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

TL;DR

This paper introduces an unsupervised UAV detection method using spatial-temporal point cloud processing and clustering, effectively distinguishing drones from complex backgrounds in challenging environments.

Contribution

It presents a novel unsupervised pipeline combining spatial-temporal clustering and scoring for UAV detection in point clouds, outperforming traditional methods.

Findings

Achieved 4th place in CVPR 2024 UG2+ Challenge.

Effective background segmentation of point clouds.

Improved detection accuracy with a scoring mechanism.

Abstract

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.