Search Results (36)

Reliable and scalable landmine detection technologies are essential for humanitarian mine action (HMA), yet standardized benchmarks for Unmanned Aerial Vehicle (UAV)-based sensing in operationally relevant environments remain limited. This study presents a comprehensive evaluation of 34 multimodal datasets acquired over a standardized seeded test site for landmine and unexploded ordnance detection. Nine sensing modalities, including RGB, thermal, multispectral, hyperspectral, LiDAR, and Synthetic Aperture Radar (SAR), are evaluated using the Anomaly, Identifiable Anomaly, Unique Identifiable Anomaly (AIU) index to establish a unified framework for quantifying detection fidelity. Results indicate that RGB imagery achieves the highest surface detection rate (94.8%), with 45.4% of targets classified as uniquely identifiable, reducing false-positive risk. For sub-surface detection, handheld electromagnetic induction (EMI) and magnetometry exceed 95% detection for ferrous items but fall below 10% for plastic ordnance. Ground-penetrating radar (GPR) is the only modality capable of detecting buried plastic targets (55.6% for cart-based systems), whereas UAV-mounted GPR remains limited (18.2%) at current operational flight heights. Based on the comparative analysis, we discuss the gaps in current detection capabilities, compare false-positive rates across modalities, and perform a cost–benefit analysis fitting contamination scenarios with the most cost-effective detection method. All datasets are publicly released, along with an interactive web-map, to support reproducible benchmarking and cross-modality comparison in UAV-enabled explosive hazard detection. Full article

The detection and classification of scatterable landmines present a significant challenge for humanitarian demining, particularly in resource-constrained regions. This paper evaluates the use of a deep learning-based strategy using RGB imagery and the YOLOv11 algorithm to detect the most commonly deployed PFM-1 landmines, with the overarching goal of applying this approach to the broad category of scatterable landmines. RGB image-based YOLOv11 detection showed strong precision (78–91%) and recall (76–88%) against validation data for several model variants. Additionally, 3D-printed, paint-matched replicas of PFM-1 landmines were used provisionally as part of out-of-sample (OOS) testing to assess the realistic value of this methodology in the field, along with an inert PFM-1 mine. This demonstrated the potential for 3D-printed replicas to be used as part of the training and assessment process due to their low-cost, scalable, and safe approach, highlighting strong precision (74–80%) but weaker recall (14–24%). Additional edge deployment was tested using the model to demonstrate its capability in locating a minefield using trigonometric relationships and kernel density relationships, further supporting this method in non-technical, first-pass landmine sweeps. These results demonstrate that OOS evaluation is critical in humanitarian demining research to ensure that detection systems are truly field-ready and operationally reliable. This study provides a replicable workflow for deep learning tasks related to surface-laid landmines that can be deployed on edge devices for use in non-technical surveys. Full article

Background/Objectives: Accurate measurement of total protein (TP) in cerebrospinal fluid (CSF) is crucial for diagnosing various neurological conditions. This study aims to evaluate the concordance between a routine colorimetric method and a recently introduced turbidimetric method for measuring CSF TP. Methods: We measured 161 CSF samples using both methods, analyzing the whole population and two subgroups: normal (≤500 mg/L) and pathological (>500 mg/L). Agreement was assessed using Lin’s Concordance Correlation Coefficient (CCC), Bland–Altman, and Deming regression, while clinical concordance was determined with Cohen’s Kappa. Results: The concentrations obtained from the two methods did not differ significantly and were well-correlated across the population and subgroups. The CCC for the entire dataset was 0.9881 (substantial agreement), while the Bland–Altman analysis showed a mean bias of 4.467 mg/L. For the “normal” subgroup (n = 97), the CCC was 0.8722 (poor agreement), with a mean bias of 7.668 mg/L. In the “pathological” subgroup (n = 64), the CCC was 0.9858 (substantial agreement) with a mean bias of −3.838 mg/L. Demin regression did not show statistically significant proportional or constant bias in the whole population. However, a stratified analysis revealed a significant negative constant bias in the “normal” subgroup in absence of significant bias in the “pathological” subgroup. Cohen’s kappa was 0.804, indicating substantial agreement. Conclusions: Both methods showed substantial agreement for quantifying CSF TP and clinical classification, supporting their potential interchangeability for diagnostic purposes. Nonetheless, laboratories should note the presence of bias, particularly for samples near the clinical cut-off value. Full article

Anti-tank landmines endanger post-conflict recovery. Detecting camouflaged TM-62 landmines in low-altitude unmanned aerial vehicle (UAV) imagery is challenging because targets occupy few pixels and are low-contrast and often occluded. We introduce a single-class anti-tank dataset and a YOLOv5 pipeline augmented with a SAHI-based small-object stage and Weighted Boxes Fusion. The evaluation combines COCO metrics with an operational operating point (score = 0.25; IoU = 0.50) and stratifies by object size and occlusion. On a held-out test partition representative of UAV acquisition, the baseline YOLOv5 attains mAP@0.50:0.95 = 0.553 and AP@0.50 = 0.851. With tuned SAHI (768 px tiles, 40% overlap) plus fusion, performance rises to mAP@0.50:0.95 = 0.685 and AP@0.50 = 0.935—ΔmAP = +0.132 (+23.9% rel.) and ΔAP@0.50 = +0.084 (+9.9% rel.). At the operating point, precision = 0.94 and recall = 0.89 (F1 = 0.914), implying a 58.4% reduction in missed detections versus a non-optimized SAHI baseline and a +14.3 AP@0.50 gain on the small/occluded subset. Ablations attribute gains to tile size, overlap, and fusion, which boost recall on low-pixel, occluded landmines without inflating false positives. The pipeline sustains real-time UAV throughput and supports actionable triage for humanitarian demining, as well as motivating RGB–thermal fusion and cross-season/-domain adaptation. Full article

Objective: This in vitro study quantitatively compared the time-dependent remineralization potential of three professional agents on artificially induced enamel lesions using Scanning Electron Microscopy (SEM) and energy-dispersive X-ray analysis (EDX). Methods: Sixty extracted sound molars were randomly assigned to three groups (number = 20): G_CPP-ACP, treated with casein phosphopeptide–amorphous calcium phosphate; G_Zn-HA, treated with zinc-hydroxyapatite; and G_F-ACP, treated with fluoridated amorphous calcium phosphate. The crown of each tooth was divided into three areas: one represented the control (CTRL, sound enamel), one underwent demineralization (DEMIN, demineralized enamel), and the third one was at first demineralized and then treated with a remineralizing agent, allowing intra-sample comparison. Artificial lesions were produced by immersion in 0.1 M lactic acid (72 h). Groups were subdivided according to remineralization time (7, 14, 21, and 28 days). Samples underwent daily treatment under a pH-cycling regimen. Surface morphology and Ca/P ratios were evaluated by SEM-EDX, and data were statistically analyzed (p < 0.05). Results: All agents promoted a progressive increase in Ca/P ratio over time, confirming a time-dependent remineralization effect. At day 7, G_Zn-HA showed higher Ca/P values, but from day 14 onward, G_F-ACP produced significantly greater mineral gain than the other groups (p < 0.05). By day 21, G_F-ACP reached Ca/P values approaching CTRL, while G_CPP-ACP and G_Zn-HA remained at lower levels, reaching a plateau respectively at 21 and 14 days. SEM observations supported these findings: G_CPP-ACP and G_Zn-HA showed partial surface recovery, whereas G_F-ACP exhibited a compact, homogeneous enamel-like structure at 28 days. Conclusions: All tested agents demonstrated time-dependent remineralization, enhanced with prolonged exposure, suggesting that the time of application represents a key factor for clinical success. Full article

This paper presents a methodological framework for selectively optimizing computer vision models for safety-critical applications. Through systematic processes of hyperparameter tuning alongside multitask learning, we attempt to create a highly interpretable system to better assess the dangers of models intended for safety operations and intentionally select their trade-offs. Using thermographic images of a specific imitation explosive, we create a case study for the viability of humanitarian demining operations. We hope to demonstrate how this approach provides a developmental framework for creating humanitarian AI systems that optimize safety verification in real-world scenarios. By employing a comprehensive grid search across 64 model configurations to evaluate how loss function weights impact detection reliability, with particular focus on minimizing false negative rates due to their operational impact. The optimized configuration achieves a 37.5% reduction in false negatives while improving precision by 2.8%, resulting in 90% detection accuracy with 92% precision. However, to expand the generalizability of this model, we hope to call institutions to openly share their data to increase the breadth of imitation landmines and terrain data to train models from. Full article

Swarm Robotics (SR) is a relatively new field, inspired by the collective intelligence of social insects. It involves using local rules to control and coordinate large groups (swarms) of relatively simple physical robots. Important tasks that robot swarms can handle include demining, search, rescue, and cleaning up toxic spills. Over the past decade, the research effort in the field of Swarm Robotics has intensified significantly in terms of hardware, software, and systems integrated developments, yet significant challenges remain, particularly regarding standardization, scalability, and cost-effective deployment. To contextualize the state of Swarm Robotics technologies, this paper provides a systematic literature review (SLR) of Swarm Robotic technologies published from 2014 to 2024, with an emphasis on how hardware and software subsystems have co-evolved. This work provides an overview of 40 studies in peer-reviewed journals along with a well-defined and replicable systematic review protocol. The protocol describes criteria for including and excluding studies and outlines a data extraction approach. We explored trends in sensor hardware, actuation methods, communication devices, and energy systems, as well as an examination of software platforms to produce swarm behavior, covering meta-heuristic algorithms and generic middleware platforms such as ROS. Our results demonstrate how dependent hardware and software are to achieve Swarm Intelligence, the lack of uniform standards for their design, and the pragmatic limits which hinder scalability and deployment. We conclude by noting ongoing challenges and proposing future directions for developing interoperable, energy-efficient Swarm Robotics (SR) systems incorporating machine learning (ML). Full article

This paper presents a comparative analysis of ten state-of-the-art robotic de-mining systems, grouped into (i) sensor-centric platforms for high-precision detection and (ii) rapid mechanical-contact vehicles for clearance. Building on these findings, we propose a lightweight tracked platform (~1.9 T) equipped with a four-channel sensing suite-RGB/IR camera, 32-layer LiDAR, pulsed-induction metal detector, and 2.45 GHz microwave thermography—integrated in an adaptive Bayesian “detect → confirm → neutralize” loop. The modular end-effector permits either pinpoint mechanical intervention or deployment of a linear charge. Modelling indicates an expected detection sensitivity ≥ 95% with a false-positive rate ≤ 5% in humanitarian demining mode and a clearance throughput above 1.5 ha·h⁻¹ in breaching mode. Ongoing work includes CFD analysis of the thermal front, fabrication of a prototype, and performance testing in accordance with IMAS 10.20. Full article

Existing frameworks for classifying the fidelity for object detection tasks do not consider false positive likelihood and object uniqueness. Inspired by the Detection, Recognition, Identification (DRI) framework proposed by Johnson 1958, we propose a new modified framework that defines three categories as visible anomaly, identifiable anomaly, and unique identifiable anomaly (AIU) as determined by human interpretation of imagery or geophysical data. These categories are designed to better capture false positive rates and emphasize the importance of identifying unique versus non-unique targets compared to the DRI Index. We then analyze visual, thermal, and multispectral UAV imagery collected over a seeded minefield and apply the AIU Index for the landmine detection use-case. We find that RGB imagery provided the most value per pixel, achieving a 100% identifiable anomaly rate at 125 pixels on target, and the highest unique target classification compared to thermal and multispectral imaging for the detection and identification of surface landmines and UXO. We also investigate how the AIU Index can be applied to machine learning for the selection of training data and informing the required action to take after object detection bounding boxes are predicted. Overall, the anomaly, identifiable anomaly, and unique identifiable anomaly index prescribes essential context for false-positive-sensitive or resolution-poor object detection tasks with applications in modality comparison, machine learning, and remote sensing data acquisition. Full article

Air-coupled ground penetrating radar (GPR) systems are widely used for subsurface imaging in demining, geological surveys, and infrastructure assessment applications. However, strong surface reflections can introduce interference, leading to receiver saturation and reducing the clarity of subsurface features. This paper presents a novel surface reflection suppression algorithm for stepped-frequency continuous wave (SFCW) GPR systems. The proposed method estimates the surface reflection component and applies phase-compensated subtraction at the receiver site, effectively suppressing background reflections. A modular SFCW radar system was developed and tested in a laboratory setup simulating a low-altitude airborne deployment to validate the proposed approach. B-scan and time-domain analyses demonstrate significant suppression of surface reflections, improving the visibility of subsurface targets. Unlike previous static echo cancellation methods, the proposed method performs on-board pre-downconversion removal of surface clutter that compensates for varying ground distance, which is a unique contribution of this work. Full article

Commonly found landmines, such as the TM-62M, MON-100, and PDM-1, in the recent Russia–Ukraine war confirm the continued use of metals in munitions. Traditional demining techniques, primarily relying on handheld metal detectors and Ground Penetrating Radar (GPR) systems, remain state of the art for subsurface detection. However, manual demining with handheld metal detectors can be slow and pose significant risks to operators. Drone-based metal detection techniques offer promising solutions for rapid and effective landmine detection, but their reliability and accuracy remain a concern, as even a single missed detection can be life-threatening. This study evaluates the potential of an airborne metal detection system as an alternative to traditional handheld detectors. A comparative analysis of three distinct metal detectors for landmine detection is presented: the EM61Lite, a sensitive airborne metal detection system (tested in a pseudo-drone-based scenario); the CTX 3030, a traditional handheld all-metal detector; and the ML 3S, a traditional handheld ferrous-only detector. The comparison focuses on the number of metallic targets each detector identifies in a controlled test field containing inert landmines and UXOs. Our findings highlight the strengths and limitations of airborne metal detection systems like the EM61Lite and emphasize the need for advanced processing techniques to facilitate their practical deployment. We demonstrate how our experimental normalization technique effectively identifies additional anomalies in airborne metal detector data, providing insights for improved detection methodologies. Full article

The operational practice of the design of the Bozena 5 demining machine has shown that its belts are the critical component that fundamentally affects the functionality of the entire machine. This article is a practical continuation and extension of the previous research results from the point of view of materials (research of the uniaxial fatigue life in bending and torsion), calculation (creation of the necessary mathematical, analytical and numerical models for the research) and construction (i.e., patented design of the belt tensioning of this machine). All these actions are aimed at a single objective—to achieve a condition that guarantees a sufficient service life without malfunctions, since repairing these machines in the field is often impossible. Therefore, this study examined the fatigue life of welded joints (uniaxial bending and torsion) of S960 QL and S500MC steels welded by MAG technology. Subsequently, the data were compared with previous results (electron and laser welds) and the influence of each type of weld on the fatigue life relative to the base material was discussed. It was found that conventional MAG technology had a more significant negative impact on the fatigue life of the base material than non-conventional technologies. This trend was particularly true for the bending stress. At the same time, the bending stress was identified by the FEM analysis as the dominant load on the belt. The maximum stress in the belt link under the considered boundary conditions was approximately 240 MPa (in bending). This stress corresponded to the continuous fatigue life (more than 10⁷ cycles) for both base materials tested (S960QL, S500MC). In the whole studied spectrum of controlled deformation amplitudes (Manson–Coffin), the life of MAG welds was lower in comparison with the base material and with welds made by unconventional technologies. All the activities carried out so far (research on microstructure, hardness, strength, residual stresses, tribological properties and fatigue life) have shown that the original belt design (S500MC) using MAG technology has significant deficiencies in the state of optimal life. It is expected that the proposed material change (use of S960QL instead of S500MC) and work with advanced technologies will bring this state significantly closer. Full article

This paper introduces an intelligent model that combines military expertise with the latest advancements in machine learning (ML) and Geographic Information Systems (GIS) to support humanitarian demining decision-making processes, by predicting mined areas and classifying them by mine type, difficulty and priority of clearance. The model is based on direct input and validation from field decision-makers for their practical applicability and effectiveness, and accurate historical demining data extracted from military databases. With a survey polling the inputs of demining experts, 95% of the responses came with an affirmation of the potential of the model to reduce threats and increase operational efficiency. It includes military-specific factors that factor in the proximity to strategic locations as well as environmental variables like vegetation cover and terrain resolution. With Gradient Boosting algorithms such as XGBoost and LightGBM, the accuracy rate is almost 97%. Such precision levels further enhance threat assessment, better allocation of resources, and around a 30% reduction in the cost and time of conducting demining operations, signifying a strong synergy of human expertise with algorithmic precision for maximal safety and effectiveness in demining. Full article

An important consideration for UAV-based (unmanned aerial vehicle) object detection in the natural environment is vegetation height and foliar cover, which can visually obscure the items a machine learning model is trained to detect. Hence, the accuracy of aerial detection of objects such as surface landmines and UXO (unexploded ordnance) is highly dependent on the height and density of vegetation in a given area. In this study, we develop a model that estimates the detection accuracy (recall) of a YOLOv8 object’s detection implementation as a function of occlusion due to vegetation coverage. To solve this function, we developed an algorithm to extract vegetation height and coverage of the UAV imagery from a digital surface model generated using structure-from-motion (SfM) photogrammetry. We find the relationship between recall and percent occlusion is well modeled by a sigmoid function using the PFM-1 landmine test case. Applying the sigmoid recall-occlusion relationship in conjunction with our vegetation cover algorithm to solve for percent occlusion, we mapped the uncertainty in detection rate due to vegetation in UAV-based SfM orthomosaics in eight different minefield environments. This methodology and model have significant implications for determining the optimal location and time of year for UAV-based object detection tasks and quantifying the uncertainty of deep learning object detection models in the natural environment. Full article

As landmines and other unexploded ordnances (UXOs) present a great risk to civilians and infrastructure, humanitarian demining is an essential component of any post-conflict reconstruction. This paper introduces the Minefield Observatory, a novel web-based datastore service that semantically integrates diverse data in humanitarian demining to comprehensively and formally describe suspected minefields. Because of the high heterogeneity and isolation of the available minefield datasets, extracting relevant information to determine the optimal course of demining efforts is time-consuming, labor-intensive and requires highly specialized knowledge. Data consolidation and artificial intelligence techniques are used to convert unstructured data sources and store them in an ontology-based knowledge database that can be efficiently accessed through a Semantic Web application serving as the Minefield Observatory user interface. The MINEONT+ ontology was developed to integrate diverse mine scene information obtained through non-technical surveys and remote sensing, such as aerial and hyperspectral satellite imagery, indicators of mine presence and absence, contextual data, terrain analysis information, and battlefield reports. The Minefield Observatory uses the Microdata API to embed this dataset into dynamic HTML5 content, allowing seamless usage in a user-centric web tool. A use-case example was provided demonstrating the viability of the proposed approach. Full article