Mar 222018
 

OpenCV is an open-source framework for computer vision. It’s used for self-driving cars, surveillance, CCTV, traffic flow measurement, autonomous robots, license plate recognition, gesture recognition, and just about any other application where a computer needs to “see”.

You’ll have seen OpenCV in action whenever you’ve watched a surveillance scene in a film or documentary showing boxes being automatically drawn around moving people or cars on a computer screen.

OpenCV 3.3.0 runs well on a Raspberry Pi 3 using either the Pi camera module, USB webcam or USB video grabber and CCTV camera. Our examples run in Python 3. We have different code examples for the Pi camera and USB webcam/video grabber.

Here’s face recognition running on a Raspberry Pi 3 with the Raspberry Pi NoIR camera module

And here’s my CCTV system hooked up to the Raspberry Pi using a USB video grabber

This script looks for movement in the right of the image and saves time and date stamped photos of intruders to the Raspberry Pi’s micro SD card.

It would be quite easy to have it email the photo to you also.

There’s a full PDF guide with download links for our Python scripts here: https://www.securipi.co.uk/OpenCV.pdf

Here’s what each script does:

test-video-picam.py – shows a live feed from the Pi camera on your Desktop

find-faces-picam.py – displays a box around any face found in the Pi camera feed

find-faces-picam2.py – as above but records time stamped photos to SD card too.

mog-picam-1.py – Uses Mog2 background subtractor, takes a photo of large items on the left.

mog-picam-2-.py – as above but with erosion and dilation filters too.

Also similar examples for USB webcam or USB video grabber, without the picam titles:

test-video.py – shows live vide feed from USB webcam or USB video grabber.

find-faces.py – finds faces in the video feed and draws a box around them.

mog.py – Uses Mog2 background subtractor to find intruders and cars on our CCTV camera.

By comparing test-video-picam.py and test-video.py you can see exactly how to modify other OpenCV Python scripts for use with Raspberry Pi camera or USB webcam.

 

You can buy the OpenCV3 compatible USB video grabber we used, that will let you attach any video device with a composite output to your Pi, here:

https://www.amazon.co.uk/dp/B072Q4MNKM

https://www.amazon.com/dp/B072Q4MNKM

Jul 112017
 

The Senior Guardian project uses a PIR motion sensor to discretely keep an eye on an older vulnerable relative who lives alone.

Each time a person walks past the PIR sensor it adds one to the number of movements detected that hour. It stores the number of movements detected each hour in a Python list and can send an email to your PC or phone that looks like this:

If you didn’t see any PIR detections at times you’d normally expect them to be up & around, then you could call them up to check everything’s okay or get a neighbour to check on them.

The PIR sensor attaches on GPIO pin 4 and is wired up like this:

or you could use one of our PIR Adapter Clips if you don’t want to use cables.

This version of the Python script (pir5.py) emails a copy of today’s log to two different email addresses once an hour (there are other variations in our download)

Download our free PDF Guide : Senior Guardian PDF guide

Download the Senior Guardian scripts direct to your Pi with

wget www.securipi.co.uk/sg.zip
unzip sg.zip

Buy a PIR with Cables and GPIO pin card £3

Buy a PIR Alarm kit for Raspberry Pi £11.99

Jun 192017
 

Plug in a USB microphone

Increase mic volume for USB device to full using

alsamixer

Screenshot - 150617 - 11:14:09

(F6 to change to USB device and arrow keys move across to Mic and up arrow increases volume to full, Esc to quit)

Make a test recording:

arecord -D plughw:1,0 -f S16_LE test.wav

CTRL-C to quit

aplay test.wav

Sign up to Google cloud platform for free

https://console.cloud.google.com/start

google-cloud

Google Cloud Speech API -> go to Credenitials tab -> Create Credentials -> API Key -> cut and paste your API key for use in speechAnalyser.py later

sudo apt-get install mplayer

sudo apt-get install sox

sudo apt-get install flac

sudo apt-get install python-pycurl

sudo apt-get install python-pip

sudo pip install feedparser

sudo pip install yahoo-finance

search for stock/share symbols at https://uk.finance.yahoo.com/lookup/ and edit getShares.py to suit.
while in folder /home/pi pull ZIP file from our server with

wget www.securipi.co.uk/vr.zip

unzip vr.zip

chmod a+x speech.sh

edit speechAnalyser.py so it contains your Google Cloud Speech API key

nano speechAnalyser.py

save it and exit

run it while connected to the internet

python speechAnalyser.py

say the trigger word “oscar”, wait for a beep, and then say either “news, weather, shares, time, light on, light off, flatter me”

(light on & light off control a red LED with a 220 ohm resistor connected to GPIO4 and GND pins)

You can make a really good room mic, with 15 feet range, using a USB audio adapter and a MAX9812 amplified microphone (cost about £5 for both items on eBay)

usb-mic

You can download our 3D print case design from

http://www.securipi.co.uk/usb-mic-holder.stl

usb-mic-case

Use a hot-glue gun to secure the boards in place.

http://www.securipi.co.uk/vr.pdf
http://www.securipi.co.uk/vr.zip

With thanks to these web pages:

https://randomconsultant.blogspot.co.uk/2017/01/building-amazon-echo-like-device-with.html
and
https://pypi.python.org/pypi/yahoo-finance

Mar 212017
 

CIMG3152

To make this security camera project you’ll need:

  • Raspberry Pi Zero W
  • Raspberry Pi camera module
  • SG90 micro servo
  • Micro SD card with latest Raspbian Jessie
  • 3D printed bracket and base
  • 8x Nylon M2 nuts and bolts
  • 20x 2p coins to weight the base down

The STL files to print the brackets are at www.securipi.co.uk/twistcam.zip

CIMG3153

and you can edit the original files at:

https://www.tinkercad.com/things/jSjNEIT4z5V-twistcam-base-4-raspberry-pi-zero-w-and-servo-cctv-surveiilance

https://www.tinkercad.com/things/i6WyzsOBSMX-twistcam-using-raspberry-pi-zero-w-and-servo-cctv-surveiilance

CIMG3154

Before attaching the Raspberry Pi and camera to the 3D printed parts, it’s a good idea to do the following at the Desktop -> Preferences ->Raspberry Pi Configuration:

  • Enable SSH
  • Change passwords for Pi and Root users to something secure and hard to guess.
  • Enable the camera
  • Boot to CLI

Reboot the Pi and login to the terminal

sudo iwlist wlan0 scan

will show WiFi routers near your Pi

sudo nano /etc/wpa_supplicant/wpa_supplicant.conf

and add these lines at the bottom, using your routers SSID name and password

network={
ssid="testing"
psk="testingPassword"
}

Save the file, exit and reboot your Pi. It should now auto-attach to your wireless network when it boots up.

The servo wires can be soldered directly in place, or use a Pimoroni GPIO hammer header and cables instead.

twistcam1_bb

Assemble all the parts together

We’re using the open-source ServoBlaster code to control the servo from the BASH command line.

We install it like this:

mkdir twistcam

cd twistcam

wget https://raw.githubusercontent.com/richardghirst/PiBits/master/ServoBlaster/user/servod.c

wget https://raw.githubusercontent.com/richardghirst/PiBits/master/ServoBlaster/user/Makefile

wget https://raw.githubusercontent.com/richardghirst/PiBits/master/ServoBlaster/user/init-script

wget https://raw.githubusercontent.com/richardghirst/PiBits/master/ServoBlaster/user/mailbox.c

wget https://raw.githubusercontent.com/richardghirst/PiBits/master/ServoBlaster/user/mailbox.h

make servod

sudo ./servod

Then test it’s working with:

echo 5=50% > /dev/servoblaster

echo 5=10% > /dev/servoblaster

echo 5=90% > /dev/servoblaster

The commands above move servo number 5 (Pan left & right) on GPIO23 between centre (50%),
left (10%) & right (90%) positions

Setup Video Streaming to a web browser.

On your Raspberry Pi, while in the twistcam folder we made earlier:

sudo apt-get install libav-tools git python3-picamera python3-ws4py

Download the zip file with:

wget http://www.securipi.co.uk/tcs.zip

unzip tcs.zip

chmod a+x *.sh

python3 server.py

Then go to another PC on your network and open a web browser to:

http://ip-address-of-your-pi:8082/

back-room

And you should be able to pan the camera left and right using the slider, with hardly any lag.

 

Disable the red LED on the camera.

When you’re streaming video, you might not want anyone to know when the camera is active. It’s possible to turn off the camera’s red activity LED by doing this:

sudo nano /boot/config.txt

And at the end of the file add the line

disable_camera_led=1

Save and reboot your Pi.

Mounting the twistcam upside down.

The Twistcam is designed to sit on a flat surface the right way up, but if you mount it upside down , hanging from a ceiling or shelf then the video will be upside down and the pan controls the wrong way around. You can fix it by downloading this patch and overwriting the original server.py file.

wget http://www.securipi.co.uk/server.py

 

Start video streaming automatically at boot.

Edit /etc/rc.local so that servod and python3 server.py launch at startup.

nano /etc/rc.local

Insert these lines before the last line which says exit 0

cd /home/pi/twistcam
sudo ./servod
python3 server.py

Save the file and reboot your Pi. Video feed can be controlled from PC or phone.

phone2

If you don’t have access to a 3D printer, you can buy the two 3D printed brackets and 8x nylon M2 nuts and bolts here for £11.99 inc VAT.

(Raspberry Pi, Camera and SG90 servo NOT included)



Quantity :

 

We ship worldwide. Next day delivery in UK and 14 days for delivery worldwide.

Feb 092016
 

PocketPi is a portable Raspberry Pi Zero with a 5600mAh rechargeable battery and 4 port hub that you assemble yourself.

pocketpi1

all combined into a 3D printed custom case that measures just 92mm x 42mm x 25mm & looks like this when complete

pocketpi5

the boards are soldered together like this

pocketpi3

and fit into the case like this

pocketpi4

you use a hot-glue gun to fix the parts in place

full instructions can be found in our PDF, including buying links for each part here:

and here’s the STL file for 3D printing your own case and lid

You can edit the design of the case to add your own tweaks here:

https://tinkercad.com/things/eZgIrStOwwx

pocketpi8

If you like this post please follow @securipi on Twitter