- Supported Bit Versions
-
- 64-bit
- Source Code URL
- https://github.com/occ-ai/obs-detect
- Minimum OBS Studio Version
- 30.0.0
- Supported Platforms
-
- Windows
- Mac OS X
- Linux
A plugin that allows you to detect >80 types of objects in any source, track them and apply masking.
If you like this work please consider supporting it by sponsoring us on GitHub, Patreon or OpenCollective
This work uses the great contributions from EdgeYOLO-ROS and PINTO-Model-Zoo.
Contact us for assistance! Visit OCC-AI in our Discord server or on Github
See a feature by @Andilippi on creatively using the plugin for many fun things! https://www.twitch.tv/videos/2104923413
See a tutorial in Spanish by Angel Mendez https://www.youtube.com/watch?v=E2bO3YcAeo4
If you like this work please consider supporting it by sponsoring us on GitHub, Patreon or OpenCollective
This work uses the great contributions from EdgeYOLO-ROS and PINTO-Model-Zoo.
Contact us for assistance! Visit OCC-AI in our Discord server or on Github
Usage
- Add the "Detect" filter to any source with an image (Media, Browser, VLC, Image, etc.)
- Enable "Masking" or "Tracking"
See a feature by @Andilippi on creatively using the plugin for many fun things! https://www.twitch.tv/videos/2104923413
See a tutorial in Spanish by Angel Mendez https://www.youtube.com/watch?v=E2bO3YcAeo4
Features
Current features:- Detect over 80 categories of objects, using an efficient model (EdgeYOLO)
- 3 Model sizes: Small, Medium and Large
- Face detection model, fast and efficient (YuNet)
- Load custom ONNX detection models from disk
- Filter by: Minimal Detection confidence, Object category (e.g. only "Person"), Object Minimal Size
- Masking: Blur, Pixelate, Solid color, Transparent, output binary mask (combine with other plugins!)
- Tracking: Single object / Biggest / Oldest / All objects, Zoom factor, smooth transition
- SORT algorithm for tracking smoothness and continuity
- Save detections to file in real-time, for integrations e.g. with Streamer.bot
- Precise object mask, beyond bounding box
- Multiple object category selection (e.g. Dog + Cat + Duck)
- Make available detection information for other plugins through settings
There are visca ptz implementations for different cameras so I need to know where to start