Tag Archives: AI

In this exciting project, we combine a Raspberry Pi 5, the Fusion AI Lab Kit, a Pi Camera, and a remote IP camera to generate a stunning real-time composite video. Watch as a glowing, translucent MediaPipe face mesh of my face hovers magically over live video of the Mighty River Nice scenery captured by an IP camera. The effect looks futuristic and professional — perfect for creative video effects, interactive installations, or just blowing your mind with computer vision! Using Picamera2 for high-frame-rate local capture and OpenCV with an RTSP stream from the river camera, we process everything in real time. MediaPipe’s Face Mesh detects and tracks facial landmarks, which we draw as beautiful cyan/teal contours with glowing irises. Then we create a clean mask, separate the mesh foreground from the river background, and blend them seamlessly into one composite frame. You’ll see every debugging layer live on screen too — meshLayer, mask, inverted mask, riverBG, and meshFG — so you can understand exactly how the magic happens.This tutorial is beginner-to-intermediate friendly and packed with practical OpenCV + MediaPipe techniques you can adapt for your own augmented reality projects. Whether you’re a longtime follower of the Paul McWhorter channel or new to the Fusion AI Kit, you’ll walk away inspired and ready to build your own hovering effects, overlays, or interactive displays.Grab the full code from the video description, fire up your Pi 5, and start creating jaw-dropping computer vision projects today. Drop a comment and let me know what you’d like to overlay next — another face mesh, hand tracking, or something completely different? Let’s keep pushing the limits of what we can do with affordable AI hardware!

# ====================================================================
# DISCLAIMER:
# This code is provided as-is for educational and experimental 
# purposes only. The author makes no representations or warranties of 
# any kind concerning the safety, suitability, or accuracy of this 
# code. Use at your own risk. The author assumes no liability for any 
# damages, system failures, security breaches, or network issues 
# resulting from the use or implementation of this script.
# ====================================================================
 
import cv2
import time
from picamera2 import Picamera2
import mediapipe as mp
import numpy as np
import secret
W=1280
H=720
tStart = time.time()
fps = 0

piCam = Picamera2(1)
piCam.preview_configuration.main.size = (W, H)
piCam.preview_configuration.main.format = "RGB888"
piCam.preview_configuration.controls.FrameRate = 60
piCam.preview_configuration.align()
piCam.configure("preview")
piCam.start()

cam = cv2.VideoCapture(secret.RTSP1,cv2.CAP_FFMPEG)
cam.set(cv2.CAP_PROP_BUFFERSIZE,0)
cam.set(cv2.CAP_PROP_POS_FRAMES,0)

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

faceMesh = mp.solutions.face_mesh.FaceMesh(
    
    max_num_faces=1,
    refine_landmarks=True,
    min_detection_confidence=0.5,
    min_tracking_confidence=0.5)

cv2.namedWindow('Composite',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('Composite',W,H)
cv2.moveWindow('Composite',0,65)

cv2.namedWindow('meshLayer',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('meshLayer',320,180)
cv2.moveWindow('meshLayer',0,H+65)

cv2.namedWindow('grayLayer',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('grayLayer',320,180)
cv2.moveWindow('grayLayer',320,H+65)

cv2.namedWindow('maskLayer',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('maskLayer',320,180)
cv2.moveWindow('maskLayer',320*2,H+65)

cv2.namedWindow('invLayer',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('invLayer',320,180)
cv2.moveWindow('invLayer',320*3,H+65)

cv2.namedWindow('riverBG',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('riverBG',320,180)
cv2.moveWindow('riverBG',W,65)

cv2.namedWindow('meshFG',cv2.WINDOW_GUI_NORMAL)
cv2.resizeWindow('meshFG',320,180)
cv2.moveWindow('meshFG',W,180+65+20)
while True:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    frame = piCam.capture_array()
    frame = cv2.flip(frame, -1)
    
    _, river = cam.read()
    river = cv2.resize(river,(W,H))
    meshLayer = frame.copy()
    meshLayer[0:H-1,0:W-1] = [255,255,255]
    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    results = faceMesh.process(rgb)

    if results.multi_face_landmarks:
        for faceLandmarks in results.multi_face_landmarks:
            # Optional second pass for glow effect
            mp.solutions.drawing_utils.draw_landmarks(
                image=meshLayer,
                landmark_list=faceLandmarks,
                connections=mp.solutions.face_mesh.FACEMESH_TESSELATION,
                landmark_drawing_spec=None,
                connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(
                    color=(0, 150, 200),
                    thickness=2
                )
            )
            # === Best looking translucent mesh ===
            mp.solutions.drawing_utils.draw_landmarks(
                image=meshLayer,
                landmark_list=faceLandmarks,
                connections=mp.solutions.face_mesh.FACEMESH_CONTOURS,
                landmark_drawing_spec=None,                    # Hide dots
                connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(
                    color=(0, 0, 180),      # Bright cyan/teal
                    thickness=7
                )
            )

            # Optional: Extra detail on irises (makes eyes look better)
            mp.solutions.drawing_utils.draw_landmarks(
                image=meshLayer,
                landmark_list=faceLandmarks,
                connections=mp.solutions.face_mesh.FACEMESH_IRISES,
                landmark_drawing_spec=None,
                connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(
                    color=(255, 0, 0),
                    thickness=7
                )
            )
    gray = cv2.cvtColor(meshLayer,cv2.COLOR_BGR2GRAY)

    _ , mask =cv2.threshold(gray, 250, 255, cv2.THRESH_BINARY)
    invLayer = cv2.bitwise_not(mask)
    riverBG =cv2.bitwise_and(river, river, mask = mask)
    meshFG = cv2.bitwise_and(meshLayer,meshLayer, mask=invLayer)
    composite = cv2.add(riverBG,meshFG)
    
    myText = "FPS: "+str(round(fps,1))
    cv2.putText(composite,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)

    cv2.imshow("Composite", composite)
    cv2.imshow("meshLayer",meshLayer)
    cv2.imshow("grayLayer",gray)
    cv2.imshow("maskLayer",mask)
    cv2.imshow("invLayer",invLayer)
    cv2.imshow("riverBG",riverBG)
    cv2.imshow("meshFG",meshFG)
    if cv2.waitKey(1) == ord('q'):
        break

cv2.destroyAllWindows()
piCam.stop()

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

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

# ====================================================================

# DISCLAIMER:

# This code is provided as-is for educational and experimental

# purposes only. The author makes no representations or warranties of

# any kind concerning the safety, suitability, or accuracy of this

# code. Use at your own risk. The author assumes no liability for any

# damages, system failures, security breaches, or network issues

# resulting from the use or implementation of this script.

# ====================================================================

import cv2

import time

from picamera2 import Picamera2

import mediapipe as mp

import numpy as np

import secret

W=1280

H=720

tStart = time.time()

fps = 0

piCam = Picamera2(1)

piCam.preview_configuration.main.size = (W, H)

piCam.preview_configuration.main.format = "RGB888"

piCam.preview_configuration.controls.FrameRate = 60

piCam.preview_configuration.align()

piCam.configure("preview")

piCam.start()

cam = cv2.VideoCapture(secret.RTSP1,cv2.CAP_FFMPEG)

cam.set(cv2.CAP_PROP_BUFFERSIZE,0)

cam.set(cv2.CAP_PROP_POS_FRAMES,0)

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

fontFace = cv2.FONT_HERSHEY_SIMPLEX

fontThickness = int(W/425)

fontScale = H*.0015

fontColor = (0,0,255)

faceMesh = mp.solutions.face_mesh.FaceMesh(

max_num_faces=1,

refine_landmarks=True,

min_detection_confidence=0.5,

min_tracking_confidence=0.5)

cv2.namedWindow('Composite',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('Composite',W,H)

cv2.moveWindow('Composite',0,65)

cv2.namedWindow('meshLayer',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('meshLayer',320,180)

cv2.moveWindow('meshLayer',0,H+65)

cv2.namedWindow('grayLayer',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('grayLayer',320,180)

cv2.moveWindow('grayLayer',320,H+65)

cv2.namedWindow('maskLayer',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('maskLayer',320,180)

cv2.moveWindow('maskLayer',320*2,H+65)

cv2.namedWindow('invLayer',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('invLayer',320,180)

cv2.moveWindow('invLayer',320*3,H+65)

cv2.namedWindow('riverBG',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('riverBG',320,180)

cv2.moveWindow('riverBG',W,65)

cv2.namedWindow('meshFG',cv2.WINDOW_GUI_NORMAL)

cv2.resizeWindow('meshFG',320,180)

cv2.moveWindow('meshFG',W,180+65+20)

while True:

deltaT = time.time() - tStart

tStart=time.time()

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

frame = piCam.capture_array()

frame = cv2.flip(frame, -1)

_, river = cam.read()

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

meshLayer = frame.copy()

meshLayer[0:H-1,0:W-1] = [255,255,255]

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

results = faceMesh.process(rgb)

if results.multi_face_landmarks:

for faceLandmarks in results.multi_face_landmarks:

# Optional second pass for glow effect

mp.solutions.drawing_utils.draw_landmarks(

image=meshLayer,

landmark_list=faceLandmarks,

connections=mp.solutions.face_mesh.FACEMESH_TESSELATION,

landmark_drawing_spec=None,

connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(

color=(0, 150, 200),

thickness=2

)

# === Best looking translucent mesh ===

mp.solutions.drawing_utils.draw_landmarks(

image=meshLayer,

landmark_list=faceLandmarks,

connections=mp.solutions.face_mesh.FACEMESH_CONTOURS,

landmark_drawing_spec=None, # Hide dots

connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(

color=(0, 0, 180), # Bright cyan/teal

thickness=7

)

# Optional: Extra detail on irises (makes eyes look better)

mp.solutions.drawing_utils.draw_landmarks(

image=meshLayer,

landmark_list=faceLandmarks,

connections=mp.solutions.face_mesh.FACEMESH_IRISES,

landmark_drawing_spec=None,

connection_drawing_spec=mp.solutions.drawing_utils.DrawingSpec(

color=(255, 0, 0),

thickness=7

)

gray = cv2.cvtColor(meshLayer,cv2.COLOR_BGR2GRAY)

_ , mask =cv2.threshold(gray, 250, 255, cv2.THRESH_BINARY)

invLayer = cv2.bitwise_not(mask)

riverBG =cv2.bitwise_and(river, river, mask = mask)

meshFG = cv2.bitwise_and(meshLayer,meshLayer, mask=invLayer)

composite = cv2.add(riverBG,meshFG)

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

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

cv2.imshow("Composite", composite)

cv2.imshow("meshLayer",meshLayer)

cv2.imshow("grayLayer",gray)

cv2.imshow("maskLayer",mask)

cv2.imshow("invLayer",invLayer)

cv2.imshow("riverBG",riverBG)

cv2.imshow("meshFG",meshFG)

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

break

cv2.destroyAllWindows()

piCam.stop()

AI On the Edge, Raspberry Pi

AI on the Edge 38: Using MediaPipe for Face Recognition on the Raspberry Pi 5

August 2, 2026 admin

In this video lesson we introduce you to MediaPipe. The OS we had you flash in LESSON 1 already has the MediaPipe framework installed, and all the needed and working dependencies. If you have installed that OS and not modified it, this and future lessons will work. If you find dependency errors, you might need to reflash the original OS.

MediaPipe is a free, open-source framework developed by Google that makes it much easier to add advanced computer vision and AI features to your Python programs. It is especially popular among developers who use OpenCV because it works seamlessly with it and delivers excellent real-time performance, even on devices like the Raspberry Pi 5.

With MediaPipe, you can quickly add powerful capabilities such as face detection, face mesh (detailed facial landmarks), hand tracking, body pose estimation, and more — all without having to write complex deep learning code from scratch. It comes with pre-trained machine learning models that are optimized for speed, allowing your programs to run smoothly at 30 frames per second or higher.

The biggest advantage for Python + OpenCV users is its simplicity. You capture video frames using OpenCV or picamera2, pass them to MediaPipe for processing, and then draw the results (such as bounding boxes or landmarks) back onto your image using normal OpenCV functions. This combination gives developers a fast and straightforward way to build interactive computer vision projects like face trackers, gesture-controlled robots, or smart camera applications.

In short, MediaPipe acts as a powerful, easy-to-use toolkit that bridges the gap between OpenCV and modern AI vision technology.

We introduce you to MediaPipe using a simple example where we create a faceFinder on our Raspberry Pi 5.

# ====================================================================
# DISCLAIMER:
# This code is provided as-is for educational and experimental 
# purposes only. The author makes no representations or warranties of 
# any kind concerning the safety, suitability, or accuracy of this 
# code. Use at your own risk. The author assumes no liability for any 
# damages, system failures, security breaches, or network issues 
# resulting from the use or implementation of this script.
# ====================================================================
import cv2
import time
from picamera2 import Picamera2
import mediapipe as mp
piCam = Picamera2()
W=1280
H=720
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)

faceFinder = mp.solutions.face_detection.FaceDetection(
    model_selection = 0,
    min_detection_confidence = .5)
mpDraw = mp.solutions.drawing_utils

while True:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    frame= piCam.capture_array()
    #frame=cv2.flip(frame,-1)
    
    rgbFrame = cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
    results = faceFinder.process(rgbFrame)
    if results.detections:
        for detection in results.detections:
            mpDraw.draw_detection(frame,detection)
    
    myText = "FPS: "+str(round(fps,1))
    cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)
    cv2.imshow("Camera", frame)
    cv2.moveWindow("Camera",0,60)
    if cv2.waitKey(1)==ord('q'):
        break
cv2.destroyAllWindows()
print('Program Terminated')

# ====================================================================

# DISCLAIMER:

# This code is provided as-is for educational and experimental

# purposes only. The author makes no representations or warranties of

# any kind concerning the safety, suitability, or accuracy of this

# code. Use at your own risk. The author assumes no liability for any

# damages, system failures, security breaches, or network issues

# resulting from the use or implementation of this script.

# ====================================================================

import cv2

import time

from picamera2 import Picamera2

import mediapipe as mp

piCam = Picamera2()

W=1280

H=720

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)

faceFinder = mp.solutions.face_detection.FaceDetection(

model_selection = 0,

min_detection_confidence = .5)

mpDraw = mp.solutions.drawing_utils

while True:

deltaT = time.time() - tStart

tStart=time.time()

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

frame= piCam.capture_array()

#frame=cv2.flip(frame,-1)

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

results = faceFinder.process(rgbFrame)

if results.detections:

for detection in results.detections:

mpDraw.draw_detection(frame,detection)

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

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

cv2.imshow("Camera", frame)

cv2.moveWindow("Camera",0,60)

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

break

cv2.destroyAllWindows()

print('Program Terminated')

AI On the Edge, Raspberry Pi

AI on the Edge LESSON 37: Using RTSP and IP Cameras in OpenCV on Raspberry Pi 5

July 30, 2026 admin

The code below shows the work we did in this lesson.

AI on the Edge Lesson 37: Using RTSP and IP Cameras in OpenCV on Raspberry Pi 5

Hey guys! Welcome back to our AI on the Edge series. In our previous lessons, we’ve had a blast working with standard USB webcams, but if you are building a real-world computer vision application, an automation rig, or a security monitoring setup around your home or farm, USB cables just aren’t going to cut it. You need to pull video feeds from remote IP cameras using the Real-Time Streaming Protocol (RTSP).

Today, we are taking that exact step on the Raspberry Pi 5, connecting to an IP camera, streaming the feed smoothly into OpenCV, and—most importantly—solving the dreaded latency problem that plagues RTSP feeds.

The Big Challenge: Conquering RTSP Latency

If you’ve ever tried pulling an RTSP stream into OpenCV straight out of the box, you’ve probably noticed something frustrating: the video lags behind real-time, sometimes by several seconds or even tens of seconds.

Why does that happen? Because by default, FFmpeg and OpenCV buffer incoming frames to ensure smooth playback. But when you are doing computer vision, AI inferencing, or real-time tracking on the edge, you don’t want old history—you want right now.

To fix that, we pass the cv2.CAP_FFMPEG backend flag and immediately flush the buffer by setting the property to 0. This forces OpenCV to drop the backlog and grab the absolute newest frame available from the camera stream, keeping your Pi 5 processing live data in real-time.

Understanding the Script Structure

Let’s break down the key parts of today’s implementation:

Credentials & Resolution: We import a separate secret file to keep our camera IP addresses, usernames, and passwords safe and out of public repositories. We lock our resolution at 1280×720 to balance crisp detail with the Pi 5’s processing overhead.
Smooth FPS Calculation: Instead of a jittery raw frame-rate readout, we use an exponential moving average to give us a stable, readable performance metric on screen.
The Display Window: We configure a GUI window using OpenCV’s window flags so we can easily position and resize our output feed on the desktop.

Drop Your Questions Below

Working with network streams can sometimes be tricky depending on your specific camera’s firmware, codec settings, and network stability. If you run into any connection drops or lag spikes on your Raspberry Pi 5, drop a comment on the video!

Keep building, stay creative, and I will see you guys in Lesson 38!

Here is the code developed in the video

# ====================================================================
# DISCLAIMER:
# This code is provided as-is for educational and experimental 
# purposes only. The author makes no representations or warranties of 
# any kind concerning the safety, suitability, or accuracy of this 
# code. Use at your own risk. The author assumes no liability for any 
# damages, system failures, security breaches, or network issues 
# resulting from the use or implementation of this script.
# ====================================================================
import cv2
import time
import secret
W=1280
H=720
tStart = time.time()
fps = 0
RES = (W,H)

textLowerLeft = (int(W*.01),int(H*.05))
fontFace = cv2.FONT_HERSHEY_SIMPLEX
fontThickness = int(W/425)
fontScale = H*.0015
fontColor = (0,0,255)
print(secret.RTSP8)
cam = cv2.VideoCapture(secret.RTSP1, cv2.CAP_FFMPEG)
cam.set(cv2.CAP_PROP_BUFFERSIZE, 0)
cam.set(cv2.CAP_PROP_POS_FRAMES, 0)

cv2.namedWindow('Camera',cv2.WINDOW_GUI_NORMAL)
cv2.moveWindow('Camera',0,65)
cv2.resizeWindow('Camera',W,H)

while True:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    _, frame= cam.read()
    #frame=cv2.flip(frame,-1)
    myText = "FPS: "+str(round(fps,1))
    cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)
    cv2.imshow("Camera", frame)
    if cv2.waitKey(1)==ord('q'):
        break
cv2.destroyAllWindows()
print('Program Terminated')

# ====================================================================

# DISCLAIMER:

# This code is provided as-is for educational and experimental

# purposes only. The author makes no representations or warranties of

# any kind concerning the safety, suitability, or accuracy of this

# code. Use at your own risk. The author assumes no liability for any

# damages, system failures, security breaches, or network issues

# resulting from the use or implementation of this script.

# ====================================================================

import cv2

import time

import secret

W=1280

H=720

tStart = time.time()

fps = 0

RES = (W,H)

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

fontFace = cv2.FONT_HERSHEY_SIMPLEX

fontThickness = int(W/425)

fontScale = H*.0015

fontColor = (0,0,255)

print(secret.RTSP8)

cam = cv2.VideoCapture(secret.RTSP1, cv2.CAP_FFMPEG)

cam.set(cv2.CAP_PROP_BUFFERSIZE, 0)

cam.set(cv2.CAP_PROP_POS_FRAMES, 0)

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

cv2.moveWindow('Camera',0,65)

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

while True:

deltaT = time.time() - tStart

tStart=time.time()

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

_, frame= cam.read()

#frame=cv2.flip(frame,-1)

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

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

cv2.imshow("Camera", frame)

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

break

cv2.destroyAllWindows()

print('Program Terminated')

NVIDIA, NVIDIA Jetson Orin Nano

Local Voice Control of NVIDIA Jetson Orin Nano with STT: Getting Started with Vosk

July 22, 2026 admin

Engineering Your Own Local Voice Assistant: No Cloud, No Compromise

Most “smart” voice assistants are just glorified remote controls for someone else’s server. Today, we’re changing that. We are going to build a local, offline voice command pipeline. This isn’t just about saving data; it’s about ownership. When you can control your hardware—like opening and closing a farm gate—without an internet connection, you have built a system that is robust, private, and yours to control forever. Today you are going to get Speech to Text up and running on your NVIDIA Jetson Orin Nano running under Jetpack 7.2.

The “Why” Behind the Setup

You might ask, “Why not just use a cloud API?” Because cloud APIs are fragile. They rely on internet stability, external servers, and privacy-invasive data logging. By running Vosk locally, we keep the processing on your hardware (like the NVIDIA Jetson). It’s faster, it works in the middle of a power-isolated homestead, and it’s 100% secure.

Part 1: Preparing the Environment

Before we can make the machine listen, we have to prepare the battlefield. We aren’t just downloading files; we are setting up a stable environment where your dependencies won’t conflict with your OS.

# Create a dedicated directory so our work stays organized
mkdir -p ~/STT
cd ~/STT

# We need the PortAudio headers. Why? Because Python’s 'pyaudio' is just a wrapper.
# Under the hood, it talks to the C-based PortAudio library. If the headers aren't there,
# the library won't compile, and your microphone will never wake up.
sudo apt update
sudo apt install -y portaudio19-dev wget unzip

# Download the lightweight, low-latency English model weights from Vosk
wget https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip

# Unzip the archive and rename the folder cleanly to 'model' so the Python script finds it
unzip vosk-model-small-en-us-0.15.zip
mv vosk-model-small-en-us-0.15 model

# Clean up the downloaded zip file to keep the folder pristine
rm vosk-model-small-en-us-0.15.zip

# Setting up a Virtual Environment (venv) is the hallmark of a pro.
# It traps our project dependencies inside this folder so we don't break our system Python.
python3 -m venv sttVenv
source sttVenv/bin/activate
pip install --upgrade pip

# Vosk does the heavy lifting for speech recognition, and Pyaudio grabs the raw data.
pip install vosk pyaudio

# Create a dedicated directory so our work stays organized

mkdir -p ~/STT

cd ~/STT

# We need the PortAudio headers. Why? Because Python’s 'pyaudio' is just a wrapper.

# Under the hood, it talks to the C-based PortAudio library. If the headers aren't there,

# the library won't compile, and your microphone will never wake up.

sudo apt update

sudo apt install -y portaudio19-dev wget unzip

# Download the lightweight, low-latency English model weights from Vosk

wget https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip

# Unzip the archive and rename the folder cleanly to 'model' so the Python script finds it

unzip vosk-model-small-en-us-0.15.zip

mv vosk-model-small-en-us-0.15 model

# Clean up the downloaded zip file to keep the folder pristine

rm vosk-model-small-en-us-0.15.zip

# Setting up a Virtual Environment (venv) is the hallmark of a pro.

# It traps our project dependencies inside this folder so we don't break our system Python.

python3 -m venv sttVenv

source sttVenv/bin/activate

pip install --upgrade pip

# Vosk does the heavy lifting for speech recognition, and Pyaudio grabs the raw data.

pip install vosk pyaudio

This is IMPORTANT!

Now you can post the code below. You also have to point Thonny to run in the virtual environment. Open Thonny, and under run – select interpreter. Then you must point it to /home/yourUserName/STT/ttsVenv/bin/python3. For me, my username is pjm, but you put in your user name in path above. Here is what mine looked like:

Part 2: Solving the PipeWire Challenge

The biggest headache in modern Linux audio is PipeWire. If you try to open a microphone stream using a hardcoded sample rate that doesn’t match your hardware, your program won’t just fail—it will segfault. We use the validation script below to programmatically query the hardware, asking it: “What sample rate are you running at?” before we even try to open a stream.

# Import the PyAudio library to handle real-time microphone recording and audio stream manipulation.
import pyaudio
# Import the built-in JSON module to parse the structured text results returned by the speech recognition engine.
import json
# Import the audioop library to perform real-time mathematical operations and downsampling on raw audio byte data.
import audioop
# Import the core Vosk objects: Model loads the AI brain/weights, and KaldiRecognizer handles the acoustic processing.
from vosk import Model, KaldiRecognizer
# Import the standard OS module to reliably build absolute system file paths across different user directories.
import os
state=None

# Define a function to discover the specific hardware index and sample rate of the active system sound server.
def get_pipewire_index():
    # Instantiate a PyAudio session object to query the operating system's hardware configuration list.
    p = pyaudio.PyAudio()
    # Loop through every single available audio device reported by the operating system kernel.
    for i in range(p.get_device_count()):
        # Retrieve a descriptive configuration dictionary for the current audio device index.
        dev = p.get_device_info_by_index(i)
        # Check if the name of the device contains 'pipewire' to target the modern Linux audio subsystem.
        if "pipewire" in dev.get('name', '').lower():
            # Return the valid device index integer and its hardware default sample rate, converted cleanly to an integer.
            return i, int(dev.get('defaultSampleRate'))
    # Return empty values if the loop completes without finding an active PipeWire sound server profile.
    return None, None

# Execute the discovery function to capture both the correct system hardware device index and its native sample rate.
dev_index, native_rate = get_pipewire_index()

# Check if the hardware discovery handshake failed to locate an active PipeWire audio interface.
if dev_index is None:
    # Alert the user on screen that the script cannot communicate with the system's active audio server layer.
    print("Error: Could not find 'pipewire' device.")
    # Stop the script execution immediately since it is impossible to record audio without a valid device hook.
    exit()

# Instantiate a fresh PyAudio session specifically dedicated to opening our incoming recording channel.
p = pyaudio.PyAudio()
# Open the active system recording stream channel using explicit audio hardware parameter configurations.
# PARAMETER MANUAL:
# - format=pyaudio.paInt16: Sets 16-bit Signed Integer PCM format. (LEAVE ALONE - required by the Vosk engine).
# - channels=1: Sets recording to Mono channel audio. (LEAVE ALONE - Vosk processes single-channel input).
# - rate=native_rate: Sets the sample rate to match the mic exactly. (LEAVE ALONE - prevents driver hardware failure).
# - input=True: Configures this stream as an audio capture device. (LEAVE ALONE - required to wake up the microphone).
# - input_device_index=dev_index: Points to our discovered target device. (LEAVE ALONE - ensures we grab the right mic).
# - frames_per_buffer=4096: Controls audio chunk size. (PLAY WITH: Lower values like 2048 reduce latency but risk buffer overflows; higher values like 8192 increase safety but introduce slight latency).
stream = p.open(format=pyaudio.paInt16, channels=1, rate=native_rate, 
                input=True, input_device_index=dev_index, frames_per_buffer=4096)

# Generate an absolute directory path targeting the exact folder containing your extracted acoustic model weights.
# PARAMETER MANUAL:
# - "STT", "model": Represents folder names. (PLAY WITH: Change these only if your physical folder layout uses different names).
model_path = os.path.join(os.path.expanduser("~"), "STT", "model")
# Load the heavy machine learning weights into system memory to initialize the Vosk voice processing brain.
model = Model(model_path)
# Initialize the primary speech recognizer object using the loaded model weights and target processing frequency.
# PARAMETER MANUAL:
# - model: The initialized AI brain variable. (LEAVE ALONE).
# - 16000: Specifies the target processing sample rate in Hertz. (LEAVE ALONE - Vosk models are mathematically trained for exactly 16000Hz).
recognizer = KaldiRecognizer(model, 16000)

# Print a status message to the terminal showing that the handshake succeeded and revealing the mic's operating frequency.
print(f"Listening on PipeWire at {native_rate}Hz...")
# Turn on the hardware recording valve to begin filling up the system input data buffers.
stream.start_stream()

# Set up an exception safety block to intercept manual user exits gracefully without leaving system resources locked up.
try:
    # Launch the infinite real-time audio capture loop to continuously monitor the microphone stream.
    while True:
        # Pull raw binary audio frame bytes directly out of the incoming hardware stream buffer memory block.
        # PARAMETER MANUAL:
        # - 4096: The chunk size to read. (LEAVE ALONE - must perfectly match your stream's frames_per_buffer setting).
        # - exception_on_overflow=False: Prevents Python crashes if the Orin momentarily falls behind. (LEAVE ALONE).
        data = stream.read(4096, exception_on_overflow=False)
        # Downsample the raw audio bytes mathematically to 16000Hz using digital filtering algorithms.
        # PARAMETER MANUAL:
        # - data: Raw input audio byte string. (LEAVE ALONE).
        # - 2: Size of sample width in bytes for 16-bit sound. (LEAVE ALONE).
        # - 1: Input audio channel count. (LEAVE ALONE).
        # - native_rate: The native frequency of your mic. (LEAVE ALONE).
        # - 16000: The required downsampled output frequency. (LEAVE ALONE).
        # - state: The digital filtering conversion state history object. (LEAVE ALONE).
        # CRITICAL NOTE: The 'state' variable must be initialized as 'state = None' before entering this 'try:' block, 
        # otherwise Python will throw a NameError on the very first loop iteration because 'state' does not exist yet.
        data_16k, state = audioop.ratecv(data, 2, 1, native_rate, 16000, state)
        
        # Feed the processed 16kHz audio data block into Vosk to evaluate if a complete spoken phrase has finished.
        if recognizer.AcceptWaveform(data_16k):
            # Parse the structured JSON text string returned by the acoustic model into a standard Python dictionary.
            res = json.loads(recognizer.Result())
            # Check the parsed result dictionary to ensure that the detected text sequence is not completely blank.
            if res.get("text"):
                # Cleanly output the decoded text command straight to the standard system terminal display screen.
                print("Command: "+res['text'])
# Intercept the user pressing Ctrl+C in the terminal to stop the continuous script loop cleanly.
except KeyboardInterrupt:
    # Print a clean closing status notification on a new line to confirm the signal was intercepted.
    print("\nStopped.")
# Execute mandatory clean up instructions that are guaranteed to run no matter how the script terminates or crashes.
finally:
    # Turn off the active recording stream data valve to stop pulling raw information from the audio driver layer.
    stream.stop_stream()
    # Close the recording stream channel completely to drop the active hardware pointer binding handles.
    stream.close()
    # Terminate the parent PyAudio engine instance to release all allocated audio device resources back to the OS.
    p.terminate()

100

101

102

103

104

105

106

107

108

# Import the PyAudio library to handle real-time microphone recording and audio stream manipulation.

import pyaudio

# Import the built-in JSON module to parse the structured text results returned by the speech recognition engine.

import json

# Import the audioop library to perform real-time mathematical operations and downsampling on raw audio byte data.

import audioop

# Import the core Vosk objects: Model loads the AI brain/weights, and KaldiRecognizer handles the acoustic processing.

from vosk import Model, KaldiRecognizer

# Import the standard OS module to reliably build absolute system file paths across different user directories.

import os

state=None

# Define a function to discover the specific hardware index and sample rate of the active system sound server.

def get_pipewire_index():

# Instantiate a PyAudio session object to query the operating system's hardware configuration list.

p = pyaudio.PyAudio()

# Loop through every single available audio device reported by the operating system kernel.

for i in range(p.get_device_count()):

# Retrieve a descriptive configuration dictionary for the current audio device index.

dev = p.get_device_info_by_index(i)

# Check if the name of the device contains 'pipewire' to target the modern Linux audio subsystem.

if "pipewire" in dev.get('name', '').lower():

# Return the valid device index integer and its hardware default sample rate, converted cleanly to an integer.

return i, int(dev.get('defaultSampleRate'))

# Return empty values if the loop completes without finding an active PipeWire sound server profile.

return None, None

# Execute the discovery function to capture both the correct system hardware device index and its native sample rate.

dev_index, native_rate = get_pipewire_index()

# Check if the hardware discovery handshake failed to locate an active PipeWire audio interface.

if dev_index is None:

# Alert the user on screen that the script cannot communicate with the system's active audio server layer.

print("Error: Could not find 'pipewire' device.")

# Stop the script execution immediately since it is impossible to record audio without a valid device hook.

exit()

# Instantiate a fresh PyAudio session specifically dedicated to opening our incoming recording channel.

p = pyaudio.PyAudio()

# Open the active system recording stream channel using explicit audio hardware parameter configurations.

# PARAMETER MANUAL:

# - format=pyaudio.paInt16: Sets 16-bit Signed Integer PCM format. (LEAVE ALONE - required by the Vosk engine).

# - channels=1: Sets recording to Mono channel audio. (LEAVE ALONE - Vosk processes single-channel input).

# - rate=native_rate: Sets the sample rate to match the mic exactly. (LEAVE ALONE - prevents driver hardware failure).

# - input=True: Configures this stream as an audio capture device. (LEAVE ALONE - required to wake up the microphone).

# - input_device_index=dev_index: Points to our discovered target device. (LEAVE ALONE - ensures we grab the right mic).

# - frames_per_buffer=4096: Controls audio chunk size. (PLAY WITH: Lower values like 2048 reduce latency but risk buffer overflows; higher values like 8192 increase safety but introduce slight latency).

stream = p.open(format=pyaudio.paInt16, channels=1, rate=native_rate,

input=True, input_device_index=dev_index, frames_per_buffer=4096)

# Generate an absolute directory path targeting the exact folder containing your extracted acoustic model weights.

# PARAMETER MANUAL:

# - "STT", "model": Represents folder names. (PLAY WITH: Change these only if your physical folder layout uses different names).

model_path = os.path.join(os.path.expanduser("~"), "STT", "model")

# Load the heavy machine learning weights into system memory to initialize the Vosk voice processing brain.

model = Model(model_path)

# Initialize the primary speech recognizer object using the loaded model weights and target processing frequency.

# PARAMETER MANUAL:

# - model: The initialized AI brain variable. (LEAVE ALONE).

# - 16000: Specifies the target processing sample rate in Hertz. (LEAVE ALONE - Vosk models are mathematically trained for exactly 16000Hz).

recognizer = KaldiRecognizer(model, 16000)

# Print a status message to the terminal showing that the handshake succeeded and revealing the mic's operating frequency.

print(f"Listening on PipeWire at {native_rate}Hz...")

# Turn on the hardware recording valve to begin filling up the system input data buffers.

stream.start_stream()

# Set up an exception safety block to intercept manual user exits gracefully without leaving system resources locked up.

try:

# Launch the infinite real-time audio capture loop to continuously monitor the microphone stream.

while True:

# Pull raw binary audio frame bytes directly out of the incoming hardware stream buffer memory block.

# PARAMETER MANUAL:

# - 4096: The chunk size to read. (LEAVE ALONE - must perfectly match your stream's frames_per_buffer setting).

# - exception_on_overflow=False: Prevents Python crashes if the Orin momentarily falls behind. (LEAVE ALONE).

data = stream.read(4096, exception_on_overflow=False)

# Downsample the raw audio bytes mathematically to 16000Hz using digital filtering algorithms.

# PARAMETER MANUAL:

# - data: Raw input audio byte string. (LEAVE ALONE).

# - 2: Size of sample width in bytes for 16-bit sound. (LEAVE ALONE).

# - 1: Input audio channel count. (LEAVE ALONE).

# - native_rate: The native frequency of your mic. (LEAVE ALONE).

# - 16000: The required downsampled output frequency. (LEAVE ALONE).

# - state: The digital filtering conversion state history object. (LEAVE ALONE).

# CRITICAL NOTE: The 'state' variable must be initialized as 'state = None' before entering this 'try:' block,

# otherwise Python will throw a NameError on the very first loop iteration because 'state' does not exist yet.

data_16k, state = audioop.ratecv(data, 2, 1, native_rate, 16000, state)

# Feed the processed 16kHz audio data block into Vosk to evaluate if a complete spoken phrase has finished.

if recognizer.AcceptWaveform(data_16k):

# Parse the structured JSON text string returned by the acoustic model into a standard Python dictionary.

res = json.loads(recognizer.Result())

# Check the parsed result dictionary to ensure that the detected text sequence is not completely blank.

if res.get("text"):

# Cleanly output the decoded text command straight to the standard system terminal display screen.

print("Command: "+res['text'])

# Intercept the user pressing Ctrl+C in the terminal to stop the continuous script loop cleanly.

except KeyboardInterrupt:

# Print a clean closing status notification on a new line to confirm the signal was intercepted.

print("\nStopped.")

# Execute mandatory clean up instructions that are guaranteed to run no matter how the script terminates or crashes.

finally:

# Turn off the active recording stream data valve to stop pulling raw information from the audio driver layer.

stream.stop_stream()

# Close the recording stream channel completely to drop the active hardware pointer binding handles.

stream.close()

# Terminate the parent PyAudio engine instance to release all allocated audio device resources back to the OS.

p.terminate()

Homework: Your Gate Controller

You now have a system that identifies audio input, resamples it to 16kHz, and outputs text. Your assignment: Transform this text output into an action.

I want you to add a conditional statement to the main loop. If the recognized text is “open”, print an ASCII art representation of an open gate. If it’s “close”, print the closed version. This is the first step in closing the loop between your AI and the physical world. Go get ’em, and don’t just copy the code—understand how the data flows from the microphone to your decision logic!

AI On the Edge, Raspberry Pi

AI on the Edge LESSON 34 SUPPLEMENT: Simple Improvement to FPS

July 21, 2026 admin

In this video I show you how to dramatically improve the FPS of our work in lesson 34. I also show the solution to the issue of the Fusion Hat microphone not working with the project.

# ====================================================================
# DISCLAIMER:
# This code is provided as-is for educational and experimental 
# purposes only. The author makes no representations or warranties of 
# any kind concerning the safety, suitability, or accuracy of this 
# code. Use at your own risk. The author assumes no liability for any 
# damages, system failures, security breaches, or network issues 
# resulting from the use or implementation of this script.
# ====================================================================
 
import cv2
import time
from picamera2 import Picamera2
#########################################
import threading
from queue import Queue
from fusion_hat.tts import Piper
tts = Piper()
tts.set_model('en_US-kristin-medium')

from fusion_hat.stt import STT
stt = STT('en-us')

cnt = 0
running = True
commandQ = Queue()
speakQ = Queue()
###########################################

from fusion_hat.servo import Servo
panPin = 2
tiltPin = 3
panServo = Servo(panPin)
tiltServo = Servo(tiltPin)
panAngle = -10
tiltAngle =-20
panServo.angle(panAngle)
tiltServo.angle(tiltAngle)
piCam = Picamera2(1)
W=1280
H=720
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)

faceFinder = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
eyeFinder = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_eye.xml")

track = False
xFrameC = int((W-1)/2)
yFrameC = int((H-1)/2)
xBoxC = xFrameC
yBoxC = yFrameC
##########################################
def speak():
    global running
    print('Speak Thread Running')
    while running:
        if speakQ.empty() == False:
            txt = speakQ.get()
            print(txt)
            tts.say(txt)
        time.sleep(.1)
    print('Speak Thread is Terminated')
    print('')
def getCommand():
    print('Get Command Thread is Running')
    global running
    while running:
        myCommand = stt.listen(stream = False)
        myCommand = myCommand.strip()
        print(myCommand)
        if myCommand == 'quit':
            msg = 'Project Humanoid Elimination Terminated. Have a Nice Day.'
            speakQ.put(msg)
            running = False
            break
        commandQ.put(myCommand)
    print('Get Command Thread Terminated')
    print('')

speakThread = threading.Thread(target=speak,daemon=True)
speakThread.start()

commandThread = threading.Thread(target=getCommand,daemon=True)
commandThread.start()
print('Main Program Has Commenced')
msg = 'Hello, I am Ready to Eliminate Humanoids'
speakQ.put(msg)
msgOld = 'Hello, I am Ready to Eliminate Humanoids'

cv2.namedWindow('Camera',cv2.WINDOW_GUI_NORMAL)
cv2.moveWindow('Camera',0,65)
cv2.resizeWindow('Camera',W,H)
############################################
while running:
    deltaT = time.time() - tStart
    tStart=time.time()
    fps = fps*.95 + (1/deltaT)*.05
    frame= piCam.capture_array()
    frame=cv2.flip(frame,-1)
    
    if commandQ.empty() == False:
        myCommand = commandQ.get()
        if myCommand == 'track':
            track = True
        if myCommand == 'release':
            track = False

    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
    faces = faceFinder.detectMultiScale(gray,scaleFactor=1.1, minNeighbors =5, minSize=(100,100))
    if len(faces) != 0:
        cnt = 0 
        msg = "Humanoid Detected, Shall I track?"
    if len(faces) == 0:
        cnt = cnt + 1
        if cnt == 25:
            msg = "No Humanoid Detected, Continuing to Scan"
    if msgOld != msg:
        speakQ.put(msg)
    msgOld = msg
    for (x,y,w,h) in faces:
        cv2.rectangle(frame, (x,y),(x+w,y+h),(0,255,255),3)
        
        xBoxC = x + int(w/2)
        yBoxC = y + int(h/2)
        xError = xBoxC - xFrameC
        yError = yBoxC - yFrameC
        
        eyes =eyeFinder.detectMultiScale(gray[y:y+h,x:x+w],scaleFactor=1.1,minNeighbors=5,minSize=(15,15))
        for (i,j,w,h) in eyes:
            cv2.rectangle(frame,(x+i,y+j),(x+i+w,y+j+h),(255,0,0),3)
    
    if track == True and len(faces)>0:
        panAngle = panAngle - xError/50/2
        panServo.angle(int(panAngle))
        #time.sleep(.02)
        tiltAngle = tiltAngle + yError/50/2
        tiltServo.angle(int(tiltAngle))
        #time.sleep(.02)
                        
    
    myText = "FPS: "+str(round(fps,1))
    cv2.putText(frame,myText,textLowerLeft,fontFace,fontScale,fontColor,fontThickness)
    cv2.imshow("Camera", frame)
    cv2.moveWindow("Camera",0,60)
    if cv2.waitKey(1)==ord('q'):
        break
cv2.destroyAllWindows()
print('')
print('Program Terminated')

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

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

# ====================================================================

# DISCLAIMER:

# This code is provided as-is for educational and experimental

# purposes only. The author makes no representations or warranties of

# any kind concerning the safety, suitability, or accuracy of this

# code. Use at your own risk. The author assumes no liability for any

# damages, system failures, security breaches, or network issues

# resulting from the use or implementation of this script.

# ====================================================================

import cv2

import time

from picamera2 import Picamera2

#########################################

import threading

from queue import Queue

from fusion_hat.tts import Piper

tts = Piper()

tts.set_model('en_US-kristin-medium')

from fusion_hat.stt import STT

stt = STT('en-us')

cnt = 0

running = True

commandQ = Queue()

speakQ = Queue()

###########################################

from fusion_hat.servo import Servo

panPin = 2

tiltPin = 3

panServo = Servo(panPin)

tiltServo = Servo(tiltPin)

panAngle = -10

tiltAngle =-20

panServo.angle(panAngle)

tiltServo.angle(tiltAngle)

piCam = Picamera2(1)

W=1280

H=720

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)

faceFinder = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

eyeFinder = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_eye.xml")

track = False

xFrameC = int((W-1)/2)

yFrameC = int((H-1)/2)

xBoxC = xFrameC

yBoxC = yFrameC

##########################################

def speak():

global running

print('Speak Thread Running')

while running:

if speakQ.empty() == False:

txt = speakQ.get()

print(txt)

tts.say(txt)

time.sleep(.1)

print('Speak Thread is Terminated')

print('')

def getCommand():

print('Get Command Thread is Running')

global running

while running:

myCommand = stt.listen(stream = False)

myCommand = myCommand.strip()

print(myCommand)

if myCommand == 'quit':

msg = 'Project Humanoid Elimination Terminated. Have a Nice Day.'

speakQ.put(msg)

running = False

break

commandQ.put(myCommand)

print('Get Command Thread Terminated')

print('')

speakThread = threading.Thread(target=speak,daemon=True)

speakThread.start()

commandThread = threading.Thread(target=getCommand,daemon=True)

commandThread.start()

print('Main Program Has Commenced')

msg = 'Hello, I am Ready to Eliminate Humanoids'

speakQ.put(msg)

msgOld = 'Hello, I am Ready to Eliminate Humanoids'

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

cv2.moveWindow('Camera',0,65)

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

############################################

while running:

deltaT = time.time() - tStart

tStart=time.time()

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

frame= piCam.capture_array()

frame=cv2.flip(frame,-1)

if commandQ.empty() == False:

myCommand = commandQ.get()

if myCommand == 'track':

track = True

if myCommand == 'release':

track = False

gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)

faces = faceFinder.detectMultiScale(gray,scaleFactor=1.1, minNeighbors =5, minSize=(100,100))

if len(faces) != 0:

cnt = 0

msg = "Humanoid Detected, Shall I track?"

if len(faces) == 0:

cnt = cnt + 1

if cnt == 25:

msg = "No Humanoid Detected, Continuing to Scan"

if msgOld != msg:

speakQ.put(msg)

msgOld = msg

for (x,y,w,h) in faces:

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

xBoxC = x + int(w/2)

yBoxC = y + int(h/2)

xError = xBoxC - xFrameC

yError = yBoxC - yFrameC

eyes =eyeFinder.detectMultiScale(gray[y:y+h,x:x+w],scaleFactor=1.1,minNeighbors=5,minSize=(15,15))

for (i,j,w,h) in eyes:

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

if track == True and len(faces)>0:

panAngle = panAngle - xError/50/2

panServo.angle(int(panAngle))

#time.sleep(.02)

tiltAngle = tiltAngle + yError/50/2

tiltServo.angle(int(tiltAngle))

#time.sleep(.02)

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

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

cv2.imshow("Camera", frame)

cv2.moveWindow("Camera",0,60)

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

break

cv2.destroyAllWindows()

print('')

print('Program Terminated')

Technology Tutorials

Tag Archives: AI

AI on the Edge LESSON 42: Create Composite Images Using Masks in OpenCV and MediaPipe

AI on the Edge 38: Using MediaPipe for Face Recognition on the Raspberry Pi 5

AI on the Edge LESSON 37: Using RTSP and IP Cameras in OpenCV on Raspberry Pi 5

AI on the Edge Lesson 37: Using RTSP and IP Cameras in OpenCV on Raspberry Pi 5

The Big Challenge: Conquering RTSP Latency

Understanding the Script Structure

Drop Your Questions Below

Local Voice Control of NVIDIA Jetson Orin Nano with STT: Getting Started with Vosk

Engineering Your Own Local Voice Assistant: No Cloud, No Compromise

The “Why” Behind the Setup

Part 1: Preparing the Environment

This is IMPORTANT!

Part 2: Solving the PipeWire Challenge

Homework: Your Gate Controller

AI on the Edge LESSON 34 SUPPLEMENT: Simple Improvement to FPS

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