{"paper":{"title":"Benchmarking Deep Learning and Statistical Target Detection Methods for PFM-1 Landmine Detection in UAV Hyperspectral Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A lightweight spectral neural network achieves the highest average precision for detecting sparse PFM-1 landmine pixels in UAV hyperspectral imagery, outperforming classical detectors under precision-focused metrics.","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Emmett J. Ientilucci, Prasanna Reddy Pulakurthi, Ramesh Bhatta, Sagar Lekhak","submitted_at":"2026-02-11T02:25:32Z","abstract_excerpt":"In recent years, unmanned aerial vehicles (UAVs) equipped with imaging sensors and automated processing algorithms have emerged as a promising tool to accelerate large-area surveys while reducing risk to human operators. Although hyperspectral imaging (HSI) enables material discrimination using spectral signatures, standardized benchmarks for UAV-based landmine detection remain scarce. In this work, we present a systematic benchmark of four classical statistical detection algorithms, including Spectral Angle Mapper (SAM), Matched Filter (MF), Adaptive Cosine Estimator (ACE), and Constrained En"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"While all methods achieve high ROC-AUC on an independent test set, the ACE method observes the highest AUC of 0.989. However, because target pixels are extremely sparse relative to background, ROC-AUC alone can be misleading; under precision-focused evaluation (PR and AP), the Spectral-NN outperforms classical detectors, achieving the highest AP.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That performance measured on inert PFM-1 targets in the released VNIR dataset will generalize to live mines, different soils, lighting conditions, or other landmine types without retraining or additional calibration.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A proposed lightweight Spectral Neural Network with Parametric Mish activations achieves the highest average precision for sparse PFM-1 landmine detection in UAV hyperspectral imagery, outperforming ACE, SAM, MF, and CEM on precision-recall metrics despite lower ROC-AUC.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A lightweight spectral neural network achieves the highest average precision for detecting sparse PFM-1 landmine pixels in UAV hyperspectral imagery, outperforming classical detectors under precision-focused metrics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e0e1a2e641ec45d74fa8506d5427145690ddb86b27a37d6dcb9f4ca19afb9936"},"source":{"id":"2602.10434","kind":"arxiv","version":3},"verdict":{"id":"cf6da1c0-7270-4811-940f-ce36b9b8500c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T04:02:18.158867Z","strongest_claim":"While all methods achieve high ROC-AUC on an independent test set, the ACE method observes the highest AUC of 0.989. However, because target pixels are extremely sparse relative to background, ROC-AUC alone can be misleading; under precision-focused evaluation (PR and AP), the Spectral-NN outperforms classical detectors, achieving the highest AP.","one_line_summary":"A proposed lightweight Spectral Neural Network with Parametric Mish activations achieves the highest average precision for sparse PFM-1 landmine detection in UAV hyperspectral imagery, outperforming ACE, SAM, MF, and CEM on precision-recall metrics despite lower ROC-AUC.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That performance measured on inert PFM-1 targets in the released VNIR dataset will generalize to live mines, different soils, lighting conditions, or other landmine types without retraining or additional calibration.","pith_extraction_headline":"A lightweight spectral neural network achieves the highest average precision for detecting sparse PFM-1 landmine pixels in UAV hyperspectral imagery, outperforming classical detectors under precision-focused metrics."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.10434/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}