TACO: Trajectory Aligning Cross-view Optimisation

TACO is a Python library for pose graph optimisation that fuses IMU (Inertial Measurement Unit) data with CVGL (Cross-View Geo-Localisation) image-based measurements for robust 6-DOF pose estimation.

Built on GTSAM (Georgia Tech Smoothing and Mapping).

Installation

pip install taco

For development:

git clone https://github.com/tavisshore/taco.git
cd taco
pip install -e ".[dev]"
pre-commit install

Quick Start

TODO

Running Tests

pytest

With coverage:

pytest --cov=taco --cov-report=html

Code Quality

# Format code
black src tests
# Lint code
ruff check src tests
# Type checking
mypy src

Pre-commit Hooks

pre-commit install
pre-commit run --all-files

License

This project is licensed under the MIT License - see the LICENSE file for details.