Landmine Detection Problem Research Articles

Review of strategies to overcome the lack of data in landmine detection

This article reviews strategies to address the lack of data for training landmine recognition models. Since the outbreak of the war in Ukraine in 2014, the area of contaminated territories has gradually increased. However, after Russia's full-scale invasion on February 24, 2022, the problem of landmines in Ukraine has become much more severe, as the area of mined territories in the country has increased to 30%. It takes many years and efforts to clear such a large area. To overcome a problem of this scale, it is necessary to look for new methods of landmine detection that will allow demining to be conducted 24/7. Machine learning is one of the options for solving the problem of landmine detection. To train landmine recognition models, a large amount of data is required. However, the lack of diverse and large datasets creates significant obstacles to the development of effective detection systems. The safety concerns associated with conducting experiments with real landmines further exacerbate the problem. This article discusses three possible strategies to overcome the above problem: augmentation methods, the use of 3D printing technology, and crowdsourced data collection. Augmentation methods offer data generation to improve model performance. 3D printing allows for the creation of realistic replicas of landmines for safe experimentation. Crowdsourcing uses collective efforts to collect real-world data from conflict zones. Through the joint efforts of researchers, technology developers and humanitarian organizations, these approaches offer promising ways to improve landmine detection capabilities. The use of these approaches can address the data gap and ensure safe data collection.

A novel landmine detection system based on within and between subclasses dispersion information

ABSTRACT : Millions of anti-personnel landmines have been left in the ground during war conflicts in many countries, which causes many security, humanitarian and economic problems. It is therefore necessary to develop an automatic and efficient technique for landmines detection and localization, in order to clear the existing minefields. Ground-penetrating radar (GPR) is a geophysical method that is able to detect any buried object in the soil, but it suffers from high false alarm rate. Several landmine detection and localization systems have been developed, using GPR data and based on competitive classification methods, such as the One-class Support Vector Machine (OSVM), which handles the common problem of unbalanced data, in a proper manner. Nevertheless, in the landmine detection problem, we assume that the target class is composed of several subclasses related to metallic contents, which are not considered by related classification methods, including OSVM. For this reason, in this paper, we propose a subclass landmine detection and localization system based on a novel variation of the OSVM that takes into account the existence of subclasses in the landmine target class in order to jointly minimize the within and between subclass dispersion and to estimate the optimal decision function. Our proposed landmine detection and localization method has been evaluated and compared to other methods based on relevant one-class classifiers, on several real-world datasets extracted from the well-known MACADAM database. Experimental results have shown clearly that our proposed method is competitive with the existing relevant one-class classifiers, in landmine detection.

Combination of physics-based and image-based features for landmine identification in ground penetrating radar data

Ground penetrating radar (GPR) is a powerful technology for detection and identification of buried explosives, especially with little or no metal content. However, subsurface clutter and soil distortions increase false alarm rates of current GPR-based landmine detection and identification methods. Most existing algorithms use shape-based, image-based, and physics-based techniques. Analysis of these techniques indicates that each type of algorithm has a different perspective to solve the landmine detection and identification problem. Therefore, one type of method has stronger and weaker points with respect to the other types of algorithms. To reduce false alarm rates of the current GPR-based landmine detection and identification methods, we propose a combined feature utilizing both physics-based and image-based techniques. Combined features are classified with a support vector machine classifier. The proposed algorithm is tested on a simulated data set that contained more than 500 innocuous object signatures and 400 landmine signatures, over half of which are completely nonmetal. The results presented indicate that the proposed method has significant performance benefits for landmine detection and identification in GPR data.

Nonlinear tuning curve vibration using a column of non-wetted or wetted glass beads vibrating over a clamped elastic plate: Case for air-borne sound excitation

A soil plate oscillator (SPO) apparatus consists of two circular flanges sandwiching and clamping a thin circular elastic plate. The apparatus can model certain aspects of the nonlinear acoustic landmine detection problem which involves the interaction of granular material with an elastic plate in flexural vibration. Uniform spherical glass beads—representing a nonlinear mesoscopic elastic material—are supported at the bottom by the acrylic plate (4.5 inch diam, 1/8 inch thick) and stiff cylindrical sidewalls of the upper flange. Two 3 in. diam loud speakers placed above the bead column are driven with a swept sinusoidal signal applied to a constant current amplifier to generate air-borne sound excitation from 50 to 1250 Hz. A small accelerometer fastened to the underside of the plate at the center measures the response. Separate tuning curve experiments are performed using a fixed column of 350 grams using 2,3,…,10 mm diameter soda-lime glass beads—wetted or non-wetted (mineral-oil). With dry beads, backbone curves (peak acceleration vs. corresponding resonant frequency) exhibit a linear region with comparable slopes, while detailed back-bone curvature vs. bead diameter reveals more structure. Wet beads exhibit less non-linear tuning curve behavior.

Classroom demonstration of nonlinear tuning curve vibration and two-tone tests using a column of glass beads vibrating over a clamped elastic plate

A soil plate oscillator (SPO) apparatus consists of two circular flanges sandwiching and clamping a thin circular elastic plate. The apparatus can model the acoustic landmine detection problem. Here, uniform spherical glass beads—representing a nonlinear mesoscopic elastic material—are supported at the bottom by the acrylic plate (4.5 inch diam, 1/8 inch thick) and stiff cylindrical sidewalls of the upper flange. A magnetic disk centered and fastened below the plate is driven by an AC coil placed below the magnet. Nonlinear tuning curves of the magnet’s acceleration are measured by driving the coil with a swept sinusoidal signal applied to a constant current amplifier. Ten (separate) tuning curve experiments are performed using a fixed column of 350 grams of beads using 1,2,3,…,10 mm diameter beads. The backbone curves (peak acceleration vs. corresponding resonant frequency) exhibit a linear region with comparable slopes, while the detailed curvature vs. bead diameter reveals more structure. A bilinear hysteresis model is useful for characterizing results. In two-tone tests, air-borne sound from two 3 inch diameter speakers drives the bead column surface at closely spaced frequencies near the fundamental resonance. Nonlinearly generated combination frequency tones are compared for each of the ten bead diameter experiments.A soil plate oscillator (SPO) apparatus consists of two circular flanges sandwiching and clamping a thin circular elastic plate. The apparatus can model the acoustic landmine detection problem. Here, uniform spherical glass beads—representing a nonlinear mesoscopic elastic material—are supported at the bottom by the acrylic plate (4.5 inch diam, 1/8 inch thick) and stiff cylindrical sidewalls of the upper flange. A magnetic disk centered and fastened below the plate is driven by an AC coil placed below the magnet. Nonlinear tuning curves of the magnet’s acceleration are measured by driving the coil with a swept sinusoidal signal applied to a constant current amplifier. Ten (separate) tuning curve experiments are performed using a fixed column of 350 grams of beads using 1,2,3,…,10 mm diameter beads. The backbone curves (peak acceleration vs. corresponding resonant frequency) exhibit a linear region with comparable slopes, while the detailed curvature vs. bead diameter reveals more structure. A bilinear hy...

Statistical moments calculated via integral images in application to landmine detection from Ground Penetrating Radar 3D scans

Under study is an application of Ground Penetrating Radar (GPR) to landmine detection problem. We focus on the detection of antitank mines carried out in the 3D GPR images, so-called C-scans, by means of a machine learning approach. In that approach, we particularly pursue a technique for fast extraction of image features based on an initial calculation of multiple integral images. This allows later to calculate each feature in constant time, regardless of the scanning window position and size. The features we study are statistical moments formulated in their 3D variant. We present a comparison of detection results for different sizes and parameterizations of feature sets. All results are obtained from a prototype GPR system of our original construction in terms of both hardware and software.

Multiple-Instance Hidden Markov Models With Applications to Landmine Detection

A novel multiple-instance hidden Markov model (MI-HMM) is introduced for classification of time-series data, and its training is developed using stochastic expectation maximization. The MI-HMM provides a single statistical form to learn the parameters of an HMM in a multiple-instance learning framework without introducing any additional parameters. The efficacy of the model is shown both on synthetic data and on a real landmine data set. Experiments on both the synthetic data and the landmine data set show that an MI-HMM can 1) achieve statistically significant performance gains when compared with the best existing HMM for the landmine detection problem, 2) eliminate the ad hoc approaches in training set selection, and 3) introduce a principled way to work with ambiguous time-series data.

The COMRADE System for Multirobot Autonomous Landmine Detection in Postconflict Regions

We consider the problem of autonomous landmine detection using a team of mobile robots. Previous research on robotic landmine detection mostly employs a single robot equipped with a landmine detection sensor to detect landmines. We envisage that the quality of landmine detection can be significantly improved if multiple robots are coordinated to detect landmines in a cooperative manner by incrementally fusing the landmine-related sensor information they collect and then use that information to visit locations of potential landmines. Towards this objective, we describe a multirobot system called COMRADES to address different aspects of the autonomous landmine detection problem including distributed area coverage to detect and locate landmines, information aggregation to fuse the sensor information obtained by different robots, and multirobot task allocation (MRTA) to enable different robots to determine a suitable sequence to visit locations of potential landmines while reducing the time required and battery expended. We have used commercially available all-terrain robots called Coroware Explorer that are customized with a metal detector to detect metallic objects including landmines, as well as indoor Corobot robots, both in simulation and in physical experiments, to test the different techniques in COMRADES.

LANDMINE DETECTION TECHNOLOGIES TO FACE THE DEMINING PROBLEM IN ANTIOQUIA

This paper presents a review of existing landmine detection techniques. The review is made with an analysis of the strengths and weaknesses of each technique in relation to the landmine detection problem in Antioquia, which ranks first in Colombia by the number of victims from landmines. According to the uniqueness of landmines and terrains in Antioquia, this paper suggests some research topics that may help in the demining task for this affected department.

Multi-stream continuous hidden Markov models with application to landmine detection

AbstractWe propose a multi-stream continuous hidden Markov model (MSCHMM) framework that can learn from multiple modalities. We assume that the feature space is partitioned into subspaces generated by different sources of information. In order to fuse the different modalities, the proposed MSCHMM introduces stream relevance weights. First, we modify the probability density function (pdf) that characterizes the standard continuous HMM to include state and component dependent stream relevance weights. The resulting pdf approximate is a linear combination of pdfs characterizing multiple modalities. Second, we formulate the CHMM objective function to allow for the simultaneous optimization of all model parameters including the relevance weights. Third, we generalize the maximum likelihood based Baum-Welch algorithm and the minimum classification error/gradient probabilistic descent (MCE/GPD) learning algorithms to include stream relevance weights. We propose two versions of the MSCHMM. The first one introduces the relevance weights at the state level while the second one introduces the weights at the component level. We illustrate the performance of the proposed MSCHMM structures using synthetic data sets. We also apply them to the problem of landmine detection using ground penetrating radar. We show that when the multiple sources of information are equally relevant across all training data, the performance of the proposed MSCHMM is comparable to the baseline CHMM. However, when the relevance of the sources varies, the MSCHMM outperforms the baseline CHMM because it can learn the optimal relevance weights. We also show that our approach outperforms existing multi-stream HMM because the latter one cannot optimize all model parameters simultaneously.

Adaptive Local Fusion With Fuzzy Integrals

We propose a novel method for fusing different classifiers outputs. Our approach, called context extraction for local fusion with fuzzy integrals (CELF-FI), is a local approach that adapts a fuzzy integrals fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification and multialgorithm fusion criteria into a joint objective function. This objective function consists of two terms: The first is designed to produce compact clusters, called contexts, and the second is designed to produce Sugeno measures for fuzzy integral fusion for each context. The terms are optimized simultaneously via alternating optimization. To test a new sample, first, its features (extracted by each algorithm) are used to assign it to each context with a fuzzy membership degree. Second, the sample confidence values (assigned by each algorithm) are fused within each context using the learned context fusion parameters. Then, the context-dependent partial confidence values are weighted by the membership degrees and averaged over all contexts to produce a final confidence value. We illustrate the performance of CELF using synthetic data, and we apply it to the problem of landmine detection using ground penetrating radar and wideband electromagnetic induction. Our extensive experiments have indicated that the proposed fusion approach outperforms all individual classifiers, the global fuzzy integral fusion method, and the basic local fusion with linear aggregation.

Land-Mine Detection With Ground-Penetrating Radar Using Multistream Discrete Hidden Markov Models

We propose a multistream discrete hidden Markov model (DHMM) framework and apply it to the problem of land-mine detection using ground-penetrating radar (GPR). We hypothesize that each signature (mine or nonmine) can be characterized better by multiple synchronous sequences representing features that capture different environments and different radar characteristics. This paper is motivated by the fact that mines and clutter objects can have different characteristics depending on the mine type, soil and weather conditions, and burial depth. Thus, ideally different sets of specialized feature extraction mechanisms may be needed to achieve high detection and low false alarm rates. In order to fuse the different modalities, a multistream DHMM that includes a stream relevance weighting component is developed. The relevance weight of each stream depends on the symbols and the states. We reformulate the Baum-Welch and the minimum classification error/gradient probabilistic descent learning algorithms to include stream relevance weights and partial state probabilities. We generalize their objective functions and derive the necessary conditions to update all model parameters simultaneously. The results on a synthetic data set and a collection of GPR signatures show that the proposed multistream DHMM framework outperforms the basic single-stream DHMM where all the streams are treated equally important.

Detection of Landmines from Acoustic Images Based on Cepstral Coefficients

This paper introduces a cepstral approach for the automatic detection of landmines from acoustic images. This approach is based on treating the problem of landmine detection as a pattern recognition problem. Cepstral features are extracted from a group of landmine images which are transformed first to 1-D signals by lexicographic ordering. Mel frequency cepstral coefficients (MFCCs) and polynomial shaping coefficients are extracted from these 1-D signals to form a database of features, which can be used to train a neural network with the landmine features. The landmine detection can be performed by extracting features from any new image with the same method used in the training phase. These features are tested with the neural network to decide whether a landmine exists or not. The different domains are tested and compared for efficient feature extraction from the lexicographically ordered 1-D signals. Experimental results show the success of the proposed cepstral approach for landmine detection at low as well as high signal to noise ratios. Results also show that the discrete cosine transform is the most appropriate domain for feature extraction.

Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic $K$-Nearest Neighbor Classifier

This paper describes an algorithm for land mine detection using sensor data generated by a ground-penetrating radar (GPR) system that uses edge histogram descriptors for feature extraction and a possibilistic <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -nearest neighbors ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -NNs) rule for confidence assignment. The algorithm demonstrated the best performance among several high-performance algorithms in extensive testing on a large real-world datasets associated with the difficult problem of land mine detection. The superior performance of the algorithm is attributed to the use of the possibilistic <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -NN algorithm, thereby providing important evidence supporting the use of possibilistic methods in real-world applications. The GPR produces a 3-D array of intensity values, representing a volume below the surface of the ground. First, a computationally inexpensive prescreening algorithm for anomaly detection is used to focus attention and identify candidate signatures that resemble mines. The identified regions of interest are processed further by a feature extraction algorithm to capture their salient features. We use translation-invariant features that are based on the local edge distribution of the 3-D GPR signatures. Specifically, each 3-D signature is divided into subsignatures, and the local edge distribution for each subsignature is represented by a histogram. Next, the training signatures are clustered to identify prototypes. The main idea is to identify few prototypes that can capture the variations of the signatures within each class. These variations could be due to different mine types, different soil conditions, different weather conditions, etc. Fuzzy memberships are assigned to these representatives to capture their degree of sharing among the mines and false alarm classes. Finally, a possibilistic <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -NN-based rule is used to assign a confidence value to distinguish true detections from false alarms. The proposed algorithm is implemented and integrated within a complete land mine prototype system. It is trained, field-tested, evaluated, and compared using a large-scale cross-validation experiment that uses a diverse dataset acquired from four outdoor test sites at different geographic locations. This collection covers over 41 807 m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of ground and includes 1593 mine encounters.

Development of a Coded Aperture X-Ray Backscatter Imager for Explosive Device Detection

Defence R&D Canada has an active research and development program on detection of explosive devices using nuclear methods. One system under development is a coded aperture-based X-ray backscatter imaging detector designed to provide sufficient speed, contrast and spatial resolution to detect antipersonnel landmines and improvised explosive devices. The successful development of a hand-held imaging detector requires, among other things, a light-weight, ruggedized detector with low power requirements, supplying high spatial resolution. The University of California, San Diego-designed HEXIS detector provides a modern, large area, high-temperature CZT imaging surface, robustly packaged in a light-weight housing with sound mechanical properties. Based on the potential for the HEXIS detector to be incorporated as the detection element of a hand-held imaging detector, the authors initiated a collaborative effort to demonstrate the capability of a coded aperture-based X-ray backscatter imaging detector. This paper will discuss the landmine and IED detection problem and review the coded aperture technique. Results from initial proof-of-principle experiments will then be reported.

Scattering of a buried circular membrane imbedded in a rigid substrate in a layered fluid waveguide

A study of mathematical modeling of the buried landmine detection problem involves wave propagation in a layered waveguide in the presence of a flush mount buried circular target. In this study, emphasis is placed on acoustic to seismic coupling of an airborne CW point source located over an iso-velocity fluid layer. The top plate of the buried landmine is modeled as a circular elastic membrane stretched flush over a cylindrical cavity in a rigid substrate beneath the fluid layer. The finite fluid layer affords a manageable study of the modal resonances in the waveguide system with and without the target. The Helmholtz equation is solved in the atmospheric layer using cylindrical coordinates and a point source. The homogeneous Helmholtz equation is used in the fluid layer. Green's function techniques involving vibrations of the membrane are incorporated into the boundary conditions. Results of the closed form normal mode solution will be presented in a MATLAB™ user interface; describing the effects of frequency, depth, density, sound, absorption, including radius and elastic parameters of the membrane. Comparison of the results (involving the fluid surface particle velocity profiles across the target) will be made with experiments reported in the literature to evaluate its usefulness.

Minimum Classification Error Training for Choquet Integrals With Applications to Landmine Detection

A novel algorithm for discriminative training of Choquet-integral-based fusion operators is described. Fusion is performed by Choquet integration of classifier outputs with respect to fuzzy measures. The fusion operators are determined by the parameters of fuzzy measures. These parameters are found by minimizing a minimum classification error (MCE) objective function. The minimization is performed with respect to a special class of measures, the Sugeno lambda-measures. An analytic expression is derived for the gradient of the Choquet integral with respect to the Sugeno lambda-measure. The new algorithm is applied to a landmine detection problem, and compared to previous techniques.

A novel SVM for Ground Penetrating Synthetic Aperture Radar landmine detection

The use of vehicle-or air-borne Ground Penetrating Synthetic Aperture Radar (GPSAR) to quickly detect landmines over large areas is becoming a trend. However, producing too many false alarms in GPSAR landmine detection is a major challenge in practical applications of GPSAR. Support Vector Machine (SVM), employing structural risk minimization theory, does not need large amounts of training data, which makes it suitable for solving the landmine detection problem. In this paper, a novel SVM with a hypersphere instead of a hyperplane classification boundary is proposed for landmine detection in GPSAR. The HyperSphere-SVM (HS-SVM) can be trained with both landmine and clutter data, or with landmine data only, which are called the two-class HS-SVM and the one-class HS-SVM, respectively. The HS-SVM has better generalization capability than the traditional HyperPlane-SVM (HP-SVM) with respect to varying operating conditions. Quantitative comparisons have been made using real data collected with the rail-GPSAR landmine detection system, which show that both the two-class and the one-class HS-SVMs have better detection performance than the HP-SVM.

Hybrid deliberative/reactive control of a scanning system for landmine detection

Antipersonnel mines infest fields all over the world. According to recent estimates, landmines are killing and maiming more than 2000 innocent civilians per month. The problem of landmine detection and removal requires the cooperation of a number of engineering fields, which in turn poses a need for new technologies, such as improved sensors, efficient manipulators and mobile robots. This paper describes the configuration and control architecture of a scanning manipulator for detecting antipersonnel landmines. The scanning system is part of a demining system based on a walking robot that acts as the carrier for the scanning manipulator. Broadly speaking, the scanning system consists of a sensor head that can detect certain kinds of landmines and, to move the sensor head over large areas, a manipulator that has been appropriately sensorized to scan irregular terrains in the presence of obstacles. The proposed control architecture is of the hybrid deliberative/reactive type: A deliberative controller defines a sweep trajectory that furnishes complete coverage of the infested area, while two reactive controllers are involved in on-line adaptation to the environment. Experiments show good performance of the whole system.

Application of feature extraction methods for landmine detection using the Wichmann/Niitek ground-penetrating radar

Ground-penetrating radar (GPR) has been proposed as an alternative to classical electromagnetic induction techniques for the landmine detection problem. The Wichmann/Niitek system provides a good platform for novel GPR-based antitank mine detection and classification algorithm development due to its extremely high SNR. When the GPR sensor is mounted on a moving vehicle, the target signatures are hyperbolas in a time-domain data record. The goal of this work is to extract useful features that exploit this knowledge in order to improve target detection. The algorithms can be divided into two steps: feature extraction and classification. Preprocessing is also considered to remove both stationary effects and nonstationary drift of the data and to improve the contrast of the desired hyperbolas. The algorithm is evaluated using real data over primarily plastic antitank mines collected with a fielded GPR sensor at a government test site.