# Separating Drone Point Clouds From Complex Backgrounds by Cluster Filter -- Technical Report for CVPR 2024 UG2 Challenge

arXiv: https://arxiv.org/abs/2412.16947 · HTML: https://mlsanity.com/paper/2412.16947/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark](https://mlsanity.com/paper/2103.13933/) (2021)
- [Dogfight: Detecting Drones from Drones Videos](https://mlsanity.com/paper/2103.17242/) (2021)
- [A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion](https://mlsanity.com/paper/2109.01800/) (2021)
- [Detection and Tracking of Small Objects in Sparse 3D Laser Range Data](https://mlsanity.com/paper/1903.05889/) (2019)
- [Adaptive Lidar Scan Frame Integration: Tracking Known MAVs in 3D Point Clouds](https://mlsanity.com/paper/2103.04069/) (2021)
- [UAV Tracking with Lidar as a Camera Sensors in GNSS-Denied Environments](https://mlsanity.com/paper/2303.00277/) (2023)
- [Audio Array-Based 3D UAV Trajectory Estimation with LiDAR Pseudo-Labeling](https://mlsanity.com/paper/2412.12698/) (2024)
- [Unsupervised UAV 3D Trajectories Estimation with Sparse Point Clouds](https://mlsanity.com/paper/2412.12716/) (2024)
- [TAME: Temporal Audio-based Mamba for Enhanced Drone Trajectory Estimation and Classification](https://mlsanity.com/paper/2412.13037/) (2024)

## Abstract (arXiv)

The increasing deployment of small drones as tools of conflict and disruption has amplified their threat, highlighting the urgent need for effective anti-drone measures. However, the compact size of most drones presents a significant challenge, as traditional supervised point cloud or image-based object detection methods often fail to identify such small objects effectively. This paper proposes a simple UAV detection method using an unsupervised pipeline. It uses spatial-temporal sequence processing to fuse multiple lidar datasets effectively, tracking and determining the position of UAVs, so as to detect and track UAVs in challenging environments. Our method performs front and rear background segmentation of point clouds through a global-local sequence clusterer and parses point cloud data from both the spatial-temporal density and spatial-temporal voxels of the point cloud. Furthermore, a scoring mechanism for point cloud moving targets is proposed, using time series detection to improve accuracy and efficiency. We used the MMAUD dataset, and our method achieved 4th place in the CVPR 2024 UG2+ Challenge, confirming the effectiveness of our method in practical applications.