Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/robmarkcole/hass-machinebox-tagbox
Home-Assistant custom integration for image tag detection using Tagbox
https://github.com/robmarkcole/hass-machinebox-tagbox
camera detection hass-machinebox-tagbox home-assistant image-classification machinebox tagbox
Last synced: 6 days ago
JSON representation
Home-Assistant custom integration for image tag detection using Tagbox
- Host: GitHub
- URL: https://github.com/robmarkcole/hass-machinebox-tagbox
- Owner: robmarkcole
- License: mit
- Created: 2018-04-02T05:57:09.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2021-06-16T17:09:11.000Z (over 3 years ago)
- Last Synced: 2024-12-24T20:01:51.154Z (10 days ago)
- Topics: camera, detection, hass-machinebox-tagbox, home-assistant, image-classification, machinebox, tagbox
- Language: Python
- Homepage: https://machinebox.io/docs/tagbox/recognizing-images
- Size: 10.9 MB
- Stars: 5
- Watchers: 3
- Forks: 2
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Home-Assistant custom component for image classification (`tag` detection) using Machinebox.io [Tagbox](https://machinebox.io/docs/tagbox/recognizing-images). The component adds an `image_processing` entity, where the state of the entity is the most likely tag in the image above a given confidence threshold. The attribute `tags` contains all data returned by the API, whilst the attribute `matched_tags` contains only tags matched with a confidence greater than a `confidence` threshold (in %). The event `tagbox.detect_tag` is fired for each tag above the confidence threshold, and the event data contains the fields `name` of tag, `confidence` of detection, and the `entity_id` that fired the event.
Place the `custom_components` folder in your configuration directory (or add its contents to an existing custom_components folder).
Add to your HA config:
```yaml
image_processing:
- platform: tagbox
ip_address: localhost
port: 8080
confidence: 50
source:
- entity_id: camera.local_file
```
Configuration variables:
- **ip_address**: the ip of your Tagbox instance
- **port**: the port of your Tagbox instance
- **confidence**: (Optional, default 80) The threshold in % above which tags appear in `matched_tags` and `tagbox.detect_tag` events are fired.
- **source**: must be a camera.
### Tagbox
Get/update Tagbox [from Dockerhub](https://hub.docker.com/r/machinebox/tagbox/) by running:
```
docker pull machinebox/tagbox
```
[Run Tagbox with](https://machinebox.io/docs/tagbox/recognizing-images):
```
MB_KEY="INSERT-YOUR-KEY-HERE"
docker run -p 8080:8080 -e "MB_KEY=$MB_KEY" machinebox/tagbox
```
To limit tagbox to only custom tags, add to the command `-e MB_TAGBOX_ONLY_CUSTOM_TAGS=true`. Tagbox will be then only return and calculate custom tags, saving some compute resources.
```
docker run -p 8080:8080 -e "MB_KEY=$MB_KEY" -e MB_TAGBOX_ONLY_CUSTOM_TAGS=true machinebox/tagbox
```
You should see a message on startup `pretrained tags are disabled, only custom tags will be returned`.
### Default tags
Tagbox is trained on https://storage.googleapis.com/openimages/web/index.html with the default tags listed in `tagbox_classes.csv`
### Teaching tagbox
I've written a script to allow teaching tagbox from folders of images, the script is at https://github.com/robmarkcole/tagbox_python
#### Limiting computation
[Image-classifier components](https://www.home-assistant.io/components/image_processing/) process the image from a camera at a fixed period given by the `scan_interval`. This leads to excessive computation if the image on the camera hasn't changed (for example if you are using a [local file camera](https://www.home-assistant.io/components/camera.local_file/) to display an image captured by a motion triggered system and this doesn't change often). The default `scan_interval` [is 10 seconds](https://github.com/home-assistant/home-assistant/blob/98e4d514a5130b747112cc0788fc2ef1d8e687c9/homeassistant/components/image_processing/__init__.py#L27). You can override this by adding to your config `scan_interval: 10000` (setting the interval to 10,000 seconds), and then call the `scan` [service](https://github.com/home-assistant/home-assistant/blob/98e4d514a5130b747112cc0788fc2ef1d8e687c9/homeassistant/components/image_processing/__init__.py#L62) when you actually want to process a camera image. So in my setup, I use an automation to call `scan` when a new motion triggered image has been saved and displayed on my local file camera.
## Local file camera
Note that for development I am using a [file camera](https://www.home-assistant.io/components/camera.local_file/).
```yaml
camera:
- platform: local_file
file_path: /images/thebeatles.jpg
```