-
Sensors (Basel, Switzerland) Jun 2024The high-altitude real-time inspection of unmanned aerial vehicles (UAVs) has always been a very challenging task. Because high-altitude inspections are susceptible to...
The high-altitude real-time inspection of unmanned aerial vehicles (UAVs) has always been a very challenging task. Because high-altitude inspections are susceptible to interference from different weather conditions, interference from communication signals and a larger field of view result in a smaller object area to be identified. We adopted a method that combines a UAV system scheduling platform with artificial intelligence object detection to implement the UAV automatic inspection technology. We trained the YOLOv5s model on five different categories of vehicle data sets, in which mAP50 and mAP50-95 reached 93.2% and 71.7%, respectively. The YOLOv5s model size is only 13.76 MB, and the detection speed of a single inspection photo reaches 11.26 ms. It is a relatively lightweight model and is suitable for deployment on edge devices for real-time detection. In the original DeepStream framework, we set up the http communication protocol to start quickly to enable different users to call and use it at the same time. In addition, asynchronous sending of alarm frame interception function was added and the auxiliary services were set up to quickly resume video streaming after interruption. We deployed the trained YOLOv5s model on the improved DeepStream framework to implement automatic UAV inspection.
PubMed: 38931645
DOI: 10.3390/s24123862 -
Sensors (Basel, Switzerland) Jun 2024In recent years, sensory polymers have evolved significantly, emerging as versatile and cost-effective materials valued for their flexibility and lightweight nature.... (Review)
Review
In recent years, sensory polymers have evolved significantly, emerging as versatile and cost-effective materials valued for their flexibility and lightweight nature. These polymers have transformed into sophisticated, active systems capable of precise detection and interaction, driving innovation across various domains, including smart materials, biomedical diagnostics, environmental monitoring, and industrial safety. Their unique responsiveness to specific stimuli has sparked considerable interest and exploration in numerous applications. However, along with these advancements, notable challenges need to be addressed. Issues such as wearable technology integration, biocompatibility, selectivity and sensitivity enhancement, stability and reliability improvement, signal processing optimization, IoT integration, and data analysis pose significant hurdles. When considered collectively, these challenges present formidable barriers to the commercial viability of sensory polymer-based technologies. Addressing these challenges requires a multifaceted approach encompassing technological innovation, regulatory compliance, market analysis, and commercialization strategies. Successfully navigating these complexities is essential for unlocking the full potential of sensory polymers and ensuring their widespread adoption and impact across industries, while also providing guidance to the scientific community to focus their research on the challenges of polymeric sensors and to understand the future prospects where research efforts need to be directed.
PubMed: 38931634
DOI: 10.3390/s24123852 -
Sensors (Basel, Switzerland) Jun 2024In this study, we enhanced odometry performance by integrating vision sensors with LiDAR sensors, which exhibit contrasting characteristics. Vision sensors provide...
In this study, we enhanced odometry performance by integrating vision sensors with LiDAR sensors, which exhibit contrasting characteristics. Vision sensors provide extensive environmental information but are limited in precise distance measurement, whereas LiDAR offers high accuracy in distance metrics but lacks detailed environmental data. By utilizing data from vision sensors, this research compensates for the inadequate descriptors of LiDAR sensors, thereby improving LiDAR feature matching performance. Traditional fusion methods, which rely on extracting depth from image features, depend heavily on vision sensors and are vulnerable under challenging conditions such as rain, darkness, or light reflection. Utilizing vision sensors as primary sensors under such conditions can lead to significant mapping errors and, in the worst cases, system divergence. Conversely, our approach uses LiDAR as the primary sensor, mitigating the shortcomings of previous methods and enabling vision sensors to support LiDAR-based mapping. This maintains LiDAR Odometry performance even in environments where vision sensors are compromised, thus enhancing performance with the support of vision sensors. We adopted five prominent algorithms from the latest LiDAR SLAM open-source projects and conducted experiments on the KITTI odometry dataset. This research proposes a novel approach by integrating a vision support module into the top three LiDAR SLAM methods, thereby improving performance. By making the source code of VA-LOAM publicly available, this work enhances the accessibility of the technology, fostering reproducibility and transparency within the research community.
PubMed: 38931615
DOI: 10.3390/s24123831 -
Sensors (Basel, Switzerland) Jun 2024The railway fastener, as a crucial component of railway tracks, directly influences the safety and stability of a railway system. However, in practical operation,...
The railway fastener, as a crucial component of railway tracks, directly influences the safety and stability of a railway system. However, in practical operation, fasteners are often in low-light conditions, such as at nighttime or within tunnels, posing significant challenges to defect detection equipment and limiting its effectiveness in real-world scenarios. To address this issue, this study proposes an unsupervised low-light image enhancement algorithm, CES-GAN, which achieves the model's generalization and adaptability under different environmental conditions. The CES-GAN network architecture adopts a U-Net model with five layers of downsampling and upsampling structures as the generator, incorporating both global and local discriminators to help the generator to preserve image details and textures during the reconstruction process, thus enhancing the realism and intricacy of the enhanced images. The combination of the feature-consistency loss, contrastive learning loss, and illumination loss functions in the generator structure, along with the discriminator loss function in the discriminator structure, collectively promotes the clarity, realism, and illumination consistency of the images, thereby improving the quality and usability of low-light images. Through the CES-GAN algorithm, this study provides reliable visual support for railway construction sites and ensures the stable operation and accurate operation of fastener identification equipment in complex environments.
PubMed: 38931578
DOI: 10.3390/s24123794 -
Sensors (Basel, Switzerland) Jun 2024In an era marked by escalating concerns about digital security, biometric identification methods have gained paramount importance. Despite the increasing adoption of...
In an era marked by escalating concerns about digital security, biometric identification methods have gained paramount importance. Despite the increasing adoption of biometric techniques, keystroke dynamics analysis remains a less explored yet promising avenue. This study highlights the untapped potential of keystroke dynamics, emphasizing its non-intrusive nature and distinctiveness. While keystroke dynamics analysis has not achieved widespread usage, ongoing research indicates its viability as a reliable biometric identifier. This research builds upon the existing foundation by proposing an innovative deep-learning methodology for keystroke dynamics-based identification. Leveraging open research datasets, our approach surpasses previously reported results, showcasing the effectiveness of deep learning in extracting intricate patterns from typing behaviors. This article contributes to the advancement of biometric identification, shedding light on the untapped potential of keystroke dynamics and demonstrating the efficacy of deep learning in enhancing the precision and reliability of identification systems.
Topics: Deep Learning; Humans; Biometric Identification; Algorithms; Biometry; Handwriting
PubMed: 38931547
DOI: 10.3390/s24123763 -
Sensors (Basel, Switzerland) Jun 2024This paper addresses the problem of removing 3D effects as one of the most challenging problems related to 2D electrical resistivity tomography (ERT) monitoring of...
This paper addresses the problem of removing 3D effects as one of the most challenging problems related to 2D electrical resistivity tomography (ERT) monitoring of embankment structures. When processing 2D ERT monitoring data measured along linear profiles, it is fundamental to estimate and correct the distortions introduced by the non-uniform 3D geometry of the embankment. Here, I adopt an iterative 3D correction plus 2D inversion procedure to correct the 3D effects and I test the validity of the proposed algorithm using both synthetic and real data. The modelled embankment is inspired by a critical section of the Parma River levee in Colorno (PR), Italy, where a permanent ERT monitoring system has been in operation since November 2018. For each model of the embankment, reference synthetic data were produced in Res2dmod and Res3dmod for the corresponding 2D and 3D models. Using the reference synthetic data, reference 3D effects were calculated to be compared with 3D effects estimated by the proposed algorithm at each iteration. The results of the synthetic tests showed that even in the absence of a priori information, the proposed algorithm for correcting 3D effects converges rapidly to ideal corrections. Having validated the proposed algorithm through synthetic tests, the method was applied to the ERT monitoring data in the study site to remove 3D effects. Two real datasets from the study site, taken after dry and rainy periods, are discussed here. The results showed that 3D effects cause about ±50% changes in the inverted resistivity images for both periods. This is a critical artifact considering that the final objective of ERT monitoring data for such studies is to produce water content maps to be integrated in alarm systems for hydrogeological risk mitigation. The proposed algorithm to remove 3D effects is thus a rapid and validated solution to satisfy near-real-time data processing and to produce reliable results.
PubMed: 38931543
DOI: 10.3390/s24123759 -
Sensors (Basel, Switzerland) Jun 2024It is common to see cases in which, when performing tasks in close vision in front of a digital screen, the posture or position of the head is not adequate, especially...
It is common to see cases in which, when performing tasks in close vision in front of a digital screen, the posture or position of the head is not adequate, especially in young people; it is essential to have a correct posture of the head to avoid visual, muscular, or joint problems. Most of the current systems to control head inclination require an external part attached to the subject's head. The aim of this study is the validation of a procedure that, through a detection algorithm and eye tracking, can control the correct position of the head in real time when subjects are in front of a digital device. The system only needs a digital device with a CCD receiver and downloadable software through which we can detect the inclination of the head, indicating if a bad posture is adopted due to a visual problem or simply inadequate visual-postural habits, alerting us to the postural anomaly to correct it.The system was evaluated in subjects with disparate interpupillary distances, at different working distances in front of the digital device, and at each distance, different tilt angles were evaluated. The system evaluated favorably in different lighting environments, correctly detecting the subjects' pupils. The results showed that for most of the variables, particularly good absolute and relative reliability values were found when measuring head tilt with lower accuracy than most of the existing systems. The evaluated results have been positive, making it a considerably inexpensive and easily affordable system for all users. It is the first application capable of measuring the head tilt of the subject at their working or reading distance in real time by tracking their eyes.
Topics: Humans; Posture; Algorithms; Head; Artificial Intelligence; Software; Male; Female; Adult
PubMed: 38931537
DOI: 10.3390/s24123756 -
Sensors (Basel, Switzerland) Jun 2024Optical tracking of head pose via fiducial markers has been proven to enable effective correction of motion artifacts in the brain during magnetic resonance imaging but...
Optical tracking of head pose via fiducial markers has been proven to enable effective correction of motion artifacts in the brain during magnetic resonance imaging but remains difficult to implement in the clinic due to lengthy calibration and set up times. Advances in deep learning for markerless head pose estimation have yet to be applied to this problem because of the sub-millimetre spatial resolution required for motion correction. In the present work, two optical tracking systems are described for the development and training of a neural network: one marker-based system (a testing platform for measuring ground truth head pose) with high tracking fidelity to act as the training labels, and one markerless deep-learning-based system using images of the markerless head as input to the network. The markerless system has the potential to overcome issues of marker occlusion, insufficient rigid attachment of the marker, lengthy calibration times, and unequal performance across degrees of freedom (DOF), all of which hamper the adoption of marker-based solutions in the clinic. Detail is provided on the development of a custom moiré-enhanced fiducial marker for use as ground truth and on the calibration procedure for both optical tracking systems. Additionally, the development of a synthetic head pose dataset is described for the proof of concept and initial pre-training of a simple convolutional neural network. Results indicate that the ground truth system has been sufficiently calibrated and can track head pose with an error of <1 mm and <1°. Tracking data of a healthy, adult participant are shown. Pre-training results show that the average root-mean-squared error across the 6 DOF is 0.13 and 0.36 (mm or degrees) on a head model included and excluded from the training dataset, respectively. Overall, this work indicates excellent feasibility of the deep-learning-based approach and will enable future work in training and testing on a real dataset in the MRI environment.
Topics: Humans; Magnetic Resonance Imaging; Head; Head Movements; Neural Networks, Computer; Fiducial Markers; Calibration; Image Processing, Computer-Assisted; Deep Learning; Brain; Artifacts
PubMed: 38931521
DOI: 10.3390/s24123737 -
Sensors (Basel, Switzerland) Jun 2024A complete framework of predicting the attributes of sea clutter under different operational conditions, specified by wind speed, wind direction, grazing angle, and...
A complete framework of predicting the attributes of sea clutter under different operational conditions, specified by wind speed, wind direction, grazing angle, and polarization, is proposed for the first time. This framework is composed of empirical spectra to characterize sea-surface profiles under different wind speeds, the Monte Carlo method to generate realizations of sea-surface profiles, the physical-optics method to compute the normalized radar cross-sections (NRCSs) from individual sea-surface realizations, and regression of NRCS data (sea clutter) with an empirical probability density function (PDF) characterized by a few statistical parameters. JONSWAP and Hwang ocean-wave spectra are adopted to generate realizations of sea-surface profiles at low and high wind speeds, respectively. The probability density functions of NRCSs are regressed with K and Weibull distributions, each characterized by two parameters. The probability density functions in the outlier regions of weak and strong signals are regressed with a power-law distribution, each characterized by an index. The statistical parameters and power-law indices of the K and Weibull distributions are derived for the first time under different operational conditions. The study reveals succinct information of sea clutter that can be used to improve the radar performance in a wide variety of complicated ocean environments. The proposed framework can be used as a reference or guidelines for designing future measurement tasks to enhance the existing empirical models on ocean-wave spectra, normalized radar cross-sections, and so on.
PubMed: 38931504
DOI: 10.3390/s24123720 -
Sensors (Basel, Switzerland) Jun 2024Space manipulators are expected to perform more challenging missions in on-orbit service (OOS) systems, but there are some unique characteristics that are not found on...
Space manipulators are expected to perform more challenging missions in on-orbit service (OOS) systems, but there are some unique characteristics that are not found on ground-based robots, such as dynamic coupling between space bases and manipulators, limited fuel supply, and working with unfixed bases. This paper focuses on trajectory-tracking control and internal force control for free-floating close-chain manipulators. First, the kinematics and dynamics of free-floating close-chain manipulators are given using the momentum conservation and spatial operator algebra (SOA) methodologies, respectively. Furthermore, an adaptive fuzzy integral sliding mode controller (AFISMC) based on time delay estimation (TDE) was designed for trajectory-tracking control, and a proportional-integral (PI) control strategy was adopted for internal force control. The global asymptotic stability of the proposed controller was proven by using the Lyapunov methodology. Three cases were conducted to verify the efficiency of the controller by using numerical simulations on two six-link manipulators with a free-floating base. The controller presents the desired tracking capability.
PubMed: 38931503
DOI: 10.3390/s24123718