print('Low Hue: ',val)

def onTrack2(val):

global hueHigh

hueHigh=val

print('High Hue: ',val)

def onTrack3(val):

global satLow

satLow=val

print('Low Sat: ',val)

def onTrack4(val):

global satHigh

satHigh=val

print('High Sat: ',val)

def onTrack5(val):

global valLow

valLow=val

print('Low Val: ',val)

def onTrack6(val):

global valHigh

valHigh=val

print('High Val: ',val)

def onTrack7(val):

global hueLow2

hueLow2=val

print('Low Hue2: ',val)

def onTrack8(val):

global hueHigh2

hueHigh2=val

print('High Hue2: ',val)

width=960

height=540

cam=cv2.VideoCapture(0)

cam.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG'))

cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)

cam.set(cv2.CAP_PROP_FRAME_HEIGHT, height)

cv2.namedWindow('myTracker')

cv2.moveWindow('myTracker',width,0)

cv2.resizeWindow('myTracker',400,500)

cv2.createTrackbar('Hue Low','myTracker',15,180,onTrack1)

cv2.createTrackbar('Hue High','myTracker',30,180,onTrack2)

cv2.createTrackbar('Hue Low2','myTracker',50,180,onTrack7)

cv2.createTrackbar('Hue High2','myTracker',60,180,onTrack8)

cv2.createTrackbar('Sat Low','myTracker',10,255,onTrack3)

cv2.createTrackbar('Sat High','myTracker',255,255,onTrack4)

cv2.createTrackbar('Val Low','myTracker',10,255,onTrack5)

cv2.createTrackbar('Val High','myTracker',255,255,onTrack6)

while True:

ignore, frame = cam.read()

frameHSV=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)

lowerBound=np.array([hueLow,satLow,valLow])

upperBound=np.array([hueHigh,satHigh,valHigh])

lowerBound2=np.array([hueLow2,satLow,valLow])

upperBound2=np.array([hueHigh2,satHigh,valHigh])

myMask=cv2.inRange(frameHSV,lowerBound,upperBound)

myMask2=cv2.inRange(frameHSV,lowerBound2,upperBound2)

myMask=myMask | myMask2

#myMask=cv2.add(myMask,myMask2)

#myMask=np.logical_or(myMask,myMask2)

contours,junk=cv2.findContours(myMask,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

#cv2.drawContours(frame,contours,-1,(255,0,0),3)

for contour in contours:

area=cv2.contourArea(contour)

if area>=200:

#cv2.drawContours(frame,[contour],0,(255,0,0),3)

x,y,w,h=cv2.boundingRect(contour)

cv2.rectangle(frame,(x,y),(x+w,y+h),(0,0,255),3)

#myMask=cv2.bitwise_not(myMask)

myMaskSmall=cv2.resize(myMask,(int(width/2),int(height/2)))

mySelection=cv2.bitwise_and(frame,frame, mask=myMask)

mySelection=cv2.resize(mySelection,(int(width/2),int(height/2)))

cv2.imshow('My Selection', mySelection)

cv2.moveWindow('My Selection',int(width/2),height)

cv2.imshow('My Mask', myMaskSmall)

cv2.moveWindow('My Mask',0,height)

cv2.imshow('my WEBcam',frame)

cv2.moveWindow('my WEBcam',0,0)

if cv2.waitKey(1) & 0xff ==ord('q'):

break

cam.release()

Python

Tracking an Object Based on Color in OpenCV

September 28, 2021 admin

In this lesson I describe how to track an object in OpenCV based on color. We use the HSV color space to make it simpler to train the model. Below, for your convenience, we include the code we develop in this lesson.

import numpy as np
import cv2
print(cv2.__version__)

def onTrack1(val):
    global hueLow
    hueLow=val
    print('Hue Low',hueLow)
def onTrack2(val):
    global hueHigh
    hueHigh=val
    print('Hue High',hueHigh)
def onTrack3(val):
    global satLow
    satLow=val
    print('Sat Low',satLow)
def onTrack4(val):
    global satHigh
    satHigh=val
    print('Sat High',satHigh)
def onTrack5(val):
    global valLow
    valLow=val
    print('Val Low',valLow)
def onTrack6(val):
    global valHigh
    valHigh=val
    print('Val High',valHigh)

width=640
height=360
cam=cv2.VideoCapture(0,cv2.CAP_DSHOW)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT,height)
cam.set(cv2.CAP_PROP_FPS, 30)
cam.set(cv2.CAP_PROP_FOURCC,cv2.VideoWriter_fourcc(*'MJPG'))

cv2.namedWindow('myTracker')
cv2.moveWindow('myTracker',width,0)

hueLow=10
hueHigh=20
satLow=10
satHigh=250
valLow=10
valHigh=250

cv2.createTrackbar('Hue Low','myTracker',10,179,onTrack1)
cv2.createTrackbar('Hue High','myTracker',20,179,onTrack2)
cv2.createTrackbar('Sat Low','myTracker',10,255,onTrack3)
cv2.createTrackbar('Sat High','myTracker',250,255,onTrack4)
cv2.createTrackbar('Val Low','myTracker',10,255,onTrack5)
cv2.createTrackbar('Val High','myTracker',250,255,onTrack6)

while True:
    ignore,  frame = cam.read()
    frameHSV=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
    lowerBound=np.array([hueLow,satLow,valLow])
    upperBound=np.array([hueHigh,satHigh,valHigh])
    myMask=cv2.inRange(frameHSV,lowerBound,upperBound)
    #myMask=cv2.bitwise_not(myMask)
    myObject=cv2.bitwise_and(frame,frame,mask=myMask)
    myObjectSmall=cv2.resize(myObject,(int(width/2),int(height/2)))
    cv2.imshow('My Object',myObjectSmall)
    cv2.moveWindow('My Object',int(width/2),int(height))
    myMaskSmall=cv2.resize(myMask,(int(width/2),int(height/2)))
    cv2.imshow('My Mask',myMaskSmall)
    cv2.moveWindow('My Mask',0,height)
    cv2.imshow('my WEBcam', frame)
    cv2.moveWindow('my WEBcam',0,0)
    if cv2.waitKey(1) & 0xff ==ord('q'):
        break
cam.release()

import numpy as np

import cv2

print(cv2.__version__)

def onTrack1(val):

global hueLow

hueLow=val

print('Hue Low',hueLow)

def onTrack2(val):

global hueHigh

hueHigh=val

print('Hue High',hueHigh)

def onTrack3(val):

global satLow

satLow=val

print('Sat Low',satLow)

def onTrack4(val):

global satHigh

satHigh=val

print('Sat High',satHigh)

def onTrack5(val):

global valLow

valLow=val

print('Val Low',valLow)

def onTrack6(val):

global valHigh

valHigh=val

print('Val High',valHigh)

width=640

height=360

cam=cv2.VideoCapture(0,cv2.CAP_DSHOW)

cam.set(cv2.CAP_PROP_FRAME_WIDTH, width)

cam.set(cv2.CAP_PROP_FRAME_HEIGHT,height)

cam.set(cv2.CAP_PROP_FPS, 30)

cam.set(cv2.CAP_PROP_FOURCC,cv2.VideoWriter_fourcc(*'MJPG'))

cv2.namedWindow('myTracker')

cv2.moveWindow('myTracker',width,0)

hueLow=10

hueHigh=20

satLow=10

satHigh=250

valLow=10

valHigh=250

cv2.createTrackbar('Hue Low','myTracker',10,179,onTrack1)

cv2.createTrackbar('Hue High','myTracker',20,179,onTrack2)

cv2.createTrackbar('Sat Low','myTracker',10,255,onTrack3)

cv2.createTrackbar('Sat High','myTracker',250,255,onTrack4)

cv2.createTrackbar('Val Low','myTracker',10,255,onTrack5)

cv2.createTrackbar('Val High','myTracker',250,255,onTrack6)

while True:

ignore, frame = cam.read()

frameHSV=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)

lowerBound=np.array([hueLow,satLow,valLow])

upperBound=np.array([hueHigh,satHigh,valHigh])

myMask=cv2.inRange(frameHSV,lowerBound,upperBound)

#myMask=cv2.bitwise_not(myMask)

myObject=cv2.bitwise_and(frame,frame,mask=myMask)

myObjectSmall=cv2.resize(myObject,(int(width/2),int(height/2)))

cv2.imshow('My Object',myObjectSmall)

cv2.moveWindow('My Object',int(width/2),int(height))

myMaskSmall=cv2.resize(myMask,(int(width/2),int(height/2)))

cv2.imshow('My Mask',myMaskSmall)

cv2.moveWindow('My Mask',0,height)

cv2.imshow('my WEBcam', frame)

cv2.moveWindow('my WEBcam',0,0)

if cv2.waitKey(1) & 0xff ==ord('q'):

break

cam.release()

Technology Tutorials

Tag Archives: Artificial intelligence

Object Detection Using YOLO and RTSP Camera on Raspberry Pi 5

AI FOR EVERYONE HOMEWORK SOLUTION: Face Recognition with Live Video in OpenCV

AI for Everyone LESSON 16: Face Recognition with OpenCV

Using Contours in OpenCV to Track an Object of Interest

Tracking an Object Based on Color in OpenCV

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