Search results

  1. N

    AI motion detection with BlueIris: an alternate approach

    Note: I will no longer be providing release updates or responding to questions on this thread. If you would like to stay up-to-date on releases you can subscribe to release notifications on the github project. For support open a github support issue.
  2. N

    AI motion detection with BlueIris: an alternate approach

    Version 5.3.1 is out. This release updates a dependency and now, hopefully, file watching for people on Macs who are mounting a network share with the images will work! There are no breaking changes in this release. To update do docker-compose pull then docker-compose up -d.
  3. N

    AI motion detection with BlueIris: an alternate approach

    You do not need a GPU. 16GB of RAM is plenty.
  4. N

    AI motion detection with BlueIris: an alternate approach

    Did you use Visual Studio Code to edit the files as mentioned in the documentation? It will provide full Intellisense auto-complete and validation of the files as you type.
  5. N

    AI motion detection with BlueIris: an alternate approach

    What was the problem? Maybe there's a way I can add some logs to detect that situation for others.
  6. N

    AI motion detection with BlueIris: an alternate approach

    Well I'm out of ideas. Please open another support request. Make sure to include Your complete docker-compose.yml file and where you have this file stored locally on your machine Your complete settings.json file Your complete triggers.json file The entire log output from the trigger container...
  7. N

    AI motion detection with BlueIris: an alternate approach

    Also what is the full path to the folder on your local machine?
  8. N

    AI motion detection with BlueIris: an alternate approach

    Is your drop folder a network share that's mounted to your computer running Docker? Or is it a local folder on the same machine as Docker?
  9. N

    AI motion detection with BlueIris: an alternate approach

    Yup it's up and running and working fine. Walk in front of your cameras and check to see if you get any logs saying a new image was detected. Check and make sure your aiinput folder is actually getting new images from BlueIris. Make sure your wildcard pattern for the filename matches the file...
  10. N

    AI motion detection with BlueIris: an alternate approach

    What do the logs for the trigger container show? There are tons of logs that will tell you if files were loaded successfully, if there were any errors, whether files are getting picked up and processed, etc.
  11. N

    AI motion detection with BlueIris: an alternate approach

    For further assistance with this please open a support request over in the github repo. Make sure to include your complete docker-compose.yml file and the complete output logs from Docker. Edit: Missed that this was a question about getting AI Tool working with Deepstack installed via my...
  12. N

    AI motion detection with BlueIris: an alternate approach

    Did you change anything in it? Are you just using straight Docker Desktop, or are you using something like Portainer or UnRaid?
  13. N

    AI motion detection with BlueIris: an alternate approach

    Are you using the provided docker-compose.yaml file?
  14. N

    AI motion detection with BlueIris: an alternate approach

    I believe you can use a straight wildcard down the folder structure in your watchPattern, e.g. cameraName///*. Note that there is a pretty big performance hit to this as it winds up being a lot of folders to watch for. For #2 a cron job that runs occasionally to do rm -rf on the folders would...
  15. N

    AI motion detection with BlueIris: an alternate approach

    I suggest handling this via automation and not via enabling/disabling triggers. That's how I have it set up using Home Assistant and NodeRed. 1. Remove the webRequest handlers 2. Create NodeRed automations that listen for the MQTT events 3. Have NodeRed decide whether to send a web request to...
  16. N

    AI motion detection with BlueIris: an alternate approach

    Not currently. Why do you need this?
  17. N

    AI motion detection with BlueIris: an alternate approach

    See the configuration options wiki.
  18. N

    AI motion detection with BlueIris: an alternate approach

    Version 5.3.0 is now out. This adds the ability to see a list of the stored original and annotated images. Go to http://localhost:4242/originals/ and http://localhost:4242/annotated/ in your browser to see a list of the stored images. This requires the webserver (or annotations) are enabled to...
  19. N

    AI motion detection with BlueIris: an alternate approach

    This is already supported via the internal web server. See danecreekphotography/node-deepstackai-trigger, scroll down to the paragraph that starts with "The basename property".
  20. N

    AI motion detection with BlueIris: an alternate approach

    The annotated image is stored temporarily and available via the web server through a direct URL access, however there is no way to see a directory of all the images. I'll look at exposing that so you could at least hit the web server and see all the images. I don't have plans to add storing...
  21. N

    AI motion detection with BlueIris: an alternate approach

    As I mentioned above this isn't supported. I'm not aware of any way to get the URL to the clip back from BlueIris after triggering the event.
  22. N

    AI motion detection with BlueIris: an alternate approach

    Yes, but in real world setups you don't get that many notifications, so chances are the clip you want is the first clip in the list.
  23. N

    AI motion detection with BlueIris: an alternate approach

    Not that I'm aware of.
  24. N

    AI motion detection with BlueIris: an alternate approach

    Another thing you can do is look at splitting the camera images out into separate folders. Have a folder for, say, every 5 cameras, then update the watchPattern on the cameras to point to the correct sub-folder.
  25. N

    AI motion detection with BlueIris: an alternate approach

    I highly recommend setting BI to clear the folder after 1 hr or 1GB of data. The more images you have in the folder the slower things will get due to how new file detection works.
  26. N

    AI motion detection with BlueIris: an alternate approach

    Did you read the section on high cpu usage?
  27. N

    AI motion detection with BlueIris: an alternate approach

    Are you running the cameras with direct-to-disk recording? If not you should be. Also see the troubleshooting wiki for how to resolve high CPU usage.
  28. N

    AI motion detection with BlueIris: an alternate approach

    The system logs everything. Run Docker Desktop and look at the log output from the trigger container. It'll show what was detected, the confidence level etc.
  29. N

    AI motion detection with BlueIris: an alternate approach

    Version 5.2.1 is now available. This release addresses two minor security vulnerabilities in dependent libraries. There are no functional changes. To update run docker-compose pull then docker-compose up to restart.
  30. N

    AI motion detection with BlueIris: an alternate approach

    If you set the cameras up as described on the wiki you'll get full HD streams when you hit UI3 to view both recorded and live footage.
Top