面向无人机高光谱PFM-1地雷探测的人机协同特征自举方法

摘要

高光谱成像（HSI）有助於材料辨識，但實際地雷篩查的效率更取決於在發現目標之前需檢查多少虛警。本文研究基於無人機（UAV）可見光與近紅外（VNIR）高光譜影像，運用光譜角映射器（SAM）、匹配濾波器（MF）、自適應相干估計器（ACE）及約束能量最小化（CEM）進行PFM-1地雷偵測。我們比較了三種光譜特徵：地面實測的SVC光譜、完全已知的場景內核心像素光譜，以及模擬人機迴圈的自助法（bootstrap）特徵。除了接收操作特徵曲線下面積與平均精度外，我們亦報告目標發現曲線及空間候選點審查次數。在完整審查的自助法中，經所有七個目標區域驗證後可達到完全已知場景內光譜特徵的表現，但所需的檢查工作量差異顯著：ACE僅需兩輪及九次候選點審查即可確認所有區域，而SAM變體則需數千次候選點審查才能鎖定最終目標位置。相關程式碼已開放於 https://github.com/SagarLekhak/IEEE_WHISPERS_2026_UAV_HSI_PFM1。

English

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.