An evaluation of several fusion algorithms for anti-tank landmine detection and discrimination

Many algorithms have been proposed for detecting anti-tank landmines and discriminating between mines and clutter objects using data generated by a ground penetrating radar (GPR) sensor. Our extensive testing of some of these algorithms has indicated that their performances are strongly dependent upon a variety of factors that are correlated with geographical and environmental conditions. It is typically the case that one algorithm may perform well in one setting and not so well in another. Thus, fusion methods that take advantage of the stronger algorithms for a given setting without suffering from the effects of weaker algorithms in the same setting are needed to improve the robustness of the detection system. In this paper, we discuss, test, and compare seven different fusion methods: Bayesian, distance-based, Dempster-Shafer, Borda count, decision template, Choquet integral, and context-dependent fusion. We present the results of a cross validation experiment that uses a diverse data set together with results of eight detection and discrimination algorithms. These algorithms are the top ranked algorithms after extensive testing. The data set was acquired from multiple collections from four outdoor sites at different locations using the NIITEK GPR system. This collection covers over 41,807 m² of ground and includes 1593 anti-tank mine encounters.     

A Back-propagation Neural Network Landmine Detector Using the Delta-technique and S-statistic

Landmines are a major problem facing the world today; there are millions of these deadly weapons still buried in various countries around the world. Humanitarian organizations dedicate an immeasurable amount of time, effort, and money to find and remove as many of these mines as possible. Unfortunately, landmines can be made out of common materials which make the correct detection of them very difficult. This paper analyzes the effectiveness of combining certain statistical techniques with a neural network to improve detection. The detection method must not only detect the majority of landmines in the ground, it must also filter out as many of the false alarms as possible. This is the true challenge to developing landmine detection algorithms. Our approach combines a Back-Propagation Neural Network (BPNN) with statistical techniques and compares the performance of mine detection against the performance of the energy detector and the δ-technique. Our results show that the combination of the δ-technique and the S-statistics with a neural network improves the performance.     

Covariance-guided landmine detection and discrimination using ground-penetrating radar data

Ground penetrating Radar (GPR) can detect and deliver the response signal from any buried kind of object like plastic or metallic landmines, stones, and wood sticks. It delivers three kinds of data: Ascan, Bscan, and Cscan. However, it cannot discriminate between landmines and inoffensive objects or ‘clutter.’ One-class classification is an alternative to detect landmines, especially, as landmines features data are unbalanced. In this article, we investigate the effectiveness of the Covariance-guided One-Class Support Vector Machine (COSVM) to detect, discriminate, and locate landmines efficiently. In fact, compared to existing one-class classifiers, the COSVM has the advantage of emphasizing low variance directions. Moreover, we will compare the one-class classification to multiclass classification to tease out the advantage of the former over the latter as data are unbalanced. Our method consists of extracting Ascan GPR data. Extracted features are used as an input for COSVM to discriminate between landmines and clutter. We provide an extensive evaluation of our detection method compared to other methods based on relevant state of the art one-class and multiclass classifiers, on the well-known MACADAM database. Our experimental results show clearly the superiority of using COSVM in landmine detection and localization.     

Evaluation of Sensors and Mapping Approaches for Disasters in Tunnels

Ground or aerial robots equipped with advanced sensing technologies, such as three‐dimensional laser scanners and advanced mapping algorithms, are deemed useful as a supporting technology for first responders. A great deal of excellent research in the field exists, but practical applications at real disaster sites are scarce. Many projects concentrate on equipping robots with advanced capabilities, such as autonomous exploration or object manipulation. In spite of this, realistic application areas for such robots are limited to teleoperated reconnaissance or search. In this paper, we investigate how well state‐of‐the‐art and off‐the‐shelf components and algorithms are suited for reconnaissance in current disaster‐relief scenarios. The basic idea is to make use of some of the most common sensors and deploy some widely used algorithms in a disaster situation, and to evaluate how well the components work for these scenarios. We acquired the sensor data from two field experiments, one from a disaster‐relief operation in a motorway tunnel, and one from a mapping experiment in a partly closed down motorway tunnel. Based on these data, which we make publicly available, we evaluate state‐of‐the‐art and off‐the‐shelf mapping approaches. In our analysis, we integrate opinions and replies from first responders as well as from some algorithm developers on the usefulness of the data and the limitations of the deployed approaches, respectively. We discuss the lessons we learned during the two missions. These lessons are interesting for the community working in similar areas of urban search and rescue, particularly reconnaissance and search.     

Efficient online cycle detection technique combining with Steensgaard points‐to information

Pointer analysis is a key static analysis during compilation. Several client analyses and transformations rely on precise pointer information to optimize programs. Therefore, it is paramount to improve the efficiency of pointer analysis. A critical piece of an inclusion‐based pointer analysis is online cycle detection. The efficiency of pointer analysis is significantly influenced by the efficacy of detecting cycles. Existing approaches perform poorly when they guess cycle formation in the constraint graph. Thus, the number of false cycle‐detection triggers of the state‐of‐the‐art methods is considerably high (over 99% on Standard Performance Evaluation Corporation (SPEC) benchmarks). In this paper, we propose bootstrapping as a way to improve cycle detection predictability of pointer analysis. The main idea is to run a sequence of increasingly precise analyses to feed into the next more precise analysis to improve the efficiency of the latter analysis. In this process, we develop a new notion of pointer equivalence called constraint equivalence. Using Steensgaard's fast unification algorithm as the bootstrap, we devise a new cycle detection method for Andersen's inclusion‐based analysis. We measure the effectiveness of our approach using a suite of programs including SPEC 2000 benchmarks and two open‐source programs, and find that our method can reduce the number of false cycle detections by almost 22× compared with a state‐of‐the‐art method. This leads to an overall analysis time improvement of 18% on an average. Copyright © 2015 John Wiley & Sons, Ltd.     

Parallel Marching Blocks: A Practical Isosurfacing Algorithm for Large Data on Many‐Core Architectures

Interactive isosurface visualisation has been made possible by mapping algorithms to GPU architectures. However, current state‐of‐the‐art isosurfacing algorithms usually consume large amounts of GPU memory owing to the additional acceleration structures they require. As a result, the continued limitations on available GPU memory mean that they are unable to deal with the larger datasets that are now increasingly becoming prevalent. This paper proposes a new parallel isosurface‐extraction algorithm that exploits the blocked organisation of the parallel threads found in modern many‐core platforms to achieve fast isosurface extraction and reduce the associated memory requirements. This is achieved by optimising thread co‐operation within thread‐blocks and reducing redundant computation; ultimately, an indexed triangular mesh can be produced. Experiments have shown that the proposed algorithm is much faster (up to 10×) than state‐of‐the‐art GPU algorithms and has a much smaller memory footprint, enabling it to handle much larger datasets (up to 64×) on the same GPU.     

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.     

DYLEMA: Using walking robots for landmine detection and location

Detection and removal of antipersonnel landmines is an important worldwide concern. A huge number of landmines has been deployed over the last twenty years, and demining will take several more decades, even if no more mines were deployed in future. An adequate mine-clearance rate can only be achieved by using new technologies such as improved sensors, efficient manipulators and mobile robots. This paper presents some basic ideas on the configuration of a mobile system for detecting and locating antipersonnel landmines efficiently and effectively. The paper describes the main features of the overall system, which consists of a sensor head that can detect certain landmine types, a manipulator to move the sensor head over large areas, a locating system based on a global-positioning system, a remote supervisor computer and a legged robot used as the subsystems’ carrier. The whole system has been configured to work in a semi-autonomous mode with a view also to robot mobility and energy efficiency.     

Biologically inspired probabilistic coverage for mobile sensor networks

Coupling sensors in a sensor network with mobility mechanism can boost the performance of wireless sensor networks (WSNs). In this paper, we address the problem of self-deploying mobile sensors to reach high coverage. The problem is modeled as a multi-objective optimization that simultaneously minimizes two contradictory parameters; the total sensor moving distance and the total uncovered area. In order to resolve the aforementioned deployment problem, this study investigates the use of biologically inspired mechanisms, including evolutionary algorithms and swarm intelligence, with their state-of-the-art algorithms. Unlike most of the existing works, the coverage parameter is expressed as a probabilistic inference model due to uncertainty in sensor readings. To the best of our knowledge, probabilistic coverage of mobile sensor networks has not been addressed in the context of multi-objective bio-inspired algorithms. Performance evaluations on deployment quality and deployment cost are measured and analyzed through extensive simulations, showing the effectiveness of each algorithm under the developed objective functions. Simulations reveal that only one multi-objective evolutionary algorithm; the so-called multi-objective evolutionary algorithm with decomposition survives to effectively tackle the probabilistic coverage deployment problem. It gathers more than 78 % signals from all of the targets (and in some cases reaches 100 % certainty). On the other hand, non-dominated sorting genetic algorithm II, multi-objective particle swarm optimization, and non-dominated sorting particle swarm optimization show inferior performance down to 16–32 %, necessitating further modifications in their internal mechanisms.     

WSN节能设计研究现状

传感器网络(WSN)综合了传感器技术、嵌入式计算技术、通信技术等,在人无法或很难到达的地方具有很高的利用价值。传感器网络能够应用于军事和民用方面,然而传感器网络中的节点数量众多,体积小,能量受限,因此如何降低节点的能量消耗,延长网络的寿命显的极为重要。文章介绍了传感器网络的结构,总结了传感器网络中的节能算法和协议,并提出了今后发展的方向。     

Comparison of multitemporal compositing methods for burnt area detection in Southeast Asian conditions

This study investigated the usability of different multitemporal compositing methods for burnt area detection purposes in the humid tropical conditions of insular Southeast Asia, characterised by persisting cloud cover, varying fire‐induced spectral changes and large amount of small burn scars. Six monthly composites of the Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance images (MOD09) were built using six different algorithms. The performance and usability of the compositing algorithms were evaluated using three criteria: separability between burnt and unburnt areas, homogeneity and average sensor zenith angle. Maximum surface temperature method (band 31, 11.0 µm) produced the most homogeneous composites with preference to close‐to‐nadir observations. However, these composites showed unexpectedly low separability between burnt and unburnt areas, mainly due to low spatial resolution of band 31 (1000 m). Overall, taking into account the performance of the compositing methods and the large amount of small burnt areas in insular Southeast Asia, a minimum NIR (band 2, 0.86 µm) method, combined with pre‐compositing cloud and cloud shadow removal, was seen as the most suitable compositing method for burnt area detection in this region. Its strengths were 250 m spatial resolution in pixel selection and high burnt/unburnt separability combined with reasonably good performance on homogeneity and average sensor zenith angle.     

Strength of landmine signatures under different soil conditions: implications for sensor fusion

Most sensors for the detection of buried landmines are influenced by the properties of the soil that surrounds the mine. The temporal and spatial variability in soil properties accounts for a significant part of the detection uncertainty that is associated with most sensors. In particular, most sensor types (e.g. ground-penetrating radar, thermal infrared cameras, and chemical sniffers) are affected by the water content of the soil. However, each sensor type reacts in its own way to variations in soil water content and other soil properties. The resulting variation in sensor performance has serious implications for sensor fusion operations. We show how knowledge of soil physics can contribute to a better understanding of sensor performance and can lead to improved data fusion.     

Microfabrication of thin film temperature sensor for cryogenic measurement

In this paper, thin film Pt temperature microsensor in the temperature range of 10–100 K for cryogenic engineering applications is proposed and researched. The sensor is designed with two structures, and they are obtained by micro fabrication technology. The sensors are annealed in different conditions. The degree crystallization and grain size are analyzed by X-ray diffraction and SEM for both as-deposited and annealed sensors. The resistance dependency on temperature test result shows that when temperature is larger and smaller than 50 K, the average temperature coefficient resistance (TCR) of rectangular shape sensor could achieve 3,118 ppm/K and above 257 ppm/K, respectively. Meanwhile, TCR of circular shape sensor is 2,778 ppm/K and above 249 ppm/K, respectively. The good thermal cycle stability is observed. After three cycles between 10 and 100 K, the maximum resistance variation values are 0.0034 and 0.0137 %, which correspond to 0.0082 and 0.061 K temperature shift for the rectangular and circular sensors, respectively. The ΔT/T (%) of rectangular and circular sensors is performed with the magnetic field up to 6T in the temperature range of 10–100 K, and they are within the range of ?19.84 to 0.137 and ?2.18 to 11.33 for rectangular and circular sensors,respectively. The impedance test shows that the sensors have the same electric properties under direct current and alternating current condition.     

State of the Art on 3D Reconstruction with RGB‐D Cameras

The advent of affordable consumer grade RGB‐D cameras has brought about a profound advancement of visual scene reconstruction methods. Both computer graphics and computer vision researchers spend significant effort to develop entirely new algorithms to capture comprehensive shape models of static and dynamic scenes with RGB‐D cameras. This led to significant advances of the state of the art along several dimensions. Some methods achieve very high reconstruction detail, despite limited sensor resolution. Others even achieve real‐time performance, yet possibly at lower quality. New concepts were developed to capture scenes at larger spatial and temporal extent. Other recent algorithms flank shape reconstruction with concurrent material and lighting estimation, even in general scenes and unconstrained conditions. In this state‐of‐the‐art report, we analyze these recent developments in RGB‐D scene reconstruction in detail and review essential related work. We explain, compare, and critically analyze the common underlying algorithmic concepts that enabled these recent advancements. Furthermore, we show how algorithms are designed to best exploit the benefits of RGB‐D data while suppressing their often non‐trivial data distortions. In addition, this report identifies and discusses important open research questions and suggests relevant directions for future work.     

A review of satellite and airborne sensors for remote sensing based detection of minefields and landmines

This paper focuses on the use of space and airborne sensors that can be applied to detect landmines and minefields. First the landmine and minefield problem is addressed and examples of the use of remote sensing images are presented that could provide valuable information for the mine action process and assist in conventional minefield and landmine detection methods. This is followed by an overview on relevant (declassified) aspects related to strategic overhead detection techniques developed by the military/intelligence community as well as those of civilian space and airborne remote sensing programmes. The airborne sensing techniques describe the state of the art of sensors such as optical (film, multi- and hyperspectral sensors), thermal infrared as well as microwave sensors and their suitability--limitations for remote sensing based minefield and landmine detection purposes.     

Orthorectified image mosaic of Antarctica from 1963 Argon satellite photography: image processing and glaciological applications

Using the state‐of‐the‐art digital imaging technology, extended block adjustment, orthorectification and mosaicking, individual Declassified Intelligence Satellite Argon photographic images are precisely assembled into a map quality mosaic of coastal Antarctica. The geometric accuracy of the mosaic is estimated to be approximately equivalent to the original resolution of the Argon photography, which is about 140 m. We compare the Argon mosaic with later satellite images to investigate changes in ice sheet geographic features and dynamical glaciological processes.     

Robot Navigation in a Decentralized Landmark-Free Sensor Network

A wireless sensor network has the ability to autonomously perform event detection over large areas, but power and/or cost constraints limit the addition of equipment such as cameras onto sensor modules to verify events. Accordingly, verification must be performed by an independent mobile robotic vehicle which has sensing equipment for improved event detection. The main challenge, however, is that the robotic vehicle itself is typically located somewhere in the sensor field and has no prior knowledge of the geographic location of the event. In this paper, we specifically focus upon the scenario of navigating a robotic vehicle through a stationary wireless sensor network as a means to perform event verification. The underlying assumptions are that the robotic vehicle has distance traveled and heading measurements, but the only additional information provided by the stationary sensors is a communication boundary. More significantly, we emphasize that under this scenario, neither the robot nor the ground-fixed sensing nodes have location or any other geographical landmark information. The paper introduces two distinct and novel navigation algorithms that permit the robotic vehicle to travel from one fixed node to another along a communication path established in an ad-hoc fashion. These navigation algorithms have been tested on a newly developed UTrekr robotic vehicle within a hardware based ground-fixed sensor network and under assumption of perfect communication and network operations, we report a nearly 100% success rate even while using open-loop robot control.     

经典YOLO系列目标检测算法及其在乳腺癌检测中的应用

目前乳腺癌已取代肺癌成为年发病率最高的癌症, 基于深度学习的目标检测技术可对乳腺X线、乳腺超声和乳腺核磁共振等非侵入式成像进行自动病变检测, 已成为乳腺癌辅助诊断的首选途径. YOLO (you only look once)系列算法是基于深度学习的目标检测算法, 经典YOLO算法在速度和精准度具有优势, 被广泛应用于计算机视觉各领域, 最新YOLO算法是计算机视觉领域的SOTA (state of the art)模型, 如何利用YOLO系列算法提高乳腺癌检测速度和准确率, 已经成为研究者关注的焦点之一. 基于此, 本文介绍经典YOLO系列算法的原理, 梳理经典YOLO系列算法在乳腺癌图像检测中的应用现状, 并归纳总结现存问题, 同时对YOLO系列算法在乳腺癌检测的进一步应用进行展望.     

LMA: A generic and efficient implementation of the Levenberg–Marquardt Algorithm

This paper presents an open‐source, generic and efficient implementation of a very popular nonlinear optimization method: the Levenberg–Marquardt algorithm (LMA). This minimization algorithm is well known and hundreds of implementations have already been released. However, none of them offer at the same time a high level of genericity, a friendly syntax and a high computational performance. In this paper, we propose a solution to gather all those advantages in one library named LMA. The main challenge is to implement an efficient solver for every encounter problem. To overcome this difficulty, LMA uses compile time algorithms to design a code specific to the given optimization problem. The features of LMA are presented and the performances are compared with the state‐of‐the‐art best alternatives through extensive benchmarks on different kind of problems. Copyright © 2017 John Wiley & Sons, Ltd.