Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection

2026-07-28

AI Summary

This study addresses the high false alarm rate in PFM-1 landmine detection using drone-based hyperspectral imaging, which imposes a heavy burden on manual verification. To mitigate this, the authors propose a human-in-the-loop feature bootstrapping mechanism that iteratively validates candidate regions through human–machine collaboration, thereby guiding spectral feature extraction without requiring prior target spectra. The approach achieves detection performance approaching that of full-information scenarios. Experimental evaluation integrates algorithms such as SAM, MF, ACE, and CEM, with effectiveness assessed via target discovery curves and spatial candidate review counts. Results demonstrate that ACE, combined with the proposed strategy, identifies all seven targets with only two rounds totaling nine manual reviews—dramatically fewer than the thousands required by SAM variants—thereby substantially reducing human intervention and confirming the method’s superiority in enhancing both detection efficiency and accuracy.

Abstract

Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspected before targets are found. This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM). We compare a ground-measured SVC signature, a fully informed in-scene core-pixel signature, and a simulated human-in-the-loop signature bootstrap. Besides receiver operating characteristic area under the curve and average precision, we report target-discovery curves and spatial candidate-review counts. Full-review bootstrapping reaches the fully informed in-scene signature case after all seven target regions are verified, but the required inspection effort varies strongly: ACE confirms all regions in two rounds and nine candidate inspections, whereas the SAM variants need thousands of candidate reviews for their final target locations. Code is available at https://github.com/SagarLekhak/IEEE_WHISPERS_2026_UAV_HSI_PFM1.

Problem

• hyperspectral imaging
• PFM-1 mine detection
• false alarms
• target discovery
• human-in-the-loop

Innovation

• Human-in-the-Loop
• Signature Bootstrapping
• Hyperspectral Mine Detection
• Target Discovery Curve
• UAV HSI