Previous Issue

E-Mail Alert

Add your e-mail address to receive forthcoming issues of this journal:

Journal Browser

Journal Browser

Table of Contents

Sensors, Volume 18, Issue 7 (July 2018)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Cover Story (view full-size image) Radon is a noble gas originated from the radioactive decay chain of uranium or thorium. It emanates [...] Read more.
View options order results:
result details:
Displaying articles 1-363
Export citation of selected articles as:
Open AccessArticle A Parameter Self-Calibration Method for GNSS/INS Deeply Coupled Navigation Systems in Highly Dynamic Environments
Sensors 2018, 18(7), 2341; https://doi.org/10.3390/s18072341 (registering DOI)
Received: 18 June 2018 / Revised: 10 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (2243 KB) | HTML Full-text | XML Full-text
Abstract
The GNSS/INS (Global Navigation Satellite System/Inertial Navigation System) navigation system has been widely discussed in recent years. Because of the unique INS-aided loop structure, the deeply coupled system performs very well in highly dynamic environments. In practice, vehicle maneuvering has a big influence
[...] Read more.
The GNSS/INS (Global Navigation Satellite System/Inertial Navigation System) navigation system has been widely discussed in recent years. Because of the unique INS-aided loop structure, the deeply coupled system performs very well in highly dynamic environments. In practice, vehicle maneuvering has a big influence on the performance of IMUs (Inertial Measurement Unit), and determining whether the selected IMUs and receiver parameters satisfy the loop dynamic requirement is still a critical problem for deeply coupled systems. Aiming at this, a new parameter self-calibration method based on the norm principle is proposed which explains the relationship between IMU precision and the velocity error of the system; the method will also provide a detailed solution to calculate the loop steady-state tracking error, so it will eventually make a judgment about the stability of the tracking loop under present system parameter settings. Lastly, a full digital simulation platform is set up, and the results of simulations show good agreement with the proposed method. Full article
(This article belongs to the Special Issue Inertial Sensors and Systems 2018)
Figures

Figure 1

Open AccessArticle Partial Inductance Model of Induction Machines for Fault Diagnosis
Sensors 2018, 18(7), 2340; https://doi.org/10.3390/s18072340 (registering DOI)
Received: 31 May 2018 / Revised: 12 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (11977 KB) | HTML Full-text | XML Full-text
Abstract
The development of advanced fault diagnostic systems for induction machines through the stator current requires accurate and fast models that can simulate the machine under faulty conditions, both in steady-state and in transient regime. These models are far more complex than the models
[...] Read more.
The development of advanced fault diagnostic systems for induction machines through the stator current requires accurate and fast models that can simulate the machine under faulty conditions, both in steady-state and in transient regime. These models are far more complex than the models used for healthy machines, because one of the effect of the faults is to change the winding configurations (broken bar faults, rotor asymmetries, and inter-turn short circuits) or the magnetic circuit (eccentricity and bearing faults). This produces a change of the self and mutual phase inductances, which induces in the stator currents the characteristic fault harmonics used to detect and to quantify the fault. The development of a machine model that can reflect these changes is a challenging task, which is addressed in this work with a novel approach, based on the concept of partial inductances. Instead of developing the machine model based on the phases’ coils, it is developed using the partial inductance of a single conductor, obtained through the magnetic vector potential, and combining the partial inductances of all the conductors with a fast Fourier transform for obtaining the phases’ inductances. The proposed method is validated using a commercial induction motor with forced broken bars. Full article
(This article belongs to the Special Issue Sensors for Fault Detection)
Figures

Figure 1

Open AccessArticle Extending QGroundControl for Automated Mission Planning of UAVs
Sensors 2018, 18(7), 2339; https://doi.org/10.3390/s18072339 (registering DOI)
Received: 15 June 2018 / Revised: 9 July 2018 / Accepted: 17 July 2018 / Published: 18 July 2018
PDF Full-text (23055 KB)
Abstract
Unmanned Aerial Vehicles (UAVs) have become very popular in the last decade due to some advantages such as strong terrain adaptation, low cost, zero casualties, and so on. One of the most interesting advances in this field is the automation of mission planning
[...] Read more.
Unmanned Aerial Vehicles (UAVs) have become very popular in the last decade due to some advantages such as strong terrain adaptation, low cost, zero casualties, and so on. One of the most interesting advances in this field is the automation of mission planning (task allocation) and real-time replanning, which are highly useful to increase the autonomy of the vehicle and reduce the operator workload. These automated mission planning and replanning systems require a Human Computer Interface (HCI) that facilitates the visualization and selection of plans that will be executed by the vehicles. In addition, most missions should be assessed before their real-life execution. This paper extends QGroundControl, an open-source simulation environment for flight control of multiple vehicles, by adding a mission designer that permits the operator to build complex missions with tasks and other scenario items; an interface for automated mission planning and replanning, which works as a test bed for different algorithms, and a Decision Support System (DSS) that helps the operator in the selection of the plan. In this work, a complete guide of these systems and some practical use cases are provided Full article
(This article belongs to the Special Issue Internet of Things Middleware Platforms and Sensing Infrastructure)
Open AccessFeature PaperReview Update of Single Event Effects Radiation Hardness Assurance of Readout Integrated Circuit of Infrared Image Sensors at Cryogenic Temperature
Sensors 2018, 18(7), 2338; https://doi.org/10.3390/s18072338 (registering DOI)
Received: 4 June 2018 / Revised: 15 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (776 KB)
Abstract
This paper review presents Single Event Effects (SEE) irradiation tests under heavy ions of the test-chip of D-Flip-Flop (DFF) cells and complete readout integrated circuits (ROIC) as a function of temperature, down to 50 K. The analyses of the experimental data are completed
[...] Read more.
This paper review presents Single Event Effects (SEE) irradiation tests under heavy ions of the test-chip of D-Flip-Flop (DFF) cells and complete readout integrated circuits (ROIC) as a function of temperature, down to 50 K. The analyses of the experimental data are completed using the SEE prediction tool MUSCA SEP3. The conclusions derived from the experimental measurements and related analyses allow to update the current SEE radiation hardness assurance (RHA) for readout integrated circuits of infrared image sensors used at cryogenic temperatures. The current RHA update is performed on SEE irradiation tests at room temperature, as opposed to the operational cryogenic temperature. These tests include SET (Single Event Transient), SEU (Single Event Upset) and SEFI (Single Event Functional Interrupt) irradiation tests. This update allows for reducing the cost of ROIC qualifications and the test setup complexity for each space mission. Full article
(This article belongs to the Special Issue Sensors and Materials for Harsh Environments)
Open AccessArticle Adaptive Square-Root Unscented Particle Filtering Algorithm for Dynamic Navigation
Sensors 2018, 18(7), 2337; https://doi.org/10.3390/s18072337 (registering DOI)
Received: 26 May 2018 / Revised: 10 July 2018 / Accepted: 17 July 2018 / Published: 18 July 2018
PDF Full-text (2701 KB) | HTML Full-text | XML Full-text
Abstract
This paper presents a new adaptive square-root unscented particle filtering algorithm by combining the adaptive filtering and square-root filtering into the unscented particle filter to inhibit the disturbance of kinematic model noise and the instability of filtering data in the process of nonlinear
[...] Read more.
This paper presents a new adaptive square-root unscented particle filtering algorithm by combining the adaptive filtering and square-root filtering into the unscented particle filter to inhibit the disturbance of kinematic model noise and the instability of filtering data in the process of nonlinear filtering. To prevent particles from degeneracy, the proposed algorithm adaptively adjusts the adaptive factor, which is constructed from predicted residuals, to refrain from the disturbance of abnormal observation and the kinematic model noise. Cholesky factorization is also applied to suppress the negative definiteness of the covariance matrices of the predicted state vector and observation vector. Experiments and comparison analysis were conducted to comprehensively evaluate the performance of the proposed algorithm. The results demonstrate that the proposed algorithm exhibits a strong overall performance for integrated navigation systems. Full article
(This article belongs to the Special Issue Sensor Fusion and Novel Technologies in Positioning and Navigation)
Figures

Figure 1

Open AccessArticle Evaluation of Atmospheric Effects on Interferograms Using DEM Errors of Fixed Ground Points
Sensors 2018, 18(7), 2336; https://doi.org/10.3390/s18072336 (registering DOI)
Received: 9 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (2452 KB) | HTML Full-text | XML Full-text
Abstract
High-resolution synthetic aperture radar (SAR) data are widely used for disaster monitoring. To extract damaged areas automatically, it is essential to understand the relationships among the sensor specifications, acquisition conditions, and land cover. Our previous studies developed a method for estimating the phase
[...] Read more.
High-resolution synthetic aperture radar (SAR) data are widely used for disaster monitoring. To extract damaged areas automatically, it is essential to understand the relationships among the sensor specifications, acquisition conditions, and land cover. Our previous studies developed a method for estimating the phase noise of interferograms using several pairs of TerraSAR-X series (TerraSAR-X and TanDEM-X) datasets. Atmospheric disturbance data are also necessary to interpret the interferograms; therefore, the purpose of this study is to estimate the atmospheric effects by focusing on the difference in digital elevation model (DEM) errors between repeat-pass (two interferometric SAR images acquired at different times) and single-pass (two interferometric SAR images acquired simultaneously) interferometry. Single-pass DEM errors are reduced due to the lack of temporal decorrelation and atmospheric disturbances. At a study site in the city of Tsukuba, a quantitative analysis of DEM errors at fixed ground objects shows that the atmospheric effects are estimated to contribute 75% to 80% of the total phase noise in interferograms. Full article
Figures

Figure 1

Open AccessArticle Rapid Airplane Detection in Remote Sensing Images Based on Multilayer Feature Fusion in Fully Convolutional Neural Networks
Sensors 2018, 18(7), 2335; https://doi.org/10.3390/s18072335 (registering DOI)
Received: 8 May 2018 / Revised: 5 July 2018 / Accepted: 13 July 2018 / Published: 18 July 2018
PDF Full-text (3624 KB) | HTML Full-text | XML Full-text
Abstract
To address the issues encountered when using traditional airplane detection methods, including the low accuracy rate, high false alarm rate, and low detection speed due to small object sizes in aerial remote sensing images, we propose a remote sensing image airplane detection method
[...] Read more.
To address the issues encountered when using traditional airplane detection methods, including the low accuracy rate, high false alarm rate, and low detection speed due to small object sizes in aerial remote sensing images, we propose a remote sensing image airplane detection method that uses multilayer feature fusion in fully convolutional neural networks. The shallow layer and deep layer features are fused at the same scale after sampling to overcome the problems of low dimensionality in the deep layer and the inadequate expression of small objects. The sizes of candidate regions are modified to fit the size of the actual airplanes in the remote sensing images. The fully connected layers are replaced with convolutional layers to reduce the network parameters and adapt to different input image sizes. The region proposal network shares convolutional layers with the detection network, which ensures high detection efficiency. The simulation results indicate that, when compared to typical airplane detection methods, the proposed method is more accurate and has a lower false alarm rate. Additionally, the detection speed is considerably faster and the method can accurately and rapidly complete airplane detection tasks in aerial remote sensing images. Full article
(This article belongs to the Special Issue High-Performance Computing in Geoscience and Remote Sensing)
Figures

Figure 1

Open AccessArticle Peptide-Cellulose Conjugates on Cotton-Based Materials Have Protease Sensor/Sequestrant Activity
Sensors 2018, 18(7), 2334; https://doi.org/10.3390/s18072334 (registering DOI)
Received: 19 April 2018 / Revised: 6 July 2018 / Accepted: 6 July 2018 / Published: 18 July 2018
PDF Full-text (1571 KB) | HTML Full-text | XML Full-text
Abstract
The growing incidence of chronic wounds in the world population has prompted increased interest in chronic wound dressings with protease-modulating activity and protease point of care sensors to treat and enable monitoring of elevated protease-based wound pathology. However, the overall design features needed
[...] Read more.
The growing incidence of chronic wounds in the world population has prompted increased interest in chronic wound dressings with protease-modulating activity and protease point of care sensors to treat and enable monitoring of elevated protease-based wound pathology. However, the overall design features needed for the combination of a chronic wound dressing that lowers protease activity along with protease detection capability as a single platform for semi-occlusive dressings has scarcely been addressed. The interface of dressing and sensor specific properties (porosity, permeability, moisture uptake properties, specific surface area, surface charge, and detection) relative to sensor bioactivity and protease sequestrant performance is explored here. Measurement of the material’s zeta potential demonstrated a correlation between negative charge and the ability of materials to bind positively charged Human Neutrophil Elastase. Peptide-cellulose conjugates as protease substrates prepared on a nanocellulosic aerogel were assessed for their compatibility with chronic wound dressing design. The porosity, wettability and absorption capacity of the nanocellulosic aerogel were consistent with values observed for semi-occlusive chronic wound dressing designs. The relationship of properties that effect dressing functionality and performance as well as impact sensor sensitivity are discussed in the context of the enzyme kinetics. The sensor sensitivity of the aerogel-based sensor is contrasted with current clinical studies on elastase. Taken together, comparative analysis of the influence of molecular features on the physical properties of three forms of cellulosic transducer surfaces provides a meaningful assessment of the interface compatibility of cellulose-based sensors and corresponding protease sequestrant materials for potential use in chronic wound sensor/dressing design platforms. Full article
(This article belongs to the Special Issue Biosensors for Theranostics)
Figures

Graphical abstract

Open AccessArticle Geo-Positioning Accuracy Improvement of Multi-Mode GF-3 Satellite SAR Imagery Based on Error Sources Analysis
Sensors 2018, 18(7), 2333; https://doi.org/10.3390/s18072333 (registering DOI)
Received: 15 June 2018 / Revised: 14 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (2756 KB) | HTML Full-text | XML Full-text
Abstract
The GaoFen-3 (GF-3) satellite is the only synthetic aperture radar (SAR) satellite in the High-Resolution Earth Observation System Project, which is the first C-band full-polarization SAR satellite in China. In this paper, we proposed some error sources-based weight strategies to improve the geometric
[...] Read more.
The GaoFen-3 (GF-3) satellite is the only synthetic aperture radar (SAR) satellite in the High-Resolution Earth Observation System Project, which is the first C-band full-polarization SAR satellite in China. In this paper, we proposed some error sources-based weight strategies to improve the geometric performance of multi-mode GF-3 satellite SAR images without using ground control points (GCPs). To get enough tie points, a robust SAR image registration method and the SAR-features from accelerated segment test (SAR-FAST) method is used to achieve the image registration and tie point extraction. Then, the original position of these tie points in object-space is calculated with the help of the space intersection method. With the dataset clustered by the density-based spatial clustering of applications with noise (DBSCAN) algorithm, we undertake the block adjustment with a bias-compensated rational function model (RFM) aided to improve the geometric performance of these multi-mode GF-3 satellite SAR images. Different weight strategies are proposed to develop the normal equation matrix according to the error sources analysis of GF-3 satellite SAR images, and the preconditioned conjugate gradient (PCG) method is utilized to solve the normal equation. The experimental results indicate that our proposed method can improve the geometric positioning accuracy of GF-3 satellite SAR images within 2 pixels. Full article
(This article belongs to the Special Issue First Experiences with Chinese Gaofen-3 SAR Sensor)
Figures

Figure 1

Open AccessArticle Fault Detection and Isolation via the Interacting Multiple Model Approach Applied to Drive-By-Wire Vehicles
Sensors 2018, 18(7), 2332; https://doi.org/10.3390/s18072332 (registering DOI)
Received: 15 May 2018 / Revised: 8 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (1281 KB) | HTML Full-text | XML Full-text
Abstract
The place of driving assistance systems is currently increasing drastically for road vehicles. Paving the road to the fully autonomous vehicle, the drive-by-wire technology could improve the potential of the vehicle control. The implementation of these new embedded systems is still limited, mainly
[...] Read more.
The place of driving assistance systems is currently increasing drastically for road vehicles. Paving the road to the fully autonomous vehicle, the drive-by-wire technology could improve the potential of the vehicle control. The implementation of these new embedded systems is still limited, mainly for reliability reasons, thus requiring the development of diagnostic mechanisms. In this paper, we investigate the detection and the identification of sensor and actuator faults for a drive-by-wire road vehicle. An Interacting Multiple Model approach is proposed, based on a non-linear vehicle dynamics observer. The adequacy of different probabilistic observers is discussed. The results, based on experimental vehicle signals, show a fast and robust identification of sensor faults while the actuator faults are more challenging. Full article
(This article belongs to the Special Issue Sensors for Fault Detection)
Figures

Figure 1

Open AccessFeature PaperArticle Coalition Formation Based Compressive Sensing in Wireless Sensor Networks
Sensors 2018, 18(7), 2331; https://doi.org/10.3390/s18072331 (registering DOI)
Received: 13 May 2018 / Revised: 8 July 2018 / Accepted: 13 July 2018 / Published: 18 July 2018
PDF Full-text (2358 KB) | HTML Full-text | XML Full-text
Abstract
Compressive sensing originates in the field of signal processing and has recently become a topic of energy-efficient data gathering in wireless sensor networks. In this paper, we propose an energy efficient distributed compressive sensing solution for sensor networks. The proposed solution utilizes sparsity
[...] Read more.
Compressive sensing originates in the field of signal processing and has recently become a topic of energy-efficient data gathering in wireless sensor networks. In this paper, we propose an energy efficient distributed compressive sensing solution for sensor networks. The proposed solution utilizes sparsity distribution of signals to group sensor nodes into several coalitions and then implements localized compressive sensing inside coalitions. This solution improves data-gathering performance in terms of both data accuracy and energy consumption. The approach curbs both data-transmission costs and number of measurements. Coalition-based data gathering cuts transmission costs, and the number of measurements is reduced by scheduling sensor nodes and adjusting their sampling frequency. Our simulation showed that our approach enhances network performance by minimizing energy cost and improving data accuracy. Full article
Figures

Figure 1

Open AccessArticle Towards a Scalable Software Defined Network-on-Chip for Next Generation Cloud
Sensors 2018, 18(7), 2330; https://doi.org/10.3390/s18072330 (registering DOI)
Received: 11 June 2018 / Revised: 11 July 2018 / Accepted: 12 July 2018 / Published: 18 July 2018
PDF Full-text (976 KB) | HTML Full-text | XML Full-text
Abstract
The rapid evolution of Cloud-based services and the growing interest in deep learning (DL)-based applications is putting increasing pressure on hyperscalers and general purpose hardware designers to provide more efficient and scalable systems. Cloud-based infrastructures must consist of more energy efficient components. The
[...] Read more.
The rapid evolution of Cloud-based services and the growing interest in deep learning (DL)-based applications is putting increasing pressure on hyperscalers and general purpose hardware designers to provide more efficient and scalable systems. Cloud-based infrastructures must consist of more energy efficient components. The evolution must take place from the core of the infrastructure (i.e., data centers (DCs)) to the edges (Edge computing) to adequately support new/future applications. Adaptability/elasticity is one of the features required to increase the performance-to-power ratios. Hardware-based mechanisms have been proposed to support system reconfiguration mostly at the processing elements level, while fewer studies have been carried out regarding scalable, modular interconnected sub-systems. In this paper, we propose a scalable Software Defined Network-on-Chip (SDNoC)-based architecture. Our solution can easily be adapted to support devices ranging from low-power computing nodes placed at the edge of the Cloud to high-performance many-core processors in the Cloud DCs, by leveraging on a modular design approach. The proposed design merges the benefits of hierarchical network-on-chip (NoC) topologies (via fusing the ring and the 2D-mesh topology), with those brought by dynamic reconfiguration (i.e., adaptation). Our proposed interconnect allows for creating different types of virtualised topologies aiming at serving different communication requirements and thus providing better resource partitioning (virtual tiles) for concurrent tasks. To further allow the software layer controlling and monitoring of the NoC subsystem, a few customised instructions supporting a data-driven program execution model (PXM) are added to the processing element’s instruction set architecture (ISA). In general, the data-driven programming and execution models are suitable for supporting the DL applications. We also introduce a mechanism to map a high-level programming language embedding concurrent execution models into the basic functionalities offered by our SDNoC for easing the programming of the proposed system. In the reported experiments, we compared our lightweight reconfigurable architecture to a conventional flattened 2D-mesh interconnection subsystem. Results show that our design provides an increment of the data traffic throughput of 9.5% and a reduction of 2.2× of the average packet latency, compared to the flattened 2D-mesh topology connecting the same number of processing elements (PEs) (up to 1024 cores). Similarly, power and resource (on FPGA devices) consumption is also low, confirming good scalability of the proposed architecture. Full article
(This article belongs to the Special Issue Software-Defined Networking Based Mobile Networks)
Figures

Figure 1

Open AccessReview The Odor Characterizations and Reproductions in Machine Olfactions: A Review
Sensors 2018, 18(7), 2329; https://doi.org/10.3390/s18072329 (registering DOI)
Received: 28 May 2018 / Revised: 26 June 2018 / Accepted: 12 July 2018 / Published: 18 July 2018
PDF Full-text (298 KB) | HTML Full-text | XML Full-text
Abstract
Machine olfaction is a novel technology and has been developed for many years. The electronic nose with an array of gas sensors, a crucial application form of the machine olfaction, is capable of sensing not only odorous compounds, but also odorless chemicals. Because
[...] Read more.
Machine olfaction is a novel technology and has been developed for many years. The electronic nose with an array of gas sensors, a crucial application form of the machine olfaction, is capable of sensing not only odorous compounds, but also odorless chemicals. Because of its fast response, mobility and easy of use, the electronic nose has been applied to scientific and commercial uses such as environment monitoring and food processing inspection. Additionally, odor characterization and reproduction are the two novel parts of machine olfaction, which extend the field of machine olfaction. Odor characterization is the technique that characterizes odorants as some form of general odor information. At present, there have already been odor characterizations by means of the electronic nose. Odor reproduction is the technique that re-produces an odor by some form of general odor information and displays the odor by the olfactory display. It enhances the human ability of controlling odors just as the control of light and voice. In analogy to visual and auditory display technologies, is it possible that the olfactory display will be used in our daily life? There have already been some efforts toward odor reproduction and olfactory displays. Full article
(This article belongs to the Section Chemical Sensors)
Figures

Figure 1

Open AccessArticle Efficient Node and Sensed Module Management for Multisensory Wireless Sensor Networks
Sensors 2018, 18(7), 2328; https://doi.org/10.3390/s18072328 (registering DOI)
Received: 14 June 2018 / Revised: 5 July 2018 / Accepted: 16 July 2018 / Published: 18 July 2018
PDF Full-text (3095 KB) | HTML Full-text | XML Full-text
Abstract
In target tracking wireless sensor networks, choosing a part of sensor nodes to execute tracking tasks and letting the other nodes sleep to save energy are efficient node management strategies. However, at present more and more sensor nodes carry many different types of
[...] Read more.
In target tracking wireless sensor networks, choosing a part of sensor nodes to execute tracking tasks and letting the other nodes sleep to save energy are efficient node management strategies. However, at present more and more sensor nodes carry many different types of sensed modules, and the existing researches on node selection are mainly focused on sensor nodes with a single sensed module. Few works involved the management and selection of the sensed modules for sensor nodes which have several multi-mode sensed modules. This work proposes an efficient node and sensed module management strategy, called ENSMM, for multisensory WSNs (wireless sensor networks). ENSMM considers not only node selection, but also the selection of the sensed modules for each node, and then the power management of sensor nodes is performed according to the selection results. Moreover, a joint weighted information utility measurement is proposed to estimate the information utility of the multiple sensed modules in the different nodes. Through extensive and realistic experiments, the results show that, ENSMM outperforms the state-of-the-art approaches by decreasing the energy consumption and prolonging the network lifetime. Meanwhile, it reduces the computational complexity with guaranteeing the tracking accuracy. Full article
(This article belongs to the Special Issue Aerospace Sensors and Multisensor Systems)
Figures

Figure 1

Open AccessArticle Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network
Sensors 2018, 18(7), 2327; https://doi.org/10.3390/s18072327 (registering DOI)
Received: 24 June 2018 / Revised: 9 July 2018 / Accepted: 11 July 2018 / Published: 18 July 2018
PDF Full-text (3371 KB) | HTML Full-text | XML Full-text
Abstract
In recent years, terahertz imaging systems and techniques have been developed and have gradually become a leading frontier field. With the advantages of low radiation and clothing-penetrable, terahertz imaging technology has been widely used for the detection of concealed weapons or other contraband
[...] Read more.
In recent years, terahertz imaging systems and techniques have been developed and have gradually become a leading frontier field. With the advantages of low radiation and clothing-penetrable, terahertz imaging technology has been widely used for the detection of concealed weapons or other contraband carried on personnel at airports and other secure locations. This paper aims to detect these concealed items with deep learning method for its well detection performance and real-time detection speed. Based on the analysis of the characteristics of terahertz images, an effective detection system is proposed in this paper. First, a lots of terahertz images are collected and labeled as the standard data format. Secondly, this paper establishes the terahertz classification dataset and proposes a classification method based on transfer learning. Then considering the special distribution of terahertz image, an improved faster region-based convolutional neural network (Faster R-CNN) method based on threshold segmentation is proposed for detecting human body and other objects independently. Finally, experimental results demonstrate the effectiveness and efficiency of the proposed method for terahertz image detection. Full article
(This article belongs to the Special Issue Automatic Target Recognition of High Resolution SAR/ISAR Images)
Figures

Figure 1

Back to Top