Search

The electrocardiogram (ECG) signal describes the heart's electrical activity, allowing it to detect several health conditions, including cardiac system abnormalities and dysfunctions. Nowadays, most patient medical records are still paper-based, especially those made in past decades. The importance of collecting digitized ECGs is twofold: firstly, all medical applications can be easily implemented with an engineering approach if the ECGs are treated as signals; secondly, paper ECGs can deteriorate over time, therefore a correct evaluation of the patient's clinical evolution is not always guaranteed. The goal of this paper is the realization of an automatic conversion algorithm from paper-based ECGs (images) to digital ECG signals. The algorithm involves a digitization process tested on an image set of 16 subjects, also with pathologies. The quantitative analysis of the digitization method is carried out by evaluating the repeatability and reproducibility of the algorithm. The digitization accuracy is evaluated both on the entire signal and on six ECG time parameters (R-R peak distance, QRS complex duration, QT interval, PQ interval, P-wave duration, and heart rate). Results demonstrate the algorithm efficiency has an average Pearson correlation coefficient of 0.94 and measurement errors of the ECG time parameters are always less than 1 mm. Due to the promising experimental results, the algorithm could be embedded into a graphical interface, becoming a measurement and collection tool for cardiologists. [ABSTRACT FROM AUTHOR]

Millimeter-wave radar-based identification technology has a wide range of applications in persistent identity verification, covering areas such as security production, healthcare, and personalized smart consumption systems. It has received extensive attention from the academic community due to its advantages of being non-invasive, environmentally insensitive and privacy-preserving. Existing identification algorithms mainly rely on a single signal, such as breathing or heartbeat. The reliability and accuracy of these algorithms are limited due to the high similarity of breathing patterns and the low signal-to-noise ratio of heartbeat signals. To address the above issues, this paper proposes an algorithm for multimodal fusion for identity recognition. This algorithm extracts and fuses features derived from phase signals, respiratory signals, and heartbeat signals for identity recognition purposes. The spatial features of signals with different modes are first extracted by the residual network (ResNet), after which these features are fused with a spatial-channel attention fusion module. On this basis, the temporal features are further extracted with a time series-based self-attention mechanism. Finally, the feature vectors of the user's vital sign modality are obtained to perform identity recognition. This method makes full use of the correlation and complementarity between different modal signals to improve the accuracy and reliability of identification. Simulation experiments show that the algorithm identity recognition proposed in this paper achieves an accuracy of 94.26% on a 20-subject self-test dataset, which is much higher than that of the traditional algorithm, which is about 85%. [ABSTRACT FROM AUTHOR]

As an indispensable part of the vehicle environment perception task, road traffic marking detection plays a vital role in correctly understanding the current traffic situation. However, the existing traffic marking detection algorithms still have some limitations. Taking lane detection as an example, the current detection methods mainly focus on the location information detection of lane lines, and they only judge the overall attribute of each detected lane line instance, thus lacking more fine-grained dynamic detection of lane line attributes. In order to meet the needs of intelligent vehicles for the dynamic attribute detection of lane lines and more perfect road environment information in urban road environment, this paper constructs a fine-grained attribute detection method for lane lines, which uses pixel-level attribute sequence points to describe the complete attribute distribution of lane lines and then matches the detection results of the lane lines. Realizing the attribute judgment of different segment positions of lane instances is called the fine-grained attribute detection of lane lines (Lane-FGA). In addition, in view of the lack of annotation information in the current open-source lane data set, this paper constructs a lane data set with both lane instance information and fine-grained attribute information by combining manual annotation and intelligent annotation. At the same time, a cyclic iterative attribute inference algorithm is designed to solve the difficult problem of lane attribute labeling in areas without visual cues such as occlusion and damage. In the end, the average accuracy of the proposed algorithm reaches 97% on various types of lane attribute detection. [ABSTRACT FROM AUTHOR]

The efficient and accurate identification of traffic signs is crucial to the safety and reliability of active driving assistance and driverless vehicles. However, the accurate detection of traffic signs under extreme cases remains challenging. Aiming at the problems of missing detection and false detection in traffic sign recognition in fog traffic scenes, this paper proposes a recognition algorithm for traffic signs based on pix2pixHD+YOLOv5-T. Firstly, the defogging model is generated by training the pix2pixHD network to meet the advanced visual task. Secondly, in order to better match the defogging algorithm with the target detection algorithm, the algorithm YOLOv5-Transformer is proposed by introducing a transformer module into the backbone of YOLOv5. Finally, the defogging algorithm pix2pixHD is combined with the improved YOLOv5 detection algorithm to complete the recognition of traffic signs in foggy environments. Comparative experiments proved that the traffic sign recognition algorithm proposed in this paper can effectively reduce the impact of a foggy environment on traffic sign recognition. Compared with the YOLOv5-T and YOLOv5 algorithms in moderate fog environments, the overall improvement of this algorithm is achieved. The precision of traffic sign recognition of the algorithm in the fog traffic scene reached 78.5%, the recall rate was 72.2%, and mAP@0.5 was 82.8%. [ABSTRACT FROM AUTHOR]

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds. [ABSTRACT FROM AUTHOR]

The ability to make informed decisions in complex scenarios is crucial for intelligent automotive systems. Traditional expert rules and other methods often fall short in complex contexts. Recently, reinforcement learning has garnered significant attention due to its superior decision-making capabilities. However, there exists the phenomenon of inaccurate target network estimation, which limits its decision-making ability in complex scenarios. This paper mainly focuses on the study of the underestimation phenomenon, and proposes an end-to-end autonomous driving decision-making method based on an improved TD3 algorithm. This method employs a forward camera to capture data. By introducing a new critic network to form a triple-critic structure and combining it with the target maximization operation, the underestimation problem in the TD3 algorithm is solved. Subsequently, the multi-timestep averaging method is used to address the policy instability caused by the new single critic. In addition, this paper uses Carla platform to construct multi-vehicle unprotected left turn and congested lane-center driving scenarios and verifies the algorithm. The results demonstrate that our method surpasses baseline DDPG and TD3 algorithms in aspects such as convergence speed, estimation accuracy, and policy stability. [ABSTRACT FROM AUTHOR]

In autonomous driving, the fusion of multiple sensors is considered essential to improve the accuracy and safety of 3D object detection. Currently, a fusion scheme combining low-cost cameras with highly robust radars can counteract the performance degradation caused by harsh environments. In this paper, we propose the IRBEVF-Q model, which mainly consists of BEV (Bird's Eye View) fusion coding module and an object decoder module.The BEV fusion coding module solves the problem of unified representation of different modal information by fusing the image and radar features through 3D spatial reference points as a medium. The query in the object decoder, as a core component, plays an important role in detection. In this paper, Heat Map-Guided Query Initialization (HGQI) and Dynamic Position Encoding (DPE) are proposed in query construction to increase the a priori information of the query. The Auxiliary Noise Query (ANQ) then helps to stabilize the matching. The experimental results demonstrate that the proposed fusion model IRBEVF-Q achieves an NDS of 0.575 and a mAP of 0.476 on the nuScenes test set. Compared to recent state-of-the-art methods, our model shows significant advantages, thus indicating that our approach contributes to improving detection accuracy. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based object detection methods are widely used in traffic detection due to their high flexibility and extensive coverage. In recent years, with the increasing complexity of the urban road environment, UAV object detection algorithms based on deep learning have gradually become a research hotspot. However, how to further improve algorithmic efficiency in response to the numerous and rapidly changing road elements, and thus achieve high-speed and accurate road object detection, remains a challenging issue. Given this context, this paper proposes the high-efficiency multi-object detection algorithm for UAVs (HeMoDU). HeMoDU reconstructs a state-of-the-art, deep-learning-based object detection model and optimizes several aspects to improve computational efficiency and detection accuracy. To validate the performance of HeMoDU in urban road environments, this paper uses the public urban road datasets VisDrone2019 and UA-DETRAC for evaluation. The experimental results show that the HeMoDU model effectively improves the speed and accuracy of UAV object detection. [ABSTRACT FROM AUTHOR]

In the work reported in this paper, a lost-in-space star pattern identification algorithm for agile spacecraft was studied. Generally, the operation of a star tracker is known to exhibit serious degradation or even failure during fast attitude maneuvers. While tracking methods are widely used solutions to handle the dynamic conditions, they require prior information about the initial orientation. Therefore, the tracking methods may not be adequate for autonomy of attitude and control systems. In this paper a novel autonomous identification method for dynamic conditions is proposed. Additional constraints are taken into account that can significantly decrease the number of stars imaged and the centroid accuracy. A strategy combining two existing classes for star pattern identification is proposed. The new approach is intended to provide a unique way to determine the identity of stars that promises robustness against noise and rapid identification. Moreover, representative algorithms implemented in actual space applications were utilized as counterparts to analyze the performance of the proposed method in various scenarios. Numerical simulations show that the proposed method is not only highly robust against positional noise and false stars, but also guarantees fast run-time, which is appropriate for high-speed applications. [ABSTRACT FROM AUTHOR]

Train wheels are crucial components for ensuring the safety of trains. The accurate and fast identification of wheel tread defects is necessary for the timely maintenance of wheels, which is essential for achieving the premise of conditional repair. Image-based detection methods are commonly used for detecting tread defects, but they still have issues with the misdetection of water stains and the leaking of small defects. In this paper, we address the challenges posed by the detection of wheel tread defects by proposing improvements to the YOLOv8 model. Firstly, the impact of water stains on tread defect detection is avoided by optimising the structure of the detection layer. Secondly, an improved SPPCSPC module is introduced to enhance the detection of small targets. Finally, the SIoU loss function is used to accelerate the convergence speed of the network, which ensures defect recognition accuracy with high operational efficiency. Validation was performed on the constructed tread defect dataset. The results demonstrate that the enhanced YOLOv8 model in this paper outperforms the original network and significantly improves the tread defect detection indexes. The average precision, accuracy, and recall reached 96.95%, 96.30%, and 95.31%. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to the Internet and enjoying the facilities of smart services. IoT marketing is experiencing an impressive 16.7% growth rate and is a nearly USD 300.3 billion market. These eye-catching figures have made it an attractive playground for cybercriminals. IoT devices are built using resource-constrained architecture to offer compact sizes and competitive prices. As a result, integrating sophisticated cybersecurity features is beyond the scope of the computational capabilities of IoT. All of these have contributed to a surge in IoT intrusion. This paper presents an LSTM-based Intrusion Detection System (IDS) with a Dynamic Access Control (DAC) algorithm that not only detects but also defends against intrusion. This novel approach has achieved an impressive 97.16% validation accuracy. Unlike most of the IDSs, the model of the proposed IDS has been selected and optimized through mathematical analysis. Additionally, it boasts the ability to identify a wider range of threats (14 to be exact) compared to other IDS solutions, translating to enhanced security. Furthermore, it has been fine-tuned to strike a balance between accurately flagging threats and minimizing false alarms. Its impressive performance metrics (precision, recall, and F1 score all hovering around 97%) showcase the potential of this innovative IDS to elevate IoT security. The proposed IDS boasts an impressive detection rate, exceeding 98%. This high accuracy instills confidence in its reliability. Furthermore, its lightning-fast response time, averaging under 1.2 s, positions it among the fastest intrusion detection systems available. [ABSTRACT FROM AUTHOR]

An autonomous place recognition system is essential for scenarios where GPS is useless, such as underground tunnels. However, it is difficult to use existing algorithms to fully utilize the small number of effective features in underground tunnel data, and recognition accuracy is difficult to guarantee. In order to solve this challenge, an efficient point cloud position recognition algorithm, named Dual-Attention Transformer Network (DAT-Net), is proposed in this paper. The algorithm firstly adopts the farthest point downsampling module to eliminate the invalid redundant points in the point cloud data and retain the basic shape of the point cloud, which reduces the size of the point cloud and, at the same time, reduces the influence of the invalid point cloud on the data analysis. After that, this paper proposes the dual-attention Transformer module to facilitate local information exchange by utilizing the multi-head self-attention mechanism. It extracts local descriptors and integrates highly discriminative global descriptors based on global context with the help of a feature fusion layer to obtain a more accurate and robust global feature representation. Experimental results show that the method proposed in this paper achieves an average F 1 score of 0.841 on the SubT-Tunnel dataset and outperforms many existing state-of-the-art algorithms in recognition accuracy and robustness tests. [ABSTRACT FROM AUTHOR]

Multitarget positioning technology, such as FMCW millimeter-wave radar, has broad application prospects in autonomous driving and related mobile scenarios. However, it is difficult for existing correlation algorithms to balance high resolution and low complexity, and it is also difficult to ensure the robustness of the positioning algorithm using an aging antenna. This paper proposes a super-resolution and low-complexity positioning algorithm based on the orthogonal matching pursuit algorithm that can achieve more accurate distance and angle estimation for multiple objects in a low-SNR environment. The algorithm proposed in this paper improves the resolving power by two and one orders of magnitude, respectively, compared to the classical FFT and MUSIC algorithms in the same signal-to-noise environment, and the complexity of the algorithm can be reduced by about 25–30%, with the same resolving power as the OMP algorithm. Based on the positioning algorithm proposed in our paper, we use the PSO algorithm to optimize the arrangement of an aging antenna array so that its angle estimation accuracy is equivalent to that observed when the antenna is intact, improving the positioning algorithm's robustness. This paper also further realizes the use of the proposed algorithm and a single-frame intermediate frequency signal to estimate the position angle information of the object and obtain its motion trajectory and velocity, verifying the proposed algorithm's estimation ability when it comes to these qualities in a moving scene. Furthermore, this paper designs and carries out simulations and experiments. The experimental results verify that the positioning algorithm proposed in this paper can achieve accuracy, robustness, and real-time performance in autonomous driving scenarios. [ABSTRACT FROM AUTHOR]

There are six possible solutions for the surface normal vectors obtained from polarization information during 3D reconstruction. To resolve the ambiguity of surface normal vectors, scholars have introduced additional information, such as shading information. However, this makes the 3D reconstruction task too burdensome. Therefore, in order to make the 3D reconstruction more generally applicable, this paper proposes a complete framework to reconstruct the surface of an object using only polarized images. To solve the ambiguity problem of surface normal vectors, a jump-compensated U-shaped generative adversarial network (RU-Gan) based on jump compensation is designed for fusing six surface normal vectors. Among them, jump compensation is proposed in the encoder and decoder parts, and the content loss function is reconstructed, among other approaches. For the problem that the reflective region of the original image will cause the estimated normal vector to deviate from the true normal vector, a specular reflection model is proposed to optimize the dataset, thus reducing the reflective region. Experiments show that the estimated normal vector obtained in this paper improves the accuracy by about 20° compared with the previous conventional work, and improves the accuracy by about 1.5° compared with the recent neural network model, which means the neural network model proposed in this paper is more suitable for the normal vector estimation task. Furthermore, the object surface reconstruction framework proposed in this paper has the characteristics of simple implementation conditions and high accuracy of reconstructed texture. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of detecting unknown or unforeseen obstacles in railway track transportation, proposing an innovative detection strategy that integrates an incremental clustering algorithm with lightweight segmentation techniques. In the detection phase, the paper innovatively employs the incremental clustering algorithm as a core method, combined with dilation and erosion theories, to expand the boundaries of point cloud clusters, merging adjacent point cloud elements into unified clusters. This method effectively identifies and connects spatially adjacent point cloud clusters while efficiently eliminating noise from target object point clouds, thereby achieving more precise recognition of unknown obstacles on the track. Furthermore, the effective integration of this algorithm with lightweight shared convolutional semantic segmentation algorithms enables accurate localization of obstacles. Experimental results using two combined public datasets demonstrate that the obstacle detection average recall rate of the proposed method reaches 90.3%, significantly enhancing system reliability. These findings indicate that the proposed detection strategy effectively improves the accuracy and real-time performance of obstacle recognition, thereby presenting important practical application value for ensuring the safe operation of railway tracks. [ABSTRACT FROM AUTHOR]

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

Autonomous vehicles are rapidly advancing and have the potential to revolutionize transportation in the future. This paper primarily focuses on vehicle motion trajectory planning algorithms, examining the methods for estimating collision risks based on sensed environmental information and approaches for achieving user-aligned trajectory planning results. It investigates the different categories of planning algorithms within the scope of local trajectory planning applications for autonomous driving, discussing and differentiating their properties in detail through a review of the recent studies. The risk estimation methods are classified and introduced based on their descriptions of the sensed collision risks in traffic environments and their integration with trajectory planning algorithms. Additionally, various user experience-oriented methods, which utilize human data to enhance the trajectory planning performance and generate human-like trajectories, are explored. The paper provides comparative analyses of these algorithms and methods from different perspectives, revealing the interconnections between these topics. The current challenges and future prospects of the trajectory planning tasks in autonomous vehicles are also discussed. [ABSTRACT FROM AUTHOR]

We live in the era of large data analysis, where processing vast datasets has become essential for uncovering valuable insights across various domains of our lives. Machine learning (ML) algorithms offer powerful tools for processing and analyzing this abundance of information. However, the considerable time and computational resources needed for training ML models pose significant challenges, especially within cascade schemes, due to the iterative nature of training algorithms, the complexity of feature extraction and transformation processes, and the large sizes of the datasets involved. This paper proposes a modification to the existing ML-based cascade scheme for analyzing large biomedical datasets by incorporating principal component analysis (PCA) at each level of the cascade. We selected the number of principal components to replace the initial inputs so that it ensured 95% variance retention. Furthermore, we enhanced the training and application algorithms and demonstrated the effectiveness of the modified cascade scheme through comparative analysis, which showcased a significant reduction in training time while improving the generalization properties of the method and the accuracy of the large data analysis. The improved enhanced generalization properties of the scheme stemmed from the reduction in nonsignificant independent attributes in the dataset, which further enhanced its performance in intelligent large data analysis. [ABSTRACT FROM AUTHOR]

With the addition of Bluetooth AOA/AOD direction-finding capabilities in the Bluetooth 5.1 protocol and the introduction of antenna array technology into the Bluetooth platform to further enhance positioning accuracy, Bluetooth has gradually become a research hotspot in the field of indoor positioning due to its standard protocol specifications, rich application ecosystem, and outstanding advantages such as low power consumption and low cost compared to other indoor positioning technologies. However, current indoor positioning based on Bluetooth AOA/AOD suffers from overly simplistic core algorithm implementations. When facing different application scenarios, the standalone AOA or AOD algorithms exhibit weak applicability, and they also encounter challenges such as poor positioning accuracy, insufficient real-time performance, and significant effects of multipath propagation. These existing problems and deficiencies render Bluetooth lacking an efficient implementation solution for indoor positioning. Therefore, this paper proposes a study on Bluetooth AOA and AOD indoor positioning algorithms. Through an analysis of the principles of Bluetooth's newly added direction-finding functionality and combined with research on array signal DOA estimation algorithms, the paper ultimately integrates the least squares algorithm to optimize positioning errors in terms of accuracy and incorporates an anti-multipath interference algorithm to address the impacts of multipath effects in different scenarios. Experimental testing demonstrates that the indoor positioning algorithms applicable to Bluetooth AOA and AOD can effectively mitigate accuracy errors and overcome multipath effects, exhibiting strong applicability and significant improvements in real-time performance. [ABSTRACT FROM AUTHOR]

This paper explores the generalization ability of defogging algorithms on RICE (A Remote Sensing Image Dataset for Cloud Removal) remotely sensed images. RICE is a dataset of remotely sensed images used for removing clouds, allowing the researcher to better evaluate the performance of defogging algorithms for cloud removal from remotely sensed images. In this paper, four classical defogging algorithms, including AOD-Net, FFA-Net, dark channel prior, and DehazeFormer, are selected and applied to the task of de-cloud in RICE remote sensing images. The performance of these algorithms on the RICE dataset is analyzed by comparing the experimental results, and their differences, advantages, and disadvantages in dealing with de-clouded remote sensing images are explored. The experimental results show that the four defogging algorithms are capable of performing well on uniform thin cloud images, but there is a color distortion and the performance is weak when it comes to inhomogeneous clouds as well as thick clouds. So, the generalization ability of the algorithms is weak when the defogging algorithms are applied to the problem of cloud removal. Finally, this paper proposes improvement ideas for the de-cloud problem of RICE remote sensing images and looks forward to possible future research directions. [ABSTRACT FROM AUTHOR]

In recent years, the incidence of cardiac arrhythmias has been on the rise because of changes in lifestyle and the aging population. Electrocardiograms (ECGs) are widely used for the automated diagnosis of cardiac arrhythmias. However, existing models possess poor noise robustness and complex structures, limiting their effectiveness. To solve these problems, this paper proposes an arrhythmia recognition system with excellent anti-noise performance: a convolutionally optimized broad learning system (COBLS). In the proposed COBLS method, the signal is convolved with blind source separation using a signal analysis method based on high-order-statistic independent component analysis (ICA). The constructed feature matrix is further feature-extracted and dimensionally reduced using principal component analysis (PCA), which reveals the essence of the signal. The linear feature correlation between the data can be effectively reduced, and redundant attributes can be eliminated to obtain a low-dimensional feature matrix that retains the essential features of the classification model. Then, arrhythmia recognition is realized by combining this matrix with the broad learning system (BLS). Subsequently, the model was evaluated using the MIT-BIH arrhythmia database and the MIT-BIH noise stress test database. The outcomes of the experiments demonstrate exceptional performance, with impressive achievements in terms of the overall accuracy, overall precision, overall sensitivity, and overall F1-score. Specifically, the results indicate outstanding performance, with figures reaching 99.11% for the overall accuracy, 96.95% for the overall precision, 89.71% for the overall sensitivity, and 93.01% for the overall F1-score across all four classification experiments. The model proposed in this paper shows excellent performance, with 24 dB, 18 dB, and 12 dB signal-to-noise ratios. [ABSTRACT FROM AUTHOR]

It is difficult to visually detect internal defects in a large transformer with a metal closure. For convenient internal inspection, a micro-robot was adopted, and an inspection method based on an image-enhancement algorithm and an improved deep-learning network was proposed in this paper. Considering the dim environment inside the transformer and the problems of irregular imaging distance and fluctuating supplementary light conditions during image acquisition with the internal-inspection robot, an improved MSRCR algorithm for image enhancement was proposed. It could analyze the local contrast of the image and enhance the details on multiple scales. At the same time, a white-balance algorithm was introduced to enhance the contrast and brightness and solve the problems of overexposure and color distortion. To improve the target recognition performance of complex carbon-trace defects, the SimAM mechanism was incorporated into the Backbone network of the YOLOv8 model to enhance the extraction of carbon-trace features. Meanwhile, the DyHead dynamic detection Head framework was constructed at the output of the YOLOv8 model to improve the perception of local carbon traces with different sizes. To improve the defect target recognition speed of the transformer-inspection robot, a pruning operation was carried out on the YOLOv8 model to remove redundant parameters, realize model lightness, and improve detection efficiency. To verify the effectiveness of the improved algorithm, the detection model was trained and validated with the carbon-trace dataset. The results showed that the MSH-YOLOv8 algorithm achieved an accuracy of 91.80%, which was 3.4 percentage points higher compared to the original YOLOv8 algorithm, and had a significant advantage over other mainstream target-detection algorithms. Meanwhile, the FPS of the proposed algorithm was up to 99.2, indicating that the model computation and model complexity were successfully reduced, which meets the requirements for engineering applications of the transformer internal-inspection robot. [ABSTRACT FROM AUTHOR]

At present, PPF-based point cloud recognition algorithms can perform better matching than competitors and be verified in the case of severe occlusion and stacking. However, including certain superfluous feature point pairs in the global model description would significantly lower the algorithm's efficiency. As a result, this paper delves into the Point Pair Feature (PPF) algorithm and proposes a 6D pose estimation method based on Keypoint Pair Feature (K-PPF) voting. The K-PPF algorithm is based on the PPF algorithm and proposes an improved algorithm for the sampling point part. The sample points are retrieved using a combination of curvature-adaptive and grid ISS, and the angle-adaptive judgment is performed on the sampling points to extract the keypoints, therefore improving the point pair feature difference and matching accuracy. To verify the effectiveness of the method, we analyze the experimental results in scenes with different occlusion and complexity levels under the evaluation metrics of ADD-S, Recall, Precision, and Overlap rate. The results show that the algorithm in this paper reduces redundant point pairs and improves recognition efficiency and robustness compared with PPF. Compared with FPFH, CSHOT, SHOT and SI algorithms, this paper improves the recall rate by more than 12.5%. [ABSTRACT FROM AUTHOR]

Oncology has emerged as a crucial field of study in the domain of medicine. Computed tomography has gained widespread adoption as a radiological modality for the identification and characterisation of pathologies, particularly in oncology, enabling precise identification of affected organs and tissues. However, achieving accurate liver segmentation in computed tomography scans remains a challenge due to the presence of artefacts and the varying densities of soft tissues and adjacent organs. This paper compares artificial intelligence algorithms and traditional medical image processing techniques to assist radiologists in liver segmentation in computed tomography scans and evaluates their accuracy and efficiency. Despite notable progress in the field, the limited availability of public datasets remains a significant barrier to broad participation in research studies and replication of methodologies. Future directions should focus on increasing the accessibility of public datasets, establishing standardised evaluation metrics, and advancing the development of three-dimensional segmentation techniques. In addition, maintaining a collaborative relationship between technological advances and medical expertise is essential to ensure that these innovations not only achieve technical accuracy, but also remain aligned with clinical needs and realities. This synergy ensures their applicability and effectiveness in real-world healthcare environments. [ABSTRACT FROM AUTHOR]

Truck hoisting detection constitutes a key focus in port security, for which no optimal resolution has been identified. To address the issues of high costs, susceptibility to weather conditions, and low accuracy in conventional methods for truck hoisting detection, a non-intrusive detection approach is proposed in this paper. The proposed approach utilizes a mathematical model and an extreme gradient boosting (XGBoost) model. Electrical signals, including voltage and current, collected by Hall sensors are processed by the mathematical model, which augments their physical information. Subsequently, the dataset filtered by the mathematical model is used to train the XGBoost model, enabling the XGBoost model to effectively identify abnormal hoists. Improvements were observed in the performance of the XGBoost model as utilized in this paper. Finally, experiments were conducted at several stations. The overall false positive rate did not exceed 0.7% and no false negatives occurred in the experiments. The experimental results demonstrated the excellent performance of the proposed approach, which can reduce the costs and improve the accuracy of detection in container hoisting. [ABSTRACT FROM AUTHOR]

The zero-velocity update (ZUPT) algorithm is a pivotal advancement in pedestrian navigation accuracy, utilizing foot-mounted inertial sensors. Its key issue hinges on accurately identifying periods of zero-velocity during human movement. This paper introduces an innovative adaptive sliding window technique, leveraging the Fourier Transform to precisely isolate the pedestrian's gait frequency from spectral data. Building on this, the algorithm adaptively adjusts the zero-velocity detection threshold in accordance with the identified gait frequency. This adaptation significantly refines the accuracy in detecting zero-velocity intervals. Experimental evaluations reveal that this method outperforms traditional fixed-threshold approaches by enhancing precision and minimizing false positives. Experiments on single-step estimation show the adaptability of the algorithm to motion states such as slow, fast, and running. Additionally, the paper demonstrates pedestrian trajectory localization experiments under a variety of walking conditions. These tests confirm that the proposed method substantially improves the performance of the ZUPT algorithm, highlighting its potential for pedestrian navigation systems. [ABSTRACT FROM AUTHOR]

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer's global modeling ability and convolutional neural network's local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. [ABSTRACT FROM AUTHOR]

Noncontact heart rate monitoring techniques based on millimeter-wave radar have advantages in unique medical scenarios. However, the accuracy of the existing noncontact heart rate estimation methods is still limited by interference, such as DC offsets, respiratory harmonics, and environmental noise. Additionally, these methods still require longer observation times. Most deep learning methods related to heart rate estimation still need to collect more heart rate marker data for training. To address the above problems, this paper introduces a radar signal-based heart rate estimation network named the "masked phase autoencoders with a vision transformer network" (MVN). This network is grounded on masked autoencoders (MAEs) for self-supervised pretraining and a vision transformer (ViT) for transfer learning. During the phase preprocessing stage, phase differencing and interpolation smoothing are performed on the input phase signal. In the self-supervised pretraining step, masked self-supervised training is performed on the phase signal using the MAE network. In the transfer learning stage, the encoder segment of the MAE network is integrated with the ViT network to enable transfer learning using labeled heart rate data. The innovative MVN offers a dual advantage—it not only reduces the cost associated with heart rate data acquisition but also adeptly addresses the issue of respiratory harmonic interference, which is an improvement over conventional signal processing methods. The experimental results show that the process in this paper improves the accuracy of heart rate estimation while reducing the requisite observation time. [ABSTRACT FROM AUTHOR]

Driverless technology refers to the technology that vehicles use to drive independently with the help of driverless system under the condition of unmanned intervention. The working environment of construction machinery is bad, and the working conditions are complex. The use of driverless technology can greatly reduce the risk of driver operation, reduce labor costs and improve economic benefits.Aiming at the problem of the GPS positioning signal in the working environment of construction machinery being weak and not able to achieve accurate positioning, this paper uses the fusion SLAM algorithm based on improved NDT to realize the real-time positioning of the whole vehicle through reconstruction of the scene. Considering that the motion characteristics of crawler construction machinery are different from those of ordinary passenger cars, this paper improves the existing pure pursuit algorithm. Simulations and real vehicle tests show that the algorithm combined with the fusion SLAM algorithm can realize the motion control of driverless crawler construction machinery well, complete the tracking of the set trajectory perfectly and have high robustness. Considering that there is no mature walking method of driverless crawler construction machinery for reference, the research of this paper will lay a foundation for the development of driverless crawler construction machinery. [ABSTRACT FROM AUTHOR]

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper delves into the problem of direct position determination (DPD) for non-Gaussian sources. Existing DPD algorithms are hindered by their high computational complexity from exhaustive grid searches and a disregard for the received signal characteristics by multiple nested arrays (MNAs). To address these issues, the paper proposes a novel DPD algorithm for non-Gaussian sources with MNAs: the Discrete Fourier Transform (DFT) and Taylor compensation algorithm. Initially, the fourth-order cumulant matrix of the received signal is computed, and the vectorizing method is applied. Subsequently, a computationally efficient DPD cost function is proposed by leveraging a normalized DFT matrix to reduce complexity. Finally, first-order Taylor compensation is utilized to enhance the accuracy of the localization results. The superiority of the proposed algorithm is demonstrated through numerical simulation results. [ABSTRACT FROM AUTHOR]

Scanning ion conductance microscopy (SICM) enables the non-invasive three-dimensional imaging of live cells and other structures in physiological environments. However, when imaging complex samples, SICM faces challenges such as having a low temporal resolution during slow scanning and a reduced signal-to-noise ratio during fast scanning, making it difficult to simultaneously improve both temporal and spatial resolution. To address these issues, this paper proposes an algorithm for enhancing image resolution under high-speed scanning. Firstly, scanning images are preprocessed using a median filtering algorithm to remove the salt-and-pepper noise generated during high-speed scanning. Next, the Canny edge detection algorithm is employed to extract the edges of the image targets. To avoid blurring the edges, the new edge-directed interpolation (NEDI) algorithm is then used to fill the edges, while non-edge areas are filled using bilinear interpolation, thereby enhancing the image resolution. Finally, the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) are used to analyze the imaging of articular chondrocytes. The results show that under a scanning speed of 480 nm/ms, the proposed algorithm improves the temporal resolution of imaging by 60% compared to traditional 2× resolution imaging, increases the peak signal-to-noise ratio of the scanning images by 7 dB, and achieves a structural similarity of 0.97. Therefore, the proposed algorithm effectively removes noise during high-speed scanning and improves the SICM scanning imaging resolution, thereby avoiding the reduction in temporal resolution when scanning larger resolution samples and effectively enhancing the performance of SICM scanning imaging. [ABSTRACT FROM AUTHOR]

Object detection is one of the core technologies for autonomous driving. Current road object detection mainly relies on visible light, which is prone to missed detections and false alarms in rainy, night-time, and foggy scenes. Multispectral object detection based on the fusion of RGB and infrared images can effectively address the challenges of complex and changing road scenes, improving the detection performance of current algorithms in complex scenarios. However, previous multispectral detection algorithms suffer from issues such as poor fusion of dual-mode information, poor detection performance for multi-scale objects, and inadequate utilization of semantic information. To address these challenges and enhance the detection performance in complex road scenes, this paper proposes a novel multispectral object detection algorithm called MRD-YOLO. In MRD-YOLO, we utilize interaction-based feature extraction to effectively fuse information and introduce the BIC-Fusion module with attention guidance to fuse different modal information. We also incorporate the SAConv module to improve the model's detection performance for multi-scale objects and utilize the AIFI structure to enhance the utilization of semantic information. Finally, we conduct experiments on two major public datasets, FLIR_Aligned and M3FD. The experimental results demonstrate that compared to other algorithms, the proposed algorithm achieves superior detection performance in complex road scenes. [ABSTRACT FROM AUTHOR]

In response to the numerous challenges faced by traditional human pose recognition methods in practical applications, such as dense targets, severe edge occlusion, limited application scenarios, complex backgrounds, and poor recognition accuracy when targets are occluded, this paper proposes a YOLO-Pose algorithm for human pose estimation. The specific improvements are divided into four parts. Firstly, in the Backbone section of the YOLO-Pose model, lightweight GhostNet modules are introduced to reduce the model's parameter count and computational requirements, making it suitable for deployment on unmanned aerial vehicles (UAVs). Secondly, the ACmix attention mechanism is integrated into the Neck section to improve detection speed during object judgment and localization. Furthermore, in the Head section, key points are optimized using coordinate attention mechanisms, significantly enhancing key point localization accuracy. Lastly, the paper improves the loss function and confidence function to enhance the model's robustness. Experimental results demonstrate that the improved model achieves a 95.58% improvement in mAP50 and a 69.54% improvement in mAP50-95 compared to the original model, with a reduction of 14.6 M parameters. The model achieves a detection speed of 19.9 ms per image, optimized by 30% and 39.5% compared to the original model. Comparisons with other algorithms such as Faster R-CNN, SSD, YOLOv4, and YOLOv7 demonstrate varying degrees of performance improvement. [ABSTRACT FROM AUTHOR]

To enhance aerial image detection in complex environments characterized by multiple small targets and mutual occlusion, we propose an aerial target detection algorithm based on an improved version of YOLOv5 in this paper. Firstly, we employ an improved Mosaic algorithm to address redundant boundaries arising from varying image scales and to augment the training sample size, thereby enhancing detection accuracy. Secondly, we integrate the constructed hybrid attention module into the backbone network to enhance the model's capability in extracting pertinent feature information. Subsequently, we incorporate feature fusion layer 7 and P2 fusion into the neck network, leading to a notable enhancement in the model's capability to detect small targets. Finally, we replace the original PAN + FPN network structure with the optimized BiFPN (Bidirectional Feature Pyramid Network) to enable the model to preserve deeper semantic information, thereby enhancing detection capabilities for dense objects. Experimental results indicate a substantial improvement in both the detection accuracy and speed of the enhanced algorithm compared to its original version. It is noteworthy that the enhanced algorithm exhibits a markedly improved detection performance for aerial images, particularly under real-time conditions. [ABSTRACT FROM AUTHOR]

Roller bearings are critical components in various mechanical systems, and the timely detection of potential failures is essential for preventing costly downtimes and avoiding substantial machinery breakdown. This research focuses on finding and verifying a robust method that can detect failures early, without creating false positive failure states. Therefore, this paper introduces a novel algorithm for the early detection of roller bearing failures, particularly tailored to high-precision bearings and automotive test bed systems. The featured method (AFI—Advanced Failure Indicator) utilizes the Fast Fourier Transform (FFT) of wideband accelerometers to calculate the spectral content of vibration signals emitted by roller bearings. By calculating the frequency bands and tracking the movement of these bands within the spectra, the method provides an indicator of the machinery's health, mainly focusing on the early stages of bearing failure. The calculated channel can be used as a trend indicator, enabling the method to identify subtle deviations associated with impending failures. The AFI algorithm incorporates a non-static limit through moving average calculations and volatility analysis methods to determine critical changes in the signal. This thresholding mechanism ensures the algorithm's responsiveness to variations in operating conditions and environmental factors, contributing to its robustness in diverse industrial settings. Further refinement was achieved through an outlier detection filter, which reduces false positives and enhances the algorithm's accuracy in identifying genuine deviations from the normal operational state. To benchmark the developed algorithm, it was compared with three industry-standard algorithms: VRMS calculations per ISO 10813-3, Mean Absolute Value of Extremums (MAVE), and Envelope Frequency Band (EFB). This comparative analysis aimed to evaluate the efficacy of the novel algorithm against the established methods in the field, providing valuable insights into its potential advantages and limitations. In summary, this paper presents an innovative algorithm for the early detection of roller bearing failures, leveraging FFT-based spectral analysis, trend monitoring, adaptive thresholding, and outlier detection. Its ability to confirm the first failure state underscores the algorithm's effectiveness. [ABSTRACT FROM AUTHOR]

The traditional rearview mirror method cannot fully guarantee safety when driving trucks. RGB and infrared images collected by cameras are used for registration and recognition, so as to achieve the perception of surroundings and ensure safe driving. The traditional scale-invariant feature transform (SIFT) algorithm has a mismatching rate, and the YOLO algorithm has an optimization space in feature extraction. To address these issues, this paper proposes a truck surround sensing technique based on multi-features and an improved YOLOv5 algorithm. Firstly, the edge corner points and infrared features of the preset target region are extracted, and then a feature point set containing the improved SIFT algorithm is generated for registration. Finally, the YOLOv5 algorithm is improved by fusing infrared features and introducing a composite prediction mechanism at the prediction end. The simulation results show that, on average, the image stitching accuracy is improved by 17%, the time is reduced by 89%, and the target recognition accuracy is improved by 2.86%. The experimental results show that this method can effectively perceive the surroundings of trucks, accurately identify targets, and reduce the missed alarm rate and false alarm rate. [ABSTRACT FROM AUTHOR]

Tunnel cracks are the main factors that cause damage and collapse of tunnel structures. How to detect tunnel cracks efficiently and avoid safety accidents caused by tunnel cracks effectively is a research hotspot at present. In order to meet the need for efficient detection of tunnel cracks, the tunnel crack detection method based on improved Retinex and deep learning is proposed in this paper. The tunnel crack images collected by optical imaging equipment are used to improve the contrast information of tunnel crack images using the image enhancement algorithm, and this image enhancement algorithm has the function of multi-scale Retinex decomposition with improved central filtering. An improved VGG19 network model is constructed to achieve efficient segmentation of tunnel crack images through deep learning methods and then form the segmented binary image. The Zhang–Suen fast parallel-thinning method is used to obtain the skeleton map of the single-layer pixel, and the length and width information of the tunnel cracks are obtained. The feasibility and effectiveness of the proposed method are verified by experiments. Compared with other methods in the literature, the maximum deviation in the length of the tunnel crack is about 5 mm, and the maximum deviation in the width of the tunnel crack is about 0.8 mm. The experimental results show that the proposed method has a shorter detection time and higher detection accuracy. The research results of this paper can provide a strong basis for the health evaluation of tunnels. [ABSTRACT FROM AUTHOR]

Realizing the distributed adaptive network construction of multi-UAV networks is an urgent challenge, as they lack a reliable common control channel and can only maintain a limited sensing range in crowded electromagnetic environments. Multi-unmanned aerial vehicle (UAV) networks are gaining popularity in many fields. In order to address these issues, this paper proposes a multi-UAV network channel rendezvous algorithm based on average consistency. The goal of the algorithm is to adjust the communication channels of each UAV to converge on the same channel, since the communication link of the multi-UAV network is broken due to interference. The proposed memory-based average consistency (MAC) algorithm utilizes the network adjacency matrix as prior information. Furthermore, for the case where the adjacency matrix is unknown, this paper also proposes the Multi-Radio Average Consensus (MRAC) algorithm, which achieves a beneficial trade-off between rendezvous performance and hardware cost. Simulation results demonstrate that the proposed MAC and MRAC algorithms provide superior network convergence time and scalability in networks of different densities. Finally, a hardware simulation platform based on a multi-UAV network was designed using a software-defined radio platform, and experimental simulations were performed to prove the effectiveness of the MAC algorithm in a real environment. [ABSTRACT FROM AUTHOR]

With the sustainable development of intelligent fisheries, accurate underwater fish segmentation is a key step toward intelligently obtaining fish morphology data. However, the blurred, distorted and low-contrast features of fish images in underwater scenes affect the improvement in fish segmentation accuracy. To solve these problems, this paper proposes a method of underwater fish segmentation based on an improved PSPNet network (IST-PSPNet). First, in the feature extraction stage, to fully perceive features and context information of different scales, we propose an iterative attention feature fusion mechanism, which realizes the depth mining of fish features of different scales and the full perception of context information. Then, a SoftPool pooling method based on fast index weighted activation is used to reduce the numbers of parameters and computations while retaining more feature information, which improves segmentation accuracy and efficiency. Finally, a triad attention mechanism module, triplet attention (TA), is added to the different scale features in the golden tower pool module so that the space attention can focus more on the specific position of the fish body features in the channel through cross-dimensional interaction to suppress the fuzzy distortion caused by background interference in underwater scenes. Additionally, the parameter-sharing strategy is used in this process to make different scale features share the same learning weight parameters and further reduce the numbers of parameters and calculations. The experimental results show that the method presented in this paper yielded better results for the DeepFish underwater fish image dataset than other methods, with 91.56% for the Miou, 46.68 M for Params and 40.27 G for GFLOPS. In the underwater fish segmentation task, the method improved the segmentation accuracy of fish with similar colors and water quality backgrounds, improved fuzziness and small size and made the edge location of fish clearer. [ABSTRACT FROM AUTHOR]

When performing robotic automatic sorting and assembly operations of multi-category hardware, there are some problems with the existing convolutional neural network visual recognition algorithms, such as large computing power consumption, low recognition efficiency, and a high rate of missed detection and false detection. A novel efficient convolutional neural algorithm for multi-category aliasing hardware recognition is proposed in this paper. On the basis of SSD, the novel algorithm uses Resnet-50 instead of VGG16 as the backbone feature extraction network, and it integrates ECA-Net and Improved Spatial Attention Block (ISAB): two attention mechanisms to improve the ability of learning and extract target features. Then, we pass the weighted features to extra feature layers to build an improved SSD algorithm. At last, in order to compare the performance difference between the novel algorithm and the existing algorithms, three kinds of hardware with different sizes are chosen to constitute an aliasing scene that can simulate an industrial site, and some comparative experiments have been completed finally. The experimental results show that the novel algorithm has an mAP of 98.20% and FPS of 78, which are better than Faster R-CNN, YOLOv4, YOLOXs, EfficientDet-D1, and original SSD in terms of comprehensive performance. The novel algorithm proposed in this paper can improve the efficiency of robotic sorting and assembly of multi-category hardware. [ABSTRACT FROM AUTHOR]

Aiming at the current lane line detection algorithm in complex traffic scenes, such as lane lines being blocked by shadows, blurred roads, and road sparseness, which lead to low lane line detection accuracy and poor real-time detection speed, this paper proposes a lane line detection algorithm based on instance segmentation. Firstly, the improved lightweight network RepVgg-A0 is used to encode road images, which expands the receptive field of the network; secondly, a multi-size asymmetric shuffling convolution model is proposed for the characteristics of sparse and slender lane lines, which enhances the ability to extract lane line features; an adaptive upsampling model is further proposed as a decoder, which upsamples the feature map to the original resolution for pixel-level classification and detection, and adds the lane line prediction branch to output the confidence of the lane line; and finally, the instance segmentation-based lane line detection algorithm is successfully deployed on the embedded platform Jetson Nano, and half-precision acceleration is performed using NVDIA's TensorRT framework. The experimental results show that the Acc value of the lane line detection algorithm based on instance segmentation is 96.7%, and the FPS is 77.5 fps/s. The detection speed deployed on the embedded platform Jetson Nano reaches 27 fps/s. [ABSTRACT FROM AUTHOR]

As an important component of autonomous intelligent systems, the research on autonomous positioning algorithms used by UAVs is of great significance. In order to resolve the problem whereby the GNSS signal is interrupted, and the visual sensor lacks sufficient feature points in complex scenes, which leads to difficulties in autonomous positioning, this paper proposes a new robust adaptive positioning algorithm that ensures the robustness and accuracy of autonomous navigation and positioning in UAVs. On the basis of the combined navigation model of vision/inertial navigation and satellite/inertial navigation, based on ESKF, a multi-source fusion model based on a federated Kalman filter is here established. Furthermore, a robust adaptive localization algorithm is proposed, which uses robust equivalent weights to estimate the sub-filters, and then uses the sub-filter state covariance to adaptively assign information sharing coefficients. After simulation experiments and dataset verification, the results show that the robust adaptive algorithm can effectively limit the impact of gross errors in observations and mathematical model deviations and can automatically update the information sharing coefficient online according to the sub-filter equivalent state covariance. Compared with the classical federated Kalman algorithm and the adaptive federated Kalman algorithm, our algorithm can meet the real-time requirements of navigation, and the accuracy of position, velocity, and attitude measurement is improved by 2–3 times. The robust adaptive localization algorithm proposed in this paper can effectively improve the reliability and accuracy of autonomous navigation systems in complex scenes. Moreover, the algorithm is general—it is not intended for a specific scene or a specific sensor combination– and is applicable to individual scenes with varied sensor combinations. [ABSTRACT FROM AUTHOR]

The detection and classification of bone marrow (BM) cells is a critical cornerstone for hematology diagnosis. However, the low accuracy caused by few BM-cell data samples, subtle difference between classes, and small target size, pathologists still need to perform thousands of manual identifications daily. To address the above issues, we propose an improved BM-cell-detection algorithm in this paper, called YOLOv7-CTA. Firstly, to enhance the model's sensitivity to fine-grained features, we design a new module called CoTLAN in the backbone network to enable the model to perform long-term modeling between target feature information. Then, in order to cooperate with the CoTLAN module to pay more attention to the features in the area to be detected, we integrate the coordinate attention (CoordAtt) module between the CoTLAN modules to improve the model's attention to small target features. Finally, we cluster the target boxes of the BM cell dataset based on K-means++ to generate more suitable anchor boxes, which accelerates the convergence of the improved model. In addition, in order to solve the imbalance between positive and negative samples in BM-cell pictures, we use the Focal loss function to replace the multi-class cross entropy. Experimental results demonstrate that the best mean average precision (mAP) of the proposed model reaches 88.6%, which is an improvement of 12.9%, 8.3%, and 6.7% compared with that of the Faster R-CNN model, YOLOv5l model, and YOLOv7 model, respectively. This verifies the effectiveness and superiority of the YOLOv7-CTA model in BM-cell-detection tasks. [ABSTRACT FROM AUTHOR]

This paper proposes an adaptive threshold segmentation algorithm for the magnesium ingot stack based on image overexposure area correction (ATSIOAC), which solves the problem of mirror reflection on the surface of magnesium alloy ingots caused by external ambient light and auxiliary light sources. Firstly, considering the brightness and chromaticity information of the mapped image, we divide the exposure probability threshold into weak exposure and strong exposure regions. Secondly, the saturation difference between the magnesium ingot region and the background region is used to obtain a mask for the magnesium ingot region to eliminate interference from the image background. Then, the RGB average of adjacent pixels in the overexposed area is used as a reference to correct the colors of the strongly exposed and weakly exposed areas, respectively. Furthermore, in order to smoothly fuse the two corrected images, pixel weighted average (WA) is applied. Finally, the magnesium ingot sorting experimental device was constructed and the corrected top surface image of the ingot pile was segmented through ATSIOAC. The experimental results show that the overexposed area detection and correction algorithm proposed in this paper can effectively correct the color information in the overexposed area, and when segmenting ingot images, complete segmentation results of the top surface of the ingot pile can be obtained, effectively improving the accuracy of magnesium alloy ingot segmentation. The segmentation algorithm achieves a segmentation accuracy of 94.38%. [ABSTRACT FROM AUTHOR]

The combination of ultra-wide band (UWB) and inertial measurement unit (IMU) positioning is subject to random errors and non-line-of-sight errors, and in this paper, an improved positioning strategy is proposed to address this problem. The Kalman filter (KF) is used to pre-process the original UWB measurements, suppressing the effect of range mutation values of UWB on combined positioning, and the extended Kalman filter (EKF) is used to fuse the UWB measurements with the IMU measurements, with the difference between the two measurements used as the measurement information. The non-line-of-sight (NLOS) measurement information is also used. The optimal estimate is obtained by adjusting the system measurement noise covariance matrix in real time, according to the judgment result, and suppressing the interference of non-line-of-sight factors. The optimal estimate of the current state is fed back to the UWB range value in the next state, and the range value is dynamically adjusted after one-dimensional filtering pre-processing. Compared with conventional tightly coupled positioning, the positioning accuracy of the method in this paper is improved by 46.15% in the field experimental positioning results. [ABSTRACT FROM AUTHOR]

The detection algorithm commonly misses obscured pedestrians in traffic scenes with a high pedestrian density because mutual occlusion among pedestrians reduces the prediction box score of the concealed pedestrians. The paper uses the YOLOv7 algorithm as the baseline and makes the following three improvements by investigating the variables influencing the detection method's performance: First, the backbone network of the YOLOv7 algorithm is replaced with the lightweight feature extraction network Mobilenetv3 since the pedestrian detection algorithm frequently needs to be deployed in driverless mobile, which requires a fast operating speed of the algorithm; second, a high-resolution feature pyramid structure is suggested for the issue of missed detection of hidden pedestrians, which upscales the feature maps generated from the feature pyramid to increase the resolution of the output feature maps and introduces shallow feature maps to strengthen the distinctions between adjacent sub-features to enhance the network's ability to extract features for the visible area of hidden pedestrians and small-sized pedestrians in order to produce deeper features with greater differentiation for pedestrians; and the third is to suggest a detection head based on an attention mechanism that is employed to lower the confidence level of target neighboring sub-features, lower the quantity of redundant detection boxes, and lower the following NMS computation. The mAP of the suggested approach in this work achieves 89.75%, which is 9.5 percentage points better than the YOLOv7 detection algorithm, according to experiments on the CrowdHuman pedestrian-intensive dataset. The algorithm proposed in this paper can considerably increase the detection performance of the detection algorithm, particularly for obscured pedestrians and small-sized pedestrians in the dataset, according to the experimental effect plots. [ABSTRACT FROM AUTHOR]

In substation lightning rod meter reading data taking, the classical object detection model is not suitable for deployment in substation monitoring hardware devices due to its large size, large number of parameters, and slow detection speed, while is difficult to balance detection accuracy and real-time requirements with the existing lightweight object detection model. To address this problem, this paper constructs a lightweight object detection algorithm, YOLOv5-Meter Reading Lighting (YOLOv5-MRL), based on the improved YOLOv5 model's speed while maintaining accuracy. Then, the YOLOv5s are pruned based on the convolutional kernel channel soft pruning algorithm, which greatly reduces the number of parameters in the YOLOv5-MRL model while maintaining a certain accuracy loss. Finally, in order to facilitate the dial reading, the dial external circle fitting method is proposed to calculate the dial reading using the circular angle algorithm. The experimental results on the self-built dataset show that the YOLOv5-MRL object detection model achieves a mean average precision of 96.9%, a detection speed of 5 ms/frame, and a model weight size of 5.5 MB, making it better than other advanced dial reading models. [ABSTRACT FROM AUTHOR]

Aiming at the common problems, such as noise pollution, low contrast, and color distortion in underwater images, and the characteristics of holothurian recognition, such as morphological ambiguity, high similarity with the background, and coexistence of special ecological scenes, this paper proposes an underwater holothurian target-detection algorithm (FA-CenterNet), based on improved CenterNet and scene feature fusion. First, to reduce the model's occupancy of embedded device resources, we use EfficientNet-B3 as the backbone network to reduce the model's Params and FLOPs. At the same time, EfficientNet-B3 increases the depth and width of the model, which improves the accuracy of the model. Then, we design an effective FPT (feature pyramid transformer) combination module to fully focus and mine the information on holothurian ecological scenarios of different scales and spaces (e.g., holothurian spines, reefs, and waterweeds are often present in the same scenario as holothurians). The co-existing scene information can be used as auxiliary features to detect holothurians, which can improve the detection ability of fuzzy and small-sized holothurians. Finally, we add the AFF module to realize the deep fusion of the shallow-detail and high-level semantic features of holothurians. The results show that the method presented in this paper yields better results on the 2020 CURPC underwater target-detection image dataset with an AP50 of 83.43%, Params of 15.90 M, and FLOPs of 25.12 G compared to other methods. In the underwater holothurian-detection task, this method improves the accuracy of detecting holothurians with fuzzy features, a small size, and dense scene. It also achieves a good balance between detection accuracy, Params, and FLOPs, and is suitable for underwater holothurian detection in most situations. [ABSTRACT FROM AUTHOR]

Door access control systems are important to protect the security and integrity of physical spaces. Accuracy and speed are important factors that govern their performance. In this paper, we investigate a novel approach to identify users by measuring patterns of their interactions with a doorknob via an embedded accelerometer and gyroscope and by applying deep-learning-based algorithms to these measurements. Our identification results obtained from 47 users show an accuracy of 90.2%. When the sex of the user is used as an input feature, the accuracy is 89.8% in the case of male individuals and 97.0% in the case of female individuals. We study how the accuracy is affected by the sample duration, finding that is its possible to identify users using a sample of 0.5 s with an accuracy of 68.5%. Our results demonstrate the feasibility of using patterns of motor activity to provide access control, thus extending with it the set of alternatives to be considered for behavioral biometrics. [ABSTRACT FROM AUTHOR]