In this paper, we are specifically interested in utilizing LiDARs and LiDAR-generated images for tracking Unmanned Aerial Vehicles (UAVs) in real- time which can benefit applications including docking, remote identification, or counter-UAV systems, among others. This is, to the best of our knowledge, the first work that explores the possibility of fusing the images and point cloud generated by a single LiDAR sensor to track a UAV without a priori known initialized position. We trained a custom YOLOv5 model for detecting UAVs based on the panoramic images collected in an indoor experiment arena with a MOCAP system. By integrating with the point cloud, we are able to continuously provide the position of the UAV. Our experiment demonstrated the effectiveness of the proposed UAV tracking approach compared with methods based only on point clouds or images.
You can check our paper in arxiv
Diagram of proposed UAV tracking system based on the image and point cloud generated by an Ouster LiDAR
Example of a signal image (top) and its corresponding point cloud with background removed (bottom).
python3 -m pip install 'ouster-sdk[examples]'
pip install yolov5
pip install open3d
pip install opencv-python
git clone https://github.com/ultralytics/yolov5.git
jupyter notebook --> YOLOv5_train_Ouster.ipynb ## need to prepare your own training data-
Download Ouster pcap frist [pcap ]
-
Run the code
python3 ouster_track.py ## still need to optimize -
Use python scripts to validate
python3 ./scrpits/plot_velo.py python3 ./scrpits/plot_error.py python3 plot_traj.py
Apply YOLOV5 to the signal image to track UAV and 3d plot of the final UAV trajectory
