Manual Yolo V7 (Python) integration in HA

[wmaker (Tommy Long)]

I’m not sure how much more I can help, but I will explain my setup:

• The camera detects motion, takes a snapshot and sends the snapshot as a jpeg image file to a remote directory. It is also setup to ignore further motion detection for a period of time so as to not get a rapid fire sequence of motion events.
• The new snapshot image file is detected on the remote directory and Deepstack is called to analyze the image and provide results.
• Deepstack’s results are then further filtered say based on what kind of objects detected, confidence level, etc. and depending on these results, HA can be notified.

I use a Windows based tool called AI Tool which detects the new snapshot image file, and it is the one that calls Deepstack with the image, and filters Deepstack’s results. One of its filtering capabilities I like is that I can setup masks to ignore certain locations of the snapshot image from having objects detected. After filtering, AI Tool sends an MQTT message to HA. Once HA gets the message I use an automation to notify me of certain objects being detected.

Rob Cole has tried to implement some of the same capabilites as AI Tool using various custom HA integrations (again using Deepstack).

Face and person detection with Deepstack - local and free!

Hi all I just published a custom component for face and object (e.g. person) detection using Deepstack, which runs locally in Docker and costs you nothing. You will need a computer with a decent amount of RAM available, as Deepstack is using deep-learning models. Therefore don’t expect to run this on a pi, but a spare laptop should do. Any feedback on usage here, and bug reports on Github. Thanks! [image]

Deepstack UI

I created a streamlit app for exploring the predicitons of Deepstack object detection, allowing a user can upload an image and filter objects by class, confidence (%) and location in the image. These are configurable parameters for my deepstack-object integration, so it is useful to have an app to explore the effect of these parameters. The app is running in a docker container so no need to install anything in order to run it (assuming you have docker installed). Created this thread to discuss …

I think your bigger question is, if I were to use Yolov7, how could I do all of the above? the answer is I really don’t know.

@SuperMaximus

P.P.S Does Deepstack use YoloV5?

Mostly yes for object detection, but see this link which says they have done something to remove some of the dependencies on Yolov5 codebase.
I should also mention that Deepstack also supports Person detection and custom training.