Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unsupervised LiDAR-Based Multi-UAV Detection and Tracking Under Extreme Sparsity

Nivand Khosravi, Rodrigo Ventura, Meysam Basiri

Abstract

Non-repetitive solid-state LiDAR scanning leads to an extremely sparse measurement regime for detecting airborne UAVs: a small quadrotor at 10-25 m typically produces only 1-2 returns per scan, which is far below the point densities assumed by most existing detection approaches and inadequate for robust multi-target data association. We introduce an unsupervised, LiDAR-only pipeline that addresses both detection and tracking without the need for labeled training data. The detector integrates range-adaptive DBSCAN clustering with a three-stage temporal consistency check and is benchmarked on real-world air-to-air flight data under eight different parameter configurations. The best setup attains 0.891 precision, 0.804 recall, and 0.63 m RMSE, and a systematic minPts sweep verifies that most scans contain at most 1-2 target points, directly quantifying the sparsity regime. For multi-target tracking, we compare deterministic Hungarian assignment with joint probabilistic data association (JPDA), each coupled with Interacting Multiple Model filtering, in four simulated scenarios with increasing levels of ambiguity. JPDA cuts identity switches by 64% with negligible impact on MOTA, demonstrating that probabilistic association is advantageous when UAV trajectories approach one another closely. A two-environment evaluation strategy, combining real-world detection with RTK-GPS ground truth and simulation-based tracking with identity-annotated ground truth, overcomes the limitations of GNSS-only evaluation at inter-UAV distances below 2 m.

Unsupervised LiDAR-Based Multi-UAV Detection and Tracking Under Extreme Sparsity

Abstract

Non-repetitive solid-state LiDAR scanning leads to an extremely sparse measurement regime for detecting airborne UAVs: a small quadrotor at 10-25 m typically produces only 1-2 returns per scan, which is far below the point densities assumed by most existing detection approaches and inadequate for robust multi-target data association. We introduce an unsupervised, LiDAR-only pipeline that addresses both detection and tracking without the need for labeled training data. The detector integrates range-adaptive DBSCAN clustering with a three-stage temporal consistency check and is benchmarked on real-world air-to-air flight data under eight different parameter configurations. The best setup attains 0.891 precision, 0.804 recall, and 0.63 m RMSE, and a systematic minPts sweep verifies that most scans contain at most 1-2 target points, directly quantifying the sparsity regime. For multi-target tracking, we compare deterministic Hungarian assignment with joint probabilistic data association (JPDA), each coupled with Interacting Multiple Model filtering, in four simulated scenarios with increasing levels of ambiguity. JPDA cuts identity switches by 64% with negligible impact on MOTA, demonstrating that probabilistic association is advantageous when UAV trajectories approach one another closely. A two-environment evaluation strategy, combining real-world detection with RTK-GPS ground truth and simulation-based tracking with identity-annotated ground truth, overcomes the limitations of GNSS-only evaluation at inter-UAV distances below 2 m.
Paper Structure (30 sections, 11 equations, 3 figures, 3 tables)

This paper contains 30 sections, 11 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. LiDAR-Based Aerial Target Detection
  4. Data Association for Multi-Target Tracking
  5. Methodology
  6. Coordinate Frames and Notation
  7. Unsupervised LiDAR-Based UAV Detection
  8. Preprocessing and Range-Adaptive Clustering
  9. Multi-Layer Validation
  10. Multi-Object Tracking
  11. State and Measurement Model
  12. IMM Filtering
  13. Gating and Data Association
  14. Track Management and Evaluation
  15. Experimental Setup
  16. ...and 15 more sections

Figures (3)

  • Figure 1: Real-world setup: observer UAV with inverted Livox Mid-360 detecting a target quadrotor at 5--25 m with RTK-GPS ground truth.
  • Figure 2: MRS UAV System Gazebo environment for tracking evaluation with millimeter-accurate ground truth and unambiguous identity labels.
  • Figure 3: XY trajectory projection for Sc-IV (Moderate). Ground-truth paths (dashed) and JPDA track estimates (solid) are overlaid for both UAVs. JPDA successfully maintains correct track identities throughout intermittent proximity events, demonstrating its advantage over Hungarian assignment in mixed-ambiguity operational conditions.