Tag Archives: AI

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

# 6. Install MediaPipe
pip install mediapipe --break

# Verify MediaPipe
python3 -c "import mediapipe as mp; print('MediaPipe version:', mp.__version__)"

# 7. 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

# 6. Install MediaPipe

pip install mediapipe --break

# Verify MediaPipe

python3 -c "import mediapipe as mp; print('MediaPipe version:', mp.__version__)"

# 7. 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
RTSP_URL = "rtsp://user:password@192.168.88.44:554/cam/realmonitor?channel=1&subtype=0"
#RTSP_URL = secret.RTSP_URL1
# 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
print("Program Terminated")

import cv2

from ultralytics import YOLO

#import secret

import threading

import time

W=1280

H=720

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

#RTSP_URL = secret.RTSP_URL1

# 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

print("Program Terminated")

The video explains everything, please watch it!

Artificial Intelligence, OpenCV

AI for Everyone LESSON 29: Control of Real World Objects with Gesture Recognition in Mediapipe

February 24, 2022 admin

In this video lesson we show you how you can control objects in the real world using OpenCV, Python, Mediapipa and our old friend, the Arduino. On the Python side, we recognize hand gestures, and then we pass the recognized gesture to Arduino and Arduino lights LED in response to what hand signal is seen. This is a simple example, but a very powerful method. Instead of LED, you could operate servos, stepper motors or relays to control any manner of different devices. For your convenience, this is the code we used on the Arduino side:

String cmd;
int LED1=9;
int LED2=6;
int LED3=5;
int LED4=3;
int LED5=10;
void setup() {
  pinMode(LED1,OUTPUT);
  pinMode(LED2,OUTPUT);
  pinMode(LED3,OUTPUT);
   pinMode(LED4,OUTPUT);
   pinMode(LED5,OUTPUT);
 Serial.begin(115200);

}
void loop() {
 while (Serial.available()==0){
 
 }
 cmd = Serial.readStringUntil('\r');
if (cmd=="One"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,LOW);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,LOW);
}
if (cmd=="Two"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,HIGH);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,LOW);
}
 if (cmd=="Three"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,HIGH);
  digitalWrite(LED3,HIGH);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,LOW);
 }
 if (cmd=="Four"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,HIGH);
  digitalWrite(LED3,HIGH);
  digitalWrite(LED4,HIGH);
  digitalWrite(LED5,LOW);
 }
 if (cmd=="Five"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,HIGH);
  digitalWrite(LED3,HIGH);
  digitalWrite(LED4,HIGH);
  digitalWrite(LED5,HIGH);

 }

 if (cmd=="Pinky"){
  digitalWrite(LED1,LOW);
  digitalWrite(LED2,LOW);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,HIGH);
  digitalWrite(LED5,LOW);

 }
  if (cmd=="Thumb"){
  digitalWrite(LED1,LOW);
  digitalWrite(LED2,LOW);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,HIGH);

 }
  if (cmd=="Inside"){
  digitalWrite(LED1,LOW);
  digitalWrite(LED2,HIGH);
  digitalWrite(LED3,HIGH);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,LOW);

 }
   if (cmd=="Outside"){
  digitalWrite(LED1,HIGH);
  digitalWrite(LED2,LOW);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,HIGH);
  digitalWrite(LED5,LOW);

 }
    if (cmd=="Unknown"){
  digitalWrite(LED1,LOW);
  digitalWrite(LED2,LOW);
  digitalWrite(LED3,LOW);
  digitalWrite(LED4,LOW);
  digitalWrite(LED5,LOW);

 }
}

String cmd;

int LED1=9;

int LED2=6;

int LED3=5;

int LED4=3;

int LED5=10;

void setup() {

pinMode(LED1,OUTPUT);

pinMode(LED2,OUTPUT);

pinMode(LED3,OUTPUT);

pinMode(LED4,OUTPUT);

pinMode(LED5,OUTPUT);

Serial.begin(115200);

}

void loop() {

while (Serial.available()==0){

}

cmd = Serial.readStringUntil('\r');

if (cmd=="One"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,LOW);

digitalWrite(LED3,LOW);

digitalWrite(LED4,LOW);

digitalWrite(LED5,LOW);

}

if (cmd=="Two"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,HIGH);

digitalWrite(LED3,LOW);

digitalWrite(LED4,LOW);

digitalWrite(LED5,LOW);

}

if (cmd=="Three"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,HIGH);

digitalWrite(LED3,HIGH);

digitalWrite(LED4,LOW);

digitalWrite(LED5,LOW);

}

if (cmd=="Four"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,HIGH);

digitalWrite(LED3,HIGH);

digitalWrite(LED4,HIGH);

digitalWrite(LED5,LOW);

}

if (cmd=="Five"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,HIGH);

digitalWrite(LED3,HIGH);

digitalWrite(LED4,HIGH);

digitalWrite(LED5,HIGH);

}

if (cmd=="Pinky"){

digitalWrite(LED1,LOW);

digitalWrite(LED2,LOW);

digitalWrite(LED3,LOW);

digitalWrite(LED4,HIGH);

digitalWrite(LED5,LOW);

}

if (cmd=="Thumb"){

digitalWrite(LED1,LOW);

digitalWrite(LED2,LOW);

digitalWrite(LED3,LOW);

digitalWrite(LED4,LOW);

digitalWrite(LED5,HIGH);

}

if (cmd=="Inside"){

digitalWrite(LED1,LOW);

digitalWrite(LED2,HIGH);

digitalWrite(LED3,HIGH);

digitalWrite(LED4,LOW);

digitalWrite(LED5,LOW);

}

if (cmd=="Outside"){

digitalWrite(LED1,HIGH);

digitalWrite(LED2,LOW);

digitalWrite(LED3,LOW);

digitalWrite(LED4,HIGH);

digitalWrite(LED5,LOW);

}

if (cmd=="Unknown"){

digitalWrite(LED1,LOW);

digitalWrite(LED2,LOW);

digitalWrite(LED3,LOW);

digitalWrite(LED4,LOW);

digitalWrite(LED5,LOW);

}

And on the python side, we used the following code.

import time
import cv2
print(cv2.__version__)
import numpy as np
import pickle
import serial

arduinoData = serial.Serial('COM3',115200)

class mpHands:
    import mediapipe as mp
    def __init__(self,maxHands=2,tol1=.5,tol2=.5):
        self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)
    def Marks(self,frame):
        myHands=[]
        frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
        results=self.hands.process(frameRGB)
        if results.multi_hand_landmarks != None:
            for handLandMarks in results.multi_hand_landmarks:
                myHand=[]
                for landMark in handLandMarks.landmark:
                    myHand.append((int(landMark.x*width),int(landMark.y*height)))
                myHands.append(myHand)
        return myHands
def findDistances(handData):
    distMatrix=np.zeros([len(handData),len(handData)],dtype='float')
    palmSize=((handData[0][0]-handData[9][0])**2+(handData[0][1]-handData[9][1])**2)**(1./2.)
    for row in range(0,len(handData)):
        for column in range(0,len(handData)):
            distMatrix[row][column]=(((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.))/palmSize
    return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):
    error=0
    for row in keyPoints:
        for column in keyPoints:
            error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])
    print(error)
    return error
def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):
    errorArray=[]
    for i in range(0,len(gestNames),1):
        error=findError(knownGestures[i],unknownGesture,keyPoints)
        errorArray.append(error)
    errorMin=errorArray[0]
    minIndex=0
    for i in range(0,len(errorArray),1):
        if errorArray[i]<errorMin:
            errorMin=errorArray[i]
            minIndex=i
    if errorMin<tol:
        gesture=gestNames[minIndex]
    if errorMin>=tol:
        gesture='Unknown'
    return gesture

width=1280
height=720
cam=cv2.VideoCapture(3,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'))
findHands=mpHands(1)
time.sleep(5)
keyPoints=[0,4,5,9,13,17,8,12,16,20]

train=int(input('Enter 1 to Train, Enter 0 to Recognize '))
if train==1:
    trainCnt=0
    knownGestures=[]
    numGest=int(input('How Many Gestures Do You Want? '))
    gestNames=[]
    for i in range(0,numGest,1):
        prompt='Name of Gesture #'+str(i+1)+' '
        name=input(prompt)
        gestNames.append(name)
    print(gestNames)
    trainName=input('Filename for training data? (Press Enter for Default) ')
    if trainName=='':
        trainName='default'
    trainName=trainName+'.pkl'
if train==0:
    trainName=input('What Training Data Do You Want to Use? (Press Enter for Default) ')
    if trainName=='':
        trainName='default'
    trainName=trainName+'.pkl'
    with open(trainName,'rb') as f:
        gestNames=pickle.load(f)
        knownGestures=pickle.load(f)

tol=10

while True:
    ignore,  frame = cam.read()
    frame=cv2.resize(frame,(width,height))
    handData=findHands.Marks(frame)
    if train==1:
        if handData!=[]:
            print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')
            if cv2.waitKey(1) & 0xff==ord('t'):
                knownGesture=findDistances(handData[0])
                knownGestures.append(knownGesture)
                trainCnt=trainCnt+1
                if trainCnt==numGest:
                    train=0
                    with open(trainName,'wb') as f:
                        pickle.dump(gestNames,f)
                        pickle.dump(knownGestures,f)
    if train == 0:
        if handData!=[]:
            unknownGesture=findDistances(handData[0])
            myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)
            #error=findError(knownGesture,unknownGesture,keyPoints)
            cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)
            myGesture=myGesture+'\r'
            arduinoData.write(myGesture.encode())
    for hand in handData:
        for ind in keyPoints:
            cv2.circle(frame,hand[ind],25,(255,0,255),3)
    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

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

import time

import cv2

print(cv2.__version__)

import numpy as np

import pickle

import serial

arduinoData = serial.Serial('COM3',115200)

class mpHands:

import mediapipe as mp

def __init__(self,maxHands=2,tol1=.5,tol2=.5):

self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)

def Marks(self,frame):

myHands=[]

frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

results=self.hands.process(frameRGB)

if results.multi_hand_landmarks != None:

for handLandMarks in results.multi_hand_landmarks:

myHand=[]

for landMark in handLandMarks.landmark:

myHand.append((int(landMark.x*width),int(landMark.y*height)))

myHands.append(myHand)

return myHands

def findDistances(handData):

distMatrix=np.zeros([len(handData),len(handData)],dtype='float')

palmSize=((handData[0][0]-handData[9][0])**2+(handData[0][1]-handData[9][1])**2)**(1./2.)

for row in range(0,len(handData)):

for column in range(0,len(handData)):

distMatrix[row][column]=(((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.))/palmSize

return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):

error=0

for row in keyPoints:

for column in keyPoints:

error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])

print(error)

return error

def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):

errorArray=[]

for i in range(0,len(gestNames),1):

error=findError(knownGestures[i],unknownGesture,keyPoints)

errorArray.append(error)

errorMin=errorArray[0]

minIndex=0

for i in range(0,len(errorArray),1):

if errorArray[i]<errorMin:

errorMin=errorArray[i]

minIndex=i

if errorMin<tol:

gesture=gestNames[minIndex]

if errorMin>=tol:

gesture='Unknown'

return gesture

width=1280

height=720

cam=cv2.VideoCapture(3,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'))

findHands=mpHands(1)

time.sleep(5)

keyPoints=[0,4,5,9,13,17,8,12,16,20]

train=int(input('Enter 1 to Train, Enter 0 to Recognize '))

if train==1:

trainCnt=0

knownGestures=[]

numGest=int(input('How Many Gestures Do You Want? '))

gestNames=[]

for i in range(0,numGest,1):

prompt='Name of Gesture #'+str(i+1)+' '

name=input(prompt)

gestNames.append(name)

print(gestNames)

trainName=input('Filename for training data? (Press Enter for Default) ')

if trainName=='':

trainName='default'

trainName=trainName+'.pkl'

if train==0:

trainName=input('What Training Data Do You Want to Use? (Press Enter for Default) ')

if trainName=='':

trainName='default'

trainName=trainName+'.pkl'

with open(trainName,'rb') as f:

gestNames=pickle.load(f)

knownGestures=pickle.load(f)

tol=10

while True:

ignore, frame = cam.read()

frame=cv2.resize(frame,(width,height))

handData=findHands.Marks(frame)

if train==1:

if handData!=[]:

print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')

if cv2.waitKey(1) & 0xff==ord('t'):

knownGesture=findDistances(handData[0])

knownGestures.append(knownGesture)

trainCnt=trainCnt+1

if trainCnt==numGest:

train=0

with open(trainName,'wb') as f:

pickle.dump(gestNames,f)

pickle.dump(knownGestures,f)

if train == 0:

if handData!=[]:

unknownGesture=findDistances(handData[0])

myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)

#error=findError(knownGesture,unknownGesture,keyPoints)

cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)

myGesture=myGesture+'\r'

arduinoData.write(myGesture.encode())

for hand in handData:

for ind in keyPoints:

cv2.circle(frame,hand[ind],25,(255,0,255),3)

cv2.imshow('my WEBcam', frame)

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

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

break

cam.release()

Artificial Intelligence, OpenCV, Python, Tutorial

Improved Gesture Recognition in Python and MediaPipe

February 10, 2022 admin

In this video lesson we show you how you can improve the accuracy of your gesture recognition program developed in the last lesson. We do this by normalizing the hand landmarks distance matrix to a standard size. By doing this, you get accurate results independent of the distance your hand is from the camera. For your convenience, I include the code below which we develop in this lesson. Enjoy!

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

class mpHands:
    import mediapipe as mp
    def __init__(self,maxHands=2,tol1=.5,tol2=.5):
        self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)
    def Marks(self,frame):
        myHands=[]
        frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
        results=self.hands.process(frameRGB)
        if results.multi_hand_landmarks != None:
            for handLandMarks in results.multi_hand_landmarks:
                myHand=[]
                for landMark in handLandMarks.landmark:
                    myHand.append((int(landMark.x*width),int(landMark.y*height)))
                myHands.append(myHand)
        return myHands
def findDistances(handData):
    distMatrix=np.zeros([len(handData),len(handData)],dtype='float')
    palmSize=((handData[0][0]-handData[9][0])**2+(handData[0][1]-handData[9][1])**2)**(1./2.)
    for row in range(0,len(handData)):
        for column in range(0,len(handData)):
            distMatrix[row][column]=(((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.))/palmSize
    return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):
    error=0
    for row in keyPoints:
        for column in keyPoints:
            error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])
    print(error)
    return error
def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):
    errorArray=[]
    for i in range(0,len(gestNames),1):
        error=findError(knownGestures[i],unknownGesture,keyPoints)
        errorArray.append(error)
    errorMin=errorArray[0]
    minIndex=0
    for i in range(0,len(errorArray),1):
        if errorArray[i]<errorMin:
            errorMin=errorArray[i]
            minIndex=i
    if errorMin<tol:
        gesture=gestNames[minIndex]
    if errorMin>=tol:
        gesture='Unknown'
    return gesture


width=1280
height=720
cam=cv2.VideoCapture(4,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'))
findHands=mpHands(1)
time.sleep(5)
keyPoints=[0,4,5,9,13,17,8,12,16,20]
train=True
tol=10
trainCnt=0
knownGestures=[]

numGest=int(input('How Many Gestures Do You Want? '))

gestNames=[]

for i in range(0,numGest,1):
    prompt='Name of Gesture #'+str(i+1)+' '
    name=input(prompt)
    gestNames.append(name)
print(gestNames)

while True:
    ignore,  frame = cam.read()
    frame=cv2.resize(frame,(width,height))
    handData=findHands.Marks(frame)
    if train==True:
        if handData!=[]:
            print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')
            if cv2.waitKey(1) & 0xff==ord('t'):
                knownGesture=findDistances(handData[0])
                knownGestures.append(knownGesture)
                trainCnt=trainCnt+1
                if trainCnt==numGest:
                    train=False
    if train == False:
        if handData!=[]:
            unknownGesture=findDistances(handData[0])
            myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)
            #error=findError(knownGesture,unknownGesture,keyPoints)
            cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)
    for hand in handData:
        for ind in keyPoints:
            cv2.circle(frame,hand[ind],25,(255,0,255),3)
    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

import time

import cv2

print(cv2.__version__)

import numpy as np

class mpHands:

import mediapipe as mp

def __init__(self,maxHands=2,tol1=.5,tol2=.5):

self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)

def Marks(self,frame):

myHands=[]

frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

results=self.hands.process(frameRGB)

if results.multi_hand_landmarks != None:

for handLandMarks in results.multi_hand_landmarks:

myHand=[]

for landMark in handLandMarks.landmark:

myHand.append((int(landMark.x*width),int(landMark.y*height)))

myHands.append(myHand)

return myHands

def findDistances(handData):

distMatrix=np.zeros([len(handData),len(handData)],dtype='float')

palmSize=((handData[0][0]-handData[9][0])**2+(handData[0][1]-handData[9][1])**2)**(1./2.)

for row in range(0,len(handData)):

for column in range(0,len(handData)):

distMatrix[row][column]=(((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.))/palmSize

return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):

error=0

for row in keyPoints:

for column in keyPoints:

error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])

print(error)

return error

def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):

errorArray=[]

for i in range(0,len(gestNames),1):

error=findError(knownGestures[i],unknownGesture,keyPoints)

errorArray.append(error)

errorMin=errorArray[0]

minIndex=0

for i in range(0,len(errorArray),1):

if errorArray[i]<errorMin:

errorMin=errorArray[i]

minIndex=i

if errorMin<tol:

gesture=gestNames[minIndex]

if errorMin>=tol:

gesture='Unknown'

return gesture

width=1280

height=720

cam=cv2.VideoCapture(4,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'))

findHands=mpHands(1)

time.sleep(5)

keyPoints=[0,4,5,9,13,17,8,12,16,20]

train=True

tol=10

trainCnt=0

knownGestures=[]

numGest=int(input('How Many Gestures Do You Want? '))

gestNames=[]

for i in range(0,numGest,1):

prompt='Name of Gesture #'+str(i+1)+' '

name=input(prompt)

gestNames.append(name)

print(gestNames)

while True:

ignore, frame = cam.read()

frame=cv2.resize(frame,(width,height))

handData=findHands.Marks(frame)

if train==True:

if handData!=[]:

print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')

if cv2.waitKey(1) & 0xff==ord('t'):

knownGesture=findDistances(handData[0])

knownGestures.append(knownGesture)

trainCnt=trainCnt+1

if trainCnt==numGest:

train=False

if train == False:

if handData!=[]:

unknownGesture=findDistances(handData[0])

myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)

#error=findError(knownGesture,unknownGesture,keyPoints)

cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)

for hand in handData:

for ind in keyPoints:

cv2.circle(frame,hand[ind],25,(255,0,255),3)

cv2.imshow('my WEBcam', frame)

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

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

break

cam.release()

s lesson. Enjoy!

Artificial Intelligence, Python

AI for Everyone LESSON 26: Accurate Gesture Recognition using Python and MediaPipe

February 3, 2022 admin

In this lesson we demonstrate how to use mediaPipe and Python to create an AI system that can accurately recognize hand gestures. This is follow on work to what we developed in Lesson 25. The code we developed is presented below.

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

class mpHands:
    import mediapipe as mp
    def __init__(self,maxHands=2,tol1=.5,tol2=.5):
        self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)
    def Marks(self,frame):
        myHands=[]
        frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
        results=self.hands.process(frameRGB)
        if results.multi_hand_landmarks != None:
            for handLandMarks in results.multi_hand_landmarks:
                myHand=[]
                for landMark in handLandMarks.landmark:
                    myHand.append((int(landMark.x*width),int(landMark.y*height)))
                myHands.append(myHand)
        return myHands
def findDistances(handData):
    distMatrix=np.zeros([len(handData),len(handData)],dtype='float')
    for row in range(0,len(handData)):
        for column in range(0,len(handData)):
            distMatrix[row][column]=((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.)
    return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):
    error=0
    for row in keyPoints:
        for column in keyPoints:
            error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])
    return error
def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):
    errorArray=[]
    for i in range(0,len(gestNames),1):
        error=findError(knownGestures[i],unknownGesture,keyPoints)
        errorArray.append(error)
    errorMin=errorArray[0]
    minIndex=0
    for i in range(0,len(errorArray),1):
        if errorArray[i]<errorMin:
            errorMin=errorArray[i]
            minIndex=i
    if errorMin<tol:
        gesture=gestNames[minIndex]
    if errorMin>=tol:
        gesture='Unknown'
    return gesture


width=1280
height=720
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'))
findHands=mpHands(1)
time.sleep(5)
keyPoints=[0,4,5,9,13,17,8,12,16,20]
train=True
tol=1500
trainCnt=0
knownGestures=[]

numGest=int(input('How Many Gestures Do You Want? '))

gestNames=[]

for i in range(0,numGest,1):
    prompt='Name of Gesture #'+str(i+1)+' '
    name=input(prompt)
    gestNames.append(name)
print(gestNames)

while True:
    ignore,  frame = cam.read()
    frame=cv2.resize(frame,(width,height))
    handData=findHands.Marks(frame)
    if train==True:
        if handData!=[]:
            print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')
            if cv2.waitKey(1) & 0xff==ord('t'):
                knownGesture=findDistances(handData[0])
                knownGestures.append(knownGesture)
                trainCnt=trainCnt+1
                if trainCnt==numGest:
                    train=False
    if train == False:
        if handData!=[]:
            unknownGesture=findDistances(handData[0])
            myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)
            #error=findError(knownGesture,unknownGesture,keyPoints)
            cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)
    for hand in handData:
        for ind in keyPoints:
            cv2.circle(frame,hand[ind],25,(255,0,255),3)
    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

import time

import cv2

print(cv2.__version__)

import numpy as np

class mpHands:

import mediapipe as mp

def __init__(self,maxHands=2,tol1=.5,tol2=.5):

self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)

def Marks(self,frame):

myHands=[]

frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

results=self.hands.process(frameRGB)

if results.multi_hand_landmarks != None:

for handLandMarks in results.multi_hand_landmarks:

myHand=[]

for landMark in handLandMarks.landmark:

myHand.append((int(landMark.x*width),int(landMark.y*height)))

myHands.append(myHand)

return myHands

def findDistances(handData):

distMatrix=np.zeros([len(handData),len(handData)],dtype='float')

for row in range(0,len(handData)):

for column in range(0,len(handData)):

distMatrix[row][column]=((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.)

return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):

error=0

for row in keyPoints:

for column in keyPoints:

error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])

return error

def findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol):

errorArray=[]

for i in range(0,len(gestNames),1):

error=findError(knownGestures[i],unknownGesture,keyPoints)

errorArray.append(error)

errorMin=errorArray[0]

minIndex=0

for i in range(0,len(errorArray),1):

if errorArray[i]<errorMin:

errorMin=errorArray[i]

minIndex=i

if errorMin<tol:

gesture=gestNames[minIndex]

if errorMin>=tol:

gesture='Unknown'

return gesture

width=1280

height=720

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'))

findHands=mpHands(1)

time.sleep(5)

keyPoints=[0,4,5,9,13,17,8,12,16,20]

train=True

tol=1500

trainCnt=0

knownGestures=[]

numGest=int(input('How Many Gestures Do You Want? '))

gestNames=[]

for i in range(0,numGest,1):

prompt='Name of Gesture #'+str(i+1)+' '

name=input(prompt)

gestNames.append(name)

print(gestNames)

while True:

ignore, frame = cam.read()

frame=cv2.resize(frame,(width,height))

handData=findHands.Marks(frame)

if train==True:

if handData!=[]:

print('Please Show Gesture ',gestNames[trainCnt],': Press t when Ready')

if cv2.waitKey(1) & 0xff==ord('t'):

knownGesture=findDistances(handData[0])

knownGestures.append(knownGesture)

trainCnt=trainCnt+1

if trainCnt==numGest:

train=False

if train == False:

if handData!=[]:

unknownGesture=findDistances(handData[0])

myGesture=findGesture(unknownGesture,knownGestures,keyPoints,gestNames,tol)

#error=findError(knownGesture,unknownGesture,keyPoints)

cv2.putText(frame,myGesture,(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)

for hand in handData:

for ind in keyPoints:

cv2.circle(frame,hand[ind],25,(255,0,255),3)

cv2.imshow('my WEBcam', frame)

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

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

break

cam.release()

Artificial Intelligence, Python

AI for Everyone LESSON 25: First Attempt at Using MediaPipe for Gesture Detection

January 27, 2022 admin

In this lesson we describe what our approach will be to creating a gesture detection and recognition algorithm using mediaPipe. We will demonstrate the algorithm with some simple code demos. In future lessons we will further develop the algorithm. The code below is the initial algorithm developed in this video. Enjoy!

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

class mpHands:
    import mediapipe as mp
    def __init__(self,maxHands=2,tol1=.5,tol2=.5):
        self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)
    def Marks(self,frame):
        myHands=[]
        frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
        results=self.hands.process(frameRGB)
        if results.multi_hand_landmarks != None:
            for handLandMarks in results.multi_hand_landmarks:
                myHand=[]
                for landMark in handLandMarks.landmark:
                    myHand.append((int(landMark.x*width),int(landMark.y*height)))
                myHands.append(myHand)
        return myHands
def findDistances(handData):
    distMatrix=np.zeros([len(handData),len(handData)],dtype='float')
    for row in range(0,len(handData)):
        for column in range(0,len(handData)):
            distMatrix[row][column]=((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.)
    return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):
    error=0
    for row in keyPoints:
        for column in keyPoints:
            error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])
    return error


width=1280
height=720
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'))
findHands=mpHands(1)

keyPoints=[0,4,5,9,13,17,8,12,16,20]
train=True
while True:
    ignore,  frame = cam.read()
    frame=cv2.resize(frame,(width,height))
    handData=findHands.Marks(frame)
    if train==True:
        if handData!=[]:
            print('Show your Gesture, press t when Ready')
            if cv2.waitKey(1) & 0xff==ord('t'):
                knownGesture=findDistances(handData[0])
                train=False
                print(knownGesture)
    if train == False:
        if handData!=[]:
            unknownGesture=findDistances(handData[0])
            error=findError(knownGesture,unknownGesture,keyPoints)
            cv2.putText(frame,str(int(error,)),(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)
    for hand in handData:
        for ind in keyPoints:
            cv2.circle(frame,hand[ind],25,(255,0,255),3)
    cv2.imshow('my WEBcam', frame)
    cv2.moveWindow('my WEBcam',0,0)
    if cv2.waitKey(1) & 0xff ==ord('q'):
        break
cam.release()

import cv2

print(cv2.__version__)

import numpy as np

class mpHands:

import mediapipe as mp

def __init__(self,maxHands=2,tol1=.5,tol2=.5):

self.hands=self.mp.solutions.hands.Hands(False,maxHands,tol1,tol2)

def Marks(self,frame):

myHands=[]

frameRGB=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

results=self.hands.process(frameRGB)

if results.multi_hand_landmarks != None:

for handLandMarks in results.multi_hand_landmarks:

myHand=[]

for landMark in handLandMarks.landmark:

myHand.append((int(landMark.x*width),int(landMark.y*height)))

myHands.append(myHand)

return myHands

def findDistances(handData):

distMatrix=np.zeros([len(handData),len(handData)],dtype='float')

for row in range(0,len(handData)):

for column in range(0,len(handData)):

distMatrix[row][column]=((handData[row][0]-handData[column][0])**2+(handData[row][1]-handData[column][1])**2)**(1./2.)

return distMatrix

def findError(gestureMatrix,unknownMatrix,keyPoints):

error=0

for row in keyPoints:

for column in keyPoints:

error=error+abs(gestureMatrix[row][column]-unknownMatrix[row][column])

return error

width=1280

height=720

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'))

findHands=mpHands(1)

keyPoints=[0,4,5,9,13,17,8,12,16,20]

train=True

while True:

ignore, frame = cam.read()

frame=cv2.resize(frame,(width,height))

handData=findHands.Marks(frame)

if train==True:

if handData!=[]:

print('Show your Gesture, press t when Ready')

if cv2.waitKey(1) & 0xff==ord('t'):

knownGesture=findDistances(handData[0])

train=False

print(knownGesture)

if train == False:

if handData!=[]:

unknownGesture=findDistances(handData[0])

error=findError(knownGesture,unknownGesture,keyPoints)

cv2.putText(frame,str(int(error,)),(100,175),cv2.FONT_HERSHEY_SIMPLEX,3,(255,0,0),8)

for hand in handData:

for ind in keyPoints:

cv2.circle(frame,hand[ind],25,(255,0,255),3)

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: AI

Object Detection Using YOLO and RTSP Camera on Raspberry Pi 5

AI for Everyone LESSON 29: Control of Real World Objects with Gesture Recognition in Mediapipe

Improved Gesture Recognition in Python and MediaPipe

AI for Everyone LESSON 26: Accurate Gesture Recognition using Python and MediaPipe

AI for Everyone LESSON 25: First Attempt at Using MediaPipe for Gesture Detection

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