Skip to content

A Unix, Windows, Raspberry Pi Object Speed Camera using python, opencv, video streaming, motion tracking. Includes a Standalone Web Server Interface, Image Search using opencv template match and a whiptail Admin Menu Interface Includes picam and webcam Plugins for motion track security camera configuration including rclone sync script. watch-app…

master
Switch branches/tags
Code

SPEED CAMERA - Object Motion Tracker Mentioned in Awesome <INSERT LIST NAME>

RPI, Unix and Windows Speed Camera Using python, openCV, RPI camera module, USB Cam or IP Cam

For Details See Program Features, Wiki Instructions and YouTube Videos.

RPI Quick curl Install or Upgrade

IMPORTANT - A raspbian sudo apt-get update and sudo apt-get upgrade will NOT be performed as part of
speed-install.sh so it is recommended you run these prior to install to ensure your system is up-to-date.

Step 1 With mouse left button highlight curl command in code box below. Right click mouse in highlighted area and Copy.
Step 2 On RPI putty SSH or terminal session right click, select paste then Enter to download and run script.

curl -L https://raw.github.com/pageauc/speed-camera/master/speed-install.sh | bash

This will download and run the speed-install.sh script. If running under python3 you will need opencv3 installed. See my Github menu driven compile opencv3 from source project

IMPORTANT speed-cam.py ver 8.x or greater Requires Updated config.py and plugins.

cd ~/speed-camera
cp config.py config.py.bak
cp config.py.new config.py

To replace plugins rename (or delete) plugins folder per below

cd ~/speed-camera
mv plugins pluginsold   # renames plugins folder
rm -r plugins           # deletes plugins folder

Then run menubox.sh UPGRADE menu pick.

Program Description

This is a raspberry pi, Windows, Unix Distro computer openCV object speed camera demo program. It is written in python and uses openCV to detect and track the x,y coordinates of the largest moving object in the camera view above a minimum pixel area.

User variables are stored in the config.py file. Motion detection is restricted between y_upper, y_lower, x_left, x_right variables (road or area of interest). Auto calculated but can be overridden in config.py by uncommenting desired variable settings. Motion Tracking is controlled by the track_counter variable in config.py. This sets the number of track events and the track length in pixels. This may need to be tuned for camera view, cpu speed, etc. Speed is calculated based on cal_obj_px and cal_obj_mm variables for L2R and R2L motion direction. A video stream frame image will be captured and saved in media/images dated subfolders (optional) per variable imageSubDirMaxFiles = 2000 For variable settings details see config.py file.

If log_data_to_CSV = True then a speed-cam.csv file will be created/updated with event data stored in CSV (Comma Separated Values) format. This can be imported into a spreadsheet, database, Etc program for further processing. Release 8.9 adds a sqlite3 database to store speed data. Default is data/speed_cam.db with data in the speed table. Database setting can be managed from config.py. Database is automatically created from config.py settings. For more details see How to Manage Sqlite3 Database

Admin, Reports, Graphs and Utilities scripts

  • menubox.sh script is a whiptail menu system to allow easier management of program settings and operation.
  • webserver.py Allows viewing images and/or data from a web browser (see config.py for webserver settings) To implement webserver3.py copy webserver3.py to webserver.py Note and update will undo this change.
  • rclone Manage settings and setup for optional remote file sync to a remote storage service like google drive, DropBox and many others.
  • watch-app.sh for administration of settings from a remote storage service. Plus application monitoring.
  • sql-make-graph-count-totals.py Query sqlite database and Generate one or more matplotlib graph images and save to media/graphs folder. Graphs display counts by hour, day or month for specfied previous days and speed over. Multiple reports can be managed from the config.py GRAPH_RUN_LIST variable under matplotlib image settings section.
  • sql-make-graph-speed-ave.py Query sqlite database and Generate one or more matplotlib graph images and save to media/graphs folder. Graphs display Average Speed by hour, day or month for specfied previous days and speed over. Multiple reports can be managed from the config.py GRAPH_RUN_LIST variable under matplotlib image settings section.
  • sql-speed_gt.py Query sqlite database and Generate html formatted report with links to images and save to media/reports folder. Can accept parameters or will prompt user if run from console with no parameters
  • makehtml.py Creates html files that combine csv and image data for easier viewing from a web browser and saved to media/html folder.
  • speed-search.py allows searching for similar target object images using opencv template matching. Results save to media/search folder.
  • alpr-speed.py This is a demo that processes existing speed camera images with a front or back view of vehicle using OPENALPR License plate reader. Output is saved to media/alpr folder. For installation, Settings and Run details see ALPR Wiki Documentaion

Reference Links

Requirements

Raspberry Pi computer and a RPI camera module installed or USB Camera plugged in. Make sure hardware is tested and works. Most RPI models will work OK. A quad core RPI will greatly improve performance due to threading. A recent version of Raspbian operating system is Recommended.
or
MS Windows or Unix distro computer with a USB Web Camera plugged in and a recent version of python installed For Details See Wiki details.

It is recommended you upgrade to OpenCV version 3.x.x For Easy compile of opencv 3.4.2 from source See https://github.com/pageauc/opencv3-setup

Windows or Non RPI Unix Installs

For Windows or Unix computer platforms (non RPI or Debian) ensure you have the most up-to-date python version. For Downloads visit https://www.python.org/downloads

The latest python versions includes numpy and recent opencv version that is required to run this code. You will also need a USB web cam installed and working. To install this program access the GitHub project page at https://github.com/pageauc/speed-camera Select the green Clone or download button. The files will be cloned or zipped to a speed-camera folder. You can run the code from python IDLE application (recommended), GUI desktop or command prompt terminal window. Note bash .sh shell scripts will not work with windows unless special support for bash is installed for windows Eg http://win-bash.sourceforge.net/ http://www.cygwin.com/ Note I have Not tested these.

Docker Install Quick Start

speed camera supports a docker installation per the following

  1. If you haven't already, install Docker
  2. Clone the repository
  3. Run docker-compose up from the directory you cloned the repo into.
  4. The Docker container will likely exit because it is using a default config.
  5. Edit the configuration file @ config/config.py
  6. Run docker-compose up

Manual Install or Upgrade

From logged in RPI SSH session or console terminal perform the following. Allows you to review install code before running

cd ~
wget https://raw.github.com/pageauc/speed-camera/master/speed-install.sh
more speed-install.sh       # You can review code if you wish
chmod +x speed-install.sh
./speed-install.sh  # runs install script.

Run to view verbose logging

cd ~/speed-camera    
./speed-cam.py

See How to Run speed-cam.py wiki section

IMPORTANT Speed Camera will start in calibrate = True Mode.
Review settings in config.py file and edit variables with nano as required. You will need to perform a calibration to set the correct value for config.py cal_obj_px and cal_obj_mm for L2R and R2L directions. The variables are based on the distance from camera to objects being measured for speed. See Calibration Procedure for more details.

The config.py motion tracking variable called track_counter = can be adjusted for your system and opencv version. Default is 5 but a quad core RPI3 and latest opencv version eg 3.4.2 can be 10-15 or possibly greater. This will require monitoring the verbose log messages in order to fine tune.

Run menubox.sh

cd ~/speed-camera
./menubox.sh

Admin speed-cam Easier using menubox.sh (Once calibrated and/or testing complete)
menubox main menu

View speed-cam data and trends from web browser per sample screen shots. These can be generated from Menubox.sh menu pick or by running scripts from console or via crontab schedule.

Speed Camera GRAPHS Folder Web Page
Speed Camera REPORTS Folder Web Page
Speed Camera HTML Folder Web Page

You can view recent or historical images directly from the speed web browser page. These are dynamically created and show up-to-date images. Press the web page refesh button to update display Speed Camera RECENT Folder Web Page
Speed Camera IMAGES Folder Web Page

Credits

Some of this code is based on a YouTube tutorial by Kyle Hounslow using C here https://www.youtube.com/watch?v=X6rPdRZzgjg

Thanks to Adrian Rosebrock jrosebr1 at http://www.pyimagesearch.com for the PiVideoStream Class code available on github at https://github.com/jrosebr1/imutils/blob/master/imutils/video/pivideostream.py

Have Fun
Claude Pageau
YouTube Channel https://www.youtube.com/user/pageaucp
GitHub Repo https://github.com/pageauc

About

A Unix, Windows, Raspberry Pi Object Speed Camera using python, opencv, video streaming, motion tracking. Includes a Standalone Web Server Interface, Image Search using opencv template match and a whiptail Admin Menu Interface Includes picam and webcam Plugins for motion track security camera configuration including rclone sync script. watch-app…

Topics

Resources

Releases

No releases published

Packages

No packages published