Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Parking Spot detection from ONVIF camera and defined regions publishing status to MQTT

Notifications You must be signed in to change notification settings

JayGoldberg/ParkingSpotDetection

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Parking Spot Detection

image image

Steps

  • Go to your home location ( My documents or where you want to have the folder created )
  • Run the docker Container in that folder
docker run -d \
  --name parking-monitor \
  -p 5000:5000 \
  -v "$(pwd)/ParkingSpotDetection:/app" \
  -v /var/run/docker.sock:/var/run/docker.sock \
  -v /etc/localtime:/etc/localtime:ro \
  -v /etc/timezone:/etc/timezone:ro \
  --restart unless-stopped \
  --network bridge \
  royal911/parking-monitor:latest
  • Clone the repository

  • git clone https://github.com/Royal911/ParkingSpotDetection.git
    
  • Edit the config.json

    • RTSP Link
    • Frame interval ( How often a picture is taken )
    • Enable or Disable the OFF Hours ( when the parking check is disabled )
    • Allowed Classes [2, 3, 5, 7] | [Car,Motorcycle,Bus,Truck]
    • Intersection Threshold - Determines how much overlap is required to say an object is inside a spot | You could go a bit higher (0.4) for stricter rules or lower (0.2) for loose inclusion.
    • Conf Threshold - Very low — will detect almost everything, including weak/confused predictions | But if you get too many false positives, increase to 0.2 or 0.3
    • IF OFF Hours is ON:
      • Select the starting time and the stoping time off the OFF Hours
    • Broker IP address and Port
  • Restart the container

  • Open the webpage : http://localhost:5000/ - replace the locahost with your host ip image

  • Go to Define Spots and Define your own spots for detection

  • There is also a http://localhost:5000/latest_frame.jpg that you can use if planning to use Home Assistant to send picture with notification when there is a free or ocupied space

About

Parking Spot detection from ONVIF camera and defined regions publishing status to MQTT

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Python 54.5%
  • HTML 45.5%