Search Results (52)

Landmines remain a significant hazard in contemporary warfare and post-conflict areas, jeopardizing the safety of both civilians and military personnel. This work suggests “Defence Pal,” a cost-effective and portable robotic prototype for landmine detection and environmental monitoring. Its primary objective is to minimize human risk while improving detection speed and accuracy. The system consists of a wireless-controlled vehicle equipped with a metal detector, gas sensors, and obstacle avoidance features, enabling real-time terrain surveillance while ensuring operator safety. Built with components including a Flysky FS-i6 transmitter and receiver, the prototype was tested under hazardous conditions. It demonstrated reliable detection of buried metallic objects and dangerous gases such as methane and carbon dioxide. The autonomous response system halts the robot and activates visual and auditory alarms upon detecting threats. Our experiments achieved average detection accuracies of 83% for metallic objects and 87% for hazardous gases, validating their performance. These results highlight the practicality and effectiveness of Defence Pal compared to conventional manual detection methods. The results confirm that Defence Pal is a practical, scalable, and cost-effective alternative to traditional manual detection methods for improving landmine identification and environmental hazard monitoring. Therefore, the novelty of this work lies in a low-cost dual-sensing prototype that enables simultaneous detection of gas and metal, providing a practical alternative to conventional single-target, high-cost systems. 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

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

This study proposes a simple deep learning-based framework for image-level anti-personnel landmine detection in long-wave infrared imagery. To address challenges posed by the limited size of the available dataset and the small spatial size of anti-personnel landmines within images, we integrate two key techniques: transfer learning using pre-trained vision foundation models, and attention-based multiple instance learning to derive discriminative image features. We evaluate five pre-trained models, including ResNet, ConvNeXt, ViT, OpenCLIP, and InfMAE, in combination with attention-based multiple instance learning. Furthermore, to mitigate the reliance of trained models on irrelevant features such as artificial or natural structures in the background, we introduce an inpainting-based image augmentation method. Experimental results, conducted on a publicly available “legbreaker” anti-personnel landmine infrared dataset, demonstrate that the proposed framework achieves high precision and recall, validating its effectiveness for landmine detection in infrared imagery. Additional experiments are also performed on an aerial image dataset designed for detecting small-sized ship targets to further validate the effectiveness of the proposed approach. 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

Ground-Penetrating Radar (GPR) systems with ultra-wideband (UWB) antennas introduce the benefits of both high and low frequencies. Higher frequencies offer finer spatial resolution, enabling the detection of small-scale features and details, while lower frequencies improve depth penetration by minimising signal attenuation, allowing the system to explore deeper subsurface layers. This combination optimises the performance of GPR systems by balancing the need for detailed imaging with the requirement for deeper penetration. This work presents the design of a wideband inverted U-shaped patch antenna with a wide rectangular slot centred at a frequency of 1.5 GHz. The antenna is fed through a microstrip feed line and employs a partial ground plane. Through simulation, the antenna is optimised by varying the patch dimensions and slot size. Further modifications to the partial ground plane improve the UWB and gain characteristics of the antenna. The optimised antenna is fabricated using a double-sided copper-clad FR4 substrate with a thickness of 1.6 mm and characterised using a Vector Network Analyser (VNA), with final dimensions of 200 mm × 300 mm. The experimental results demonstrate a return loss below −10 dB across the operational band from 1.068 GHz to 4 GHz and a maximum gain of 7.29 dB at 4 GHz. In addition to other bands, the antenna exhibits a return loss consistently below −20 dB in the frequency range of 1.367 GHz to 1.675 GHz. These results confirm the antenna’s UWB performance and its suitability for GPR applications in utility mapping, landmine and artefact detection, and identifying architectural defects. Full article

We have developed a miniaturized magnetic sensor based on diamond nitrogen-vacancy (NV) centers, combined with a two-dimensional scanning setup that enables imaging magnetic samples with millimeter-scale resolution. Using the lock-in detection scheme, we tracked changes in the NV’s spin resonances induced by the magnetic field from target samples. As a proof-of-principle demonstration of magnetic imaging, we used a toy diorama with hidden magnets to simulate scenarios such as the remote detection of landmines on a battlefield or locating concealed objects at a construction site, focusing on image analysis rather than addressing sensitivity for practical applications. The obtained magnetic images reveal that they can be influenced and distorted by the choice of frequency point used in the lock-in detection, as well as the magnitude of the sample’s magnetic field. Through magnetic simulations, we found good agreement between the measured and simulated images. Additionally, we propose a method based on NV vector magnetometry to compensate for the non-zero tilt angles of a target, enabling the accurate localization of its position. This work introduces a novel imaging method using a scanning miniaturized magnetometer to detect hidden magnetic objects, with potential applications in military and industrial sectors. 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

This study presents an unmanned aerial vehicle (UAV)-borne vector magnetometer (MAG) system and proposes a new data-processing technique for modeling the residual magnetic anomalies of three types of landmines: the metallic antitank M15, the metallic antipersonnel M16, and the minimum-metal antitank M19. The burial depth and magnetic moment of these landmines were estimated using the measured and simulated residual magnetic anomalies based on the proposed UAV-borne vector MAG model. Initial in-flight validation showed a strong correlation between the residual magnetic anomaly maps obtained from measurements and simulations. To verify the detection capability in real-world conditions, the UAV-borne MAG system was tested at the Korean Combat Training Center. Both simulations and experiments demonstrated the effectiveness of the proposed data-processing method and UAV-borne MAG model in accurately modeling the residual magnetic anomalies of landmines with metallic components. This approach will facilitate the automated detection of M15, M16, and M19 landmines with high detection rates and enable accurate classification. Full article

Non-invasive concealed object detection, identification, and discrimination have been of interest to the research community for decades due to the needs to preserve infrastructures and artifacts, guarantee safe conditions for the detection and location of landmines, etc. A modern approach is based on the use of an unmanned aerial vehicle equipped with ground-penetrating radar, which has the advantage of not requiring direct contact with the ground. Moreover, high-resolution underground images are obtained by coherently combining measurements by using a synthetic aperture radar algorithm. Due to the complexity of the real scenario, numerical analyses have always been welcomed to provide almost real-time information to make the best use of the potential of such kinds of techniques. This paper proposes an analysis of the scattering from a zero-thickness perfectly electrically conducting disk buried in a lossy half-space surrounded by air and illuminated by a field generated by a Hertzian dipole located in the air. It is carried out by means of a generalized form of the analytically regularizing Helmholtz–Galerkin technique, introduced and successfully applied by the authors to analyze the plane-wave scattering from a disk and a holed plane in a homogeneous medium. As clearly shown in the numerical results, the proposed method is very effective and drastically outperforms the commercial software CST Microwave Studio 2023. 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

Various organisms, such as dogs and moths, can locate their prey and mates by sensing their smells. Following this manner, if an engineering device with the capability to detect a smell or gas source is realized, it can have a wide range of potential applications, such as searching for landmines, locating gas leaks, and rapid detection of fire. A previous study on the estimation of smell and gas-flow direction successfully detected the smell/gas-source direction in low-wind-velocity environments using a semiconductor gas sensor array. However, some problems are generally associated with the use of semiconductor gas sensors due to the use of heaters. This study aimed to detect the location of a smell/gas source using an integrated CMOS smell sensor array, which operates at room temperature without a heater. The experiment showed that under ideal conditions, the order of gas responses and concentration gradient of the gas enabled the estimation of the direction of the smell/gas-source location on one side of the sensor. Full article

A tremendous number of landmines has been buried during the last decade. In recent years, various autonomous platforms equipped with ground-penetrating radars (GPRs) have been proposed for the detection of landmines. These systems have already demonstrated their performance in controlled environments with known ground truth. However, it has been observed that the influence of surface conditions in the form of vegetation and roughness as well as soil moisture content significantly reduce the detection probability. The influence of these individual factors on a ground-offset GPR is presented and discussed in this work. Each of these factors significantly degrades the backscattered signal. With increasing soil moisture, the signal gets attenuated more strongly; however, the signature is maintained in the phase of the C-Scans. An increase in surface roughness deteriorates the target pattern making it difficult to detect buried objects unambiguously. Vegetation, especially with irregular leaf structures, can appear as a ghost target and scatter the electromagnetic waves. In most cases, the target is easier to detect in the phase of the B- or C-Scan. Full article

This paper presents a pioneering study in the application of real-time surface landmine detection using a combination of robotics and deep learning. We introduce a novel system integrated within a demining robot, capable of detecting landmines in real time with high recall. Utilizing YOLOv8 models, we leverage both optical imaging and artificial intelligence to identify two common types of surface landmines: PFM-1 (butterfly) and PMA-2 (starfish with tripwire). Our system runs at 2 FPS on a mobile device missing at most 1.6% of targets. It demonstrates significant advancements in operational speed and autonomy, surpassing conventional methods while being compatible with other approaches like UAV. In addition to the proposed system, we release two datasets with remarkable differences in landmine and background colors, built to train and test the model performances. Full article

Supervised machine learning algorithms usually require huge labeled data sets to produce sufficiently good results. For many applications, these data sets are still not available today, and the reasons for this can be manifold. As a solution, the missing training data can be generated by fast simulators. This procedure is well studied and allows filling possible gaps in the training data, which can further improve the results of a machine learning model. For this reason, this article deals with the development of a two-dimensional electromagnetic field simulator for modeling the response of a radar sensor in an imaging system based on the synthetic aperture radar principle. The creation of completely random scenes is essential to achieve data sets with large variance. Therefore, special emphasis is placed on the development of methods that allow creating random objects, which can then be assembled into an entire scene. In the context of this contribution, we focus on humanitarian demining with regard to improvised explosive devices using a ground-penetrating radar system. This is an area where the use of trained classifiers is of great importance, but in practice, there are little to no labeled datasets for the training process. The simulation results show good agreement with the measurement results obtained in a previous contribution, demonstrating the possibility of enhancing sparse training data sets with synthetic data. Full article