🛰️ A deep-learning–based system for automated detection and classification of military vehicles in video data. Orion integrates visual recognition, motion analysis, and tracking modules to provide real-time situational awareness in complex environments.

Checkout Orion's documentation for help.

Orion provides YOLO12 models fine-tuned on a custom dataset of military vehicles with 4 classes.

Orion requires a recent version of python: .

Clone the repository and install the project in your python environment, either using pip

git clone https://github.com/jonasrenault/orion.git cd orion pip install --editable .

or uv

git clone https://github.com/jonasrenault/orion.git cd orion uv sync

When you install Orion in a virtual environment, it creates a CLI script called orion. Run

orion --help

to see the various commands available (or take a look at the documentation for examples).

The predict command will use one of orion's models to detect military vehicles in images. For example, if you downloaded the orion12m.pt model file into your current directory, and want to use it to detect military vehicles in an image, run

orion predict ./orion12m.pt resources/test/afvs.jpg -s

The predict command with the -s option will save the annotated image:

The track command will use one of orion's models to track military vehicles in videos. For example, if you downloaded the orion12m.pt model file into your current directory, and want to use it to track military vehicles in a video, run

orion track ./orion12m.pt resources/test/mev1.mp4

• The orion directory contains the source code used to fetch and format datasets for fine-tuning a YOLO12 model for object detection.
• The resources directory contains video samples for vehicle detection task.
• The notebooks directory contains exemple notebooks on how to
  1. Prepare a custom dataset of images annotated for automatic target recognition of military vehicles.
  2. Train a YOLO12 model using the prepared dataset.
  3. Evaluate a fine-tuned model on a realistic test dataset.

To run the notebooks, start a jupyter lab server with

jupyter lab

and open one of the notebooks in the notebooks directory.