Tag Archives: AI

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()

Python

Faster Launch of WEBcam and Smoother Video in OpenCV on Windows

August 12, 2021 admin

This is the code we developed in Video Lesson #6 showing how to launch a webcam quicker and with less delay in OpenCV running on windows. The video above explains the code step by step, but for your convenience, I include the code below.

import cv2
print(cv2.__version__)
width=1280
height=720
cam=cv2.VideoCapture(1,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'))
while True:
    ignore,  frame = cam.read()
    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__)

width=1280

height=720

cam=cv2.VideoCapture(1,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'))

while True:

ignore, frame = cam.read()

cv2.imshow('my WEBcam', frame)

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

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

break

cam.release()

Python

Launch a Windows WEB Camera in Ten Lines of Code with OpenCV

August 4, 2021 admin

In this lesson we show you step-by-step how to launch a WEB camera using OpenCV running on windows. In the video we show how to install OpenCV and how to write your first simple programs. Below is the code we developed in the video to launch the WEB cam.

import cv2
print(cv2.__version__)
cam=cv2.VideoCapture(1)
while True:
    ignore,  frame = cam.read()
    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__)

cam=cv2.VideoCapture(1)

while True:

ignore, frame = cam.read()

cv2.imshow('my WEBcam', frame)

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

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

break

cam.release()

Jetson Nano

AI on the Jetson Nano LESSON 60: Make Your Nano Talk With Text to Speech

September 19, 2020 admin

In this lesson we show you how to teach the NVIDIA Jetson Nano to talk. We show two different ways. In the first, we use the espeak TTS engine. We then show how to do it with gTTS. We compare and contrast the pros and cons of each technique.

Jetson Xavier NX, NVIDIA Jetson Xavier NX

Jetson Xavier NX Lesson 15: Training the Face Recognition Program to Recognize People

August 25, 2020 admin

<span data-mce-type="bookmark" style="display: inline-block; width: 0px; overflow: hidden; line-height: 0;" class="mce_SELRES_start"></span> In this video lesson we should you a simple method to train our face recognizer on larger data sets. We use the python os.walk command to step through, and train automatically on all the training images in our folder. We then show how to store our training set to our SD card using the pickle utility. This allows us to train once, and use the trained model over and over.

For your convenience, the code below is what we developed to allow training our face recognition model.

import face_recognition
import cv2
import os
import pickle
print(cv2.__version__)

Encodings=[]
Names=[]
j=0

image_dir='/home/pjm/Desktop/pyPro/demoimages/known'
for root, dirs, files in os.walk(image_dir):
    print(files)
    for file in files:
        fullPath=os.path.join(root,file)
        print(fullPath)
        name=os.path.splitext(file)[0]
        print(name)
        person=face_recognition.load_image_file(fullPath)
        encoding=face_recognition.face_encodings(person)[0]
        Encodings.append(encoding)
        Names.append(name)
print(Names)
with open('train.pkl','wb') as f:
        pickle.dump(Names,f)
        pickle.dump(Encodings,f)

import face_recognition

import cv2

import os

import pickle

print(cv2.__version__)

Encodings=[]

Names=[]

j=0

image_dir='/home/pjm/Desktop/pyPro/demoimages/known'

for root, dirs, files in os.walk(image_dir):

print(files)

for file in files:

fullPath=os.path.join(root,file)

print(fullPath)

name=os.path.splitext(file)[0]

print(name)

person=face_recognition.load_image_file(fullPath)

encoding=face_recognition.face_encodings(person)[0]

Encodings.append(encoding)

Names.append(name)

print(Names)

with open('train.pkl','wb') as f:

pickle.dump(Names,f)

pickle.dump(Encodings,f)

Then this is a simple program that loads the trained model, and uses it to recognize people in unknown images.

import cv2
print(cv2.__version__)
import face_recognition
import pickle

with open('train.pkl','rb') as f:
    Names=pickle.load(f)
    Encodings=pickle.load(f)

font=cv2.FONT_HERSHEY_SIMPLEX
testImage=face_recognition.load_image_file('/home/pjm/Desktop/pyPro/demoimages/unkno$

facePositions=face_recognition.face_locations(testImage)
allEncodings=face_recognition.face_encodings(testImage,facePositions)

testImage=cv2.cvtColor(testImage,cv2.COLOR_RGB2BGR)
for (top,right,bottom,left), face_encoding in zip(facePositions, allEncodings):
    name='Unknown Life Form'
    matches=face_recognition.compare_faces(Encodings,face_encoding)
    if True in matches:
        first_match_index=matches.index(True)
        name=Names[first_match_index]
    cv2.rectangle(testImage,(left,top),(right,bottom),(255,0,0),2)
    cv2.rectangle(testImage, (left,top),(left+200, top+30),(0,255,255),-1)
    cv2.putText(testImage,name,(left,top+20),font,.75,(255,0,0),2)
cv2.imshow('mywindow',testImage)
cv2.moveWindow('mywindow',0,0)
if cv2.waitKey(0)==ord('q'):
    cv2.destroyAllWindows()

import cv2

print(cv2.__version__)

import face_recognition

import pickle

with open('train.pkl','rb') as f:

Names=pickle.load(f)

Encodings=pickle.load(f)

font=cv2.FONT_HERSHEY_SIMPLEX

testImage=face_recognition.load_image_file('/home/pjm/Desktop/pyPro/demoimages/unkno$

facePositions=face_recognition.face_locations(testImage)

allEncodings=face_recognition.face_encodings(testImage,facePositions)

testImage=cv2.cvtColor(testImage,cv2.COLOR_RGB2BGR)

for (top,right,bottom,left), face_encoding in zip(facePositions, allEncodings):

name='Unknown Life Form'

matches=face_recognition.compare_faces(Encodings,face_encoding)

if True in matches:

first_match_index=matches.index(True)

name=Names[first_match_index]

cv2.rectangle(testImage,(left,top),(right,bottom),(255,0,0),2)

cv2.rectangle(testImage, (left,top),(left+200, top+30),(0,255,255),-1)

cv2.putText(testImage,name,(left,top+20),font,.75,(255,0,0),2)

cv2.imshow('mywindow',testImage)

cv2.moveWindow('mywindow',0,0)

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

cv2.destroyAllWindows()

Technology Tutorials

Tag Archives: AI

Tracking an Object Based on Color in OpenCV

Faster Launch of WEBcam and Smoother Video in OpenCV on Windows

Launch a Windows WEB Camera in Ten Lines of Code with OpenCV

AI on the Jetson Nano LESSON 60: Make Your Nano Talk With Text to Speech

Jetson Xavier NX Lesson 15: Training the Face Recognition Program to Recognize People

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