Raspberry Pi Projects

วันอังคารที่ 9 ตุลาคม พ.ศ. 2561

Raspberry pi Machine Learning with Intel Movidius Neural Compute Stick

Raspberry pi Machine Learning with Intel Movidius Neural Compute Stick ( Myriad2 VPU )

What is Machine Learning?

Arthur Samuel described it as: "the field of study that gives computers the ability to learn without being explicitly programmed."

What is Intel Movidius Neural Compute Stick?

The Intel® Movidius™ Neural Compute Stick (NCS) is a tiny fanless deep learning device that you can use to learn AI programming at the edge. NCS is powered by the same low power high performance Intel Movidius Vision Processing Unit (VPU) that can be found in millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, and more.

Technical Specifications
Processor Intel® Movidius™ 2 VPU ( Vision Processing Unit )
Supported Frameworks TensorFlow™, Caffe
Connectivity USB 3.0 Type-A
Dimensions USB stick (72.5mm X 27mm X 14mm)
Operating Temp0° - 40° C

Minimum system requirements
x86_64 computer running Ubuntu* 16.04 or
Raspberry Pi 3 Model B running Stretch desktop or Ubuntu* 16.04 VirtualBox instance,
USB 2.0 Type-A port (Recommend USB 3.0),
1GB RAM, 4GB free storage space

The Intel® Movidius™ Neural Compute Stick (Intel® Movidius™ NCS) is an embedded machine intelligence platform from Movidius, an Intel company. Through software and hardware tools, the Intel Movidius NCS brings machine intelligence and AI out of the data centers and into end-user devices. The Intel Movidius NCS is designed to help democratize the machine intelligence space, and accelerate an age of ubiquitous intelligence devices and systems.

Hardware

Raspberry Pi 3B Board with SD card and accessories.
Intel Movidius Neural Compute Stick
USB Camera

Software and Library

Raspbien Stretch OS
OpenCV 3.3.0
Python 3.x
Intel® Movidius™ NCSDK

Run Demo

Image Classification

Image Classifier with Python GUI

Video Objects Detection

Reference

https://software.intel.com/en-us/neural-compute-stick/get-started
https://github.com/movidius/ncappzoo/

My Website

http://softpowergroup.net/

email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400

วันพุธที่ 22 สิงหาคม พ.ศ. 2561

Raspberry pi Face Recognition

Raspberry pi Face Recognition with OpenCV

Built using dlib's state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38%

Hardware

Raspberry Pi 3B Board with SD card and accessories.

Software and Library

Raspbien Stretch OS
OpenCV 3.3.0
Python 3.x
dlib library 19.x

First You must install openCV on your raspberry pi.

If you don't have it see this

Install OpenCV on Raspberry Pi

http://raspberrypi4u.blogspot.com/2018/08/raspberry-pi-install-opencv.html

Update and Libraries

sudo apt-get update
sudo apt-get upgrade
sudo apt-get install build-essential \
    cmake \
    gfortran \
    git \
    wget \
    curl \
    graphicsmagick \
    libgraphicsmagick1-dev \
    libatlas-dev \
    libavcodec-dev \
    libavformat-dev \
    libboost-all-dev \
    libgtk2.0-dev \
    libjpeg-dev \
    liblapack-dev \
    libswscale-dev \
    pkg-config \
    python3-dev \
    python3-numpy \
    python3-pip \
    zip
sudo apt-get clean

Install Dlib

Before Install dlib.

Temporary enable a larger swap file size ( For the dlib compile won't fail )

sudo nano /etc/dphys-swapfile

< change CONF_SWAPSIZE=100 to CONF_SWAPSIZE=1024 and save / exit nano >

sudo /etc/init.d/dphys-swapfile restart

Now Install Dlib

git clone https://github.com/davisking/dlib.git

cd dlib

sudo python3 setup.py install --compiler-flags "-mfpu=neon"

Install Face Recognition

sudo pip3 install face_recognition

Reference
https://github.com/ageitgey/face_recognition

http://dlib.net/

My Website

http://softpowergroup.net/

email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400

Google+ https://plus.google.com/+SoftpowergroupNetThailand/

Android and Arduino IoT

Android Arduino Control Hardware

วันศุกร์ที่ 10 สิงหาคม พ.ศ. 2561

Install OpenCV on Raspberry Pi

Install openCV on Raspberry Pi

In this blog post I demonstrated how to install OpenCV 3 with Python 2.7 and Python 3 on Raspberry pi 3B.

What is OpenCV?
OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library.
https://opencv.org/about.html

Hardware

Raspberry Pi 3B Board with SD card and accessories.

Software and Library

Raspbien Stretch OS
OpenCV 3.3.0

Install OpenCV on Raspberry Pi

Update First.

sudo apt-get update sudo apt-get upgrade sudo rpi-update

Cmake (builder and compiler)

sudo apt-get install build-essential cmake pkg-config git

dependencies Image และ Video IO

sudo apt-get install libjpeg-dev libtiff5-dev libjasper-dev libpng12-dev sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev sudo apt-get install libxvidcore-dev libx264-dev

HiGUI
sudo apt-get install libgtk2.0-dev libgtk-3-dev
sudo apt-get install libatlas-base-dev gfortran

Python Dev
sudo apt-get install python2.7-dev python3-dev

OpenCV source code

wget -O opencv.zip https://github.com/Itseez/opencv/archive/3.3.0.zip

unzip opencv.zip

wget -O opencv_contrib.zip https://github.com/Itseez/opencv_contrib/archive/3.3.0.zip

unzip opencv_contrib.zip

Build

cd opencv-3.3.0

mkdir build
 cd build
 cmake -D CMAKE_BUILD_TYPE=RELEASE \
    -D CMAKE_INSTALL_PREFIX=/usr/local \
    -D INSTALL_PYTHON_EXAMPLES=ON \
    -D OPENCV_EXTRA_MODULES_PATH=/home/pi/opencv_contrib-3.3.0/modules \
    -D BUILD_EXAMPLES=ON \
    -D WITH_OPENGL=ON \
    -D WITH_V4L=ON ..

Change Some config

sudo /etc/init.d/dphys-swapfile stop
sudo nano /etc/dphys-swapfile

set CONF_SWAPSIZE 100 (100 MB) to 1024 (1 GB)
then reboot

login again

sudo /etc/init.d/dphys-swapfile start

MAKE ( it take 2 hours )
make -j4

sudo make install sudo ldconfig

Test Import OpenCV in python code

python

import cv2

cv2.__version__

Raspberry pi OpenCV Application

Raspberry Pi Car Detection with OpenCV

http://raspberrypi4u.blogspot.com/2018/06/raspberry-pi-car-detection-with-opencv.html

Raspberry Pi Face Detection with OpenCV

http://raspberrypi4u.blogspot.com/2018/06/raspberry-pi-face-detection-opencv.html

Reference

https://raspberrypi-thailand.blogspot.com/2016/07/opencv-310-raspberry-pi.html

https://raspberrypi-thailand.blogspot.com/2018/02/opencv-34-raspbian-stretch-released-27.html

https://www.pyimagesearch.com/2017/09/04/raspbian-stretch-install-opencv-3-python-on-your-raspberry-pi/

My Website

http://softpowergroup.net/

email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400

Google+ https://plus.google.com/+SoftpowergroupNetThailand/

Android and Arduino IoT

Android Arduino Control Hardware

วันอังคารที่ 26 มิถุนายน พ.ศ. 2561

Raspberry Pi Car Detection with OpenCV

Raspberry Pi Face Detection with OpenCV

Car or Vehicle Detection is famous technology now.I'd like to use it also for the cheap one you can use raspberry pi board with openCV in python code.

Hardware

Raspberry Pi 3B Board with SD card and accessories.

Software and Library

Raspbien Stretch OS
OpenCV 2.4.9.1 ( How to install opencv on raspberry pi )
Python 2.7.13

check python and openCV version

check openCV library and version

Demo

Run python from video file.

Source Code

https://drive.google.com/file/d/1hYa5s7fjvQc1S1wRY6GcRqOPwL0Hy_aE/view

Reference

http://www.technicdynamic.com/2017/08/28/python-motion-detection-with-opencv-simple/

Making Road Traffic Counting App based on Computer Vision and OpenCV

https://medium.com/machine-learning-world/tutorial-making-road-traffic-counting-app-based-on-computer-vision-and-opencv-166937911660

CarND-VehicleDetection

https://chatbotslife.com/vehicle-detection-and-tracking-using-computer-vision-baea4df65906

My Website

http://softpowergroup.net/

email : info@softpowergroup.net ,amphancm@gmail.com Tel .+6681-6452400

Google+ https://plus.google.com/+SoftpowergroupNetThailand/

Android and Arduino IoT

Android Arduino Control Hardware

วันพฤหัสบดีที่ 21 มิถุนายน พ.ศ. 2561

Raspberry Pi Face Detection with OpenCV

Face Detection is famous technology now.I'd like to use it also for the cheap one you can use raspberry pi board and web camera with openCV in python code.