Siman Zhang | James Lewis | Shree Singhal | Ryder Paulson | Patrick Donnelly | Burke Havranek
A laser-based tracking and charging system designed to enable continuous in-flight drone operation.
- Clone the repository.
git clone https://github.com/RyderPaulson/Group_2_PANDAS_Drone_Tracking
cd Group_2_PANDAS_Drone_Tracking
- Create a v3.12.11 Python virtual environment. Conda is recommended but not required.
- Install CUDA.
# check if cuda is installed
nvcc --version
If it is not installed, install the appropriate CUDA 12.6 version for your system from here. Set the CUDA_HOME environmental variable to your CUDA instillation.
- Clone and install CoTracker3.
git clone https://github.com/facebookresearch/co-tracker
cd co-tracker
pip install -e .
pip install matplotlib flow_vis tqdm tensorboard
mkdir weights
cd weights
# download the online (multi window) model
wget https://huggingface.co/facebook/cotracker3/resolve/main/scaled_online.pth
# download the online (sliding window) model
wget https://huggingface.co/facebook/cotracker3/resolve/main/baseline_online.pth
cd ..
cd ..
- Clone and install GroundingDINO.
git clone https://github.com/IDEA-Research/GroundingDINO.git
cd GroundingDINO
- Implement this change from GroundingDINO
- Finish the install of GroundingDINO
pip install -e .
mkdir weights
cd weights
wget -q https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth
- Download the tiny weights from our Google Drive groundingdino_swint_ogc into the weights folder.
- Uninstall PyTorch and bundled packages.
pip uninstall torch torchvision
- Navigate to PyTorch's website and install get the correct command for installing PyTorch with CUDA 12.6 on your system.
- Install remaining required Python packages.
TODO
- PyTorch > 2.0.0
- CV2 Latest
- CUDA 12.6
- CoTracker3
- GroundingDINO
TODO Check on Jetson board for specific requirements.