Search

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]

As people age, abnormal gait recognition becomes a critical problem in the field of healthcare. Currently, some algorithms can classify gaits with different pathologies, but they cannot guarantee high accuracy while keeping the model lightweight. To address these issues, this paper proposes a lightweight network (NSVGT-ICBAM-FACN) based on the new side-view gait template (NSVGT), improved convolutional block attention module (ICBAM), and transfer learning that fuses convolutional features containing high-level information and attention features containing semantic information of interest to achieve robust pathological gait recognition. The NSVGT contains different levels of information such as gait shape, gait dynamics, and energy distribution at different parts of the body, which integrates and compensates for the strengths and limitations of each feature, making gait characterization more robust. The ICBAM employs parallel concatenation and depthwise separable convolution (DSC). The former strengthens the interaction between features. The latter improves the efficiency of processing gait information. In the classification head, we choose to employ DSC instead of global average pooling. This method preserves the spatial information and learns the weights of different locations, which solves the problem that the corner points and center points in the feature map have the same weight. The classification accuracies for this paper's model on the self-constructed dataset and GAIT-IST dataset are 98.43% and 98.69%, which are 0.77% and 0.59% higher than that of the SOTA model, respectively. The experiments demonstrate that the method achieves good balance between lightweightness and performance. [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]

In mobile systems, fog, rain, snow, haze, and sun glare are natural phenomena that can be very dangerous for drivers. In addition to the visibility problem, the driver must face also the choice of speed while driving. The main effects of fog are a decrease in contrast and a fade of color. Rain and snow cause also high perturbation for the driver while glare caused by the sun or by other traffic participants can be very dangerous even for a short period. In the field of autonomous vehicles, visibility is of the utmost importance. To solve this problem, different researchers have approached and offered varied solutions and methods. It is useful to focus on what has been presented in the scientific literature over the past ten years relative to these concerns. This synthesis and technological evolution in the field of sensors, in the field of communications, in data processing, can be the basis of new possibilities for approaching the problems. This paper summarizes the methods and systems found and considered relevant, which estimate or even improve visibility in adverse weather conditions. Searching in the scientific literature, in the last few years, for the preoccupations of the researchers for avoiding the problems of the mobile systems caused by the environmental factors, we found that the fog phenomenon is the most dangerous. Our focus is on the fog phenomenon, and here, we present published research about methods based on image processing, optical power measurement, systems of sensors, etc. [ABSTRACT FROM AUTHOR]

During civil aviation flights, the aircraft needs to accurately monitor the real-time navigation capability and determine whether the onboard navigation system performance meets the required navigation performance (RNP). The airborne flight management system (FMS) uses actual navigation performance (ANP) to quantitatively calculate the uncertainty of aircraft position estimation, and its evaluation accuracy is highly dependent on the position estimation covariance matrix (PECM) provided by the airborne integrated navigation system. This paper proposed an adaptive PECM estimation method based on variational Bayes (VB) to solve the problem of ANP misevaluation, which is caused by the traditional simple ANP model failing to accurately estimate PECM under unknown time-varying noise. Combined with the 3D ANP model proposed in this paper, the accuracy of ANP evaluation can be significantly improved. This enhancement contributes to ensured navigation integrity and operational safety during civil flight. [ABSTRACT FROM AUTHOR]

The relative rotation angle between two cabins should be automatically and precisely obtained during automated assembly processes for spacecraft and aircraft. This paper introduces a method to solve this problem based on distributed vision, where two groups of cameras are employed to take images of mating features, such as dowel pins and holes, in oblique directions. Then, the relative rotation between the mating flanges of two cabins is calculated. The key point is the registration of the distributed cameras; thus, a simple and practical registration process is designed. It is assumed that there are rigid and scaling transformations among the world coordinate systems (WCS) of each camera. Therefore, the rigid-correct and scaling-correct matrices are adopted to register the cameras. An auxiliary registration device with known features is designed and moved in the cameras' field of view (FOV) to obtain the matrix parameters so that each camera acquires traces of every feature. The parameters can be solved using a genetic algorithm based on the known geometric relationships between the trajectories on the registration devices. This paper designs a prototype to verify the method. The precision reaches 0.02° in the measuring space of 340 mm. [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]

Photographs taken under harsh ambient lighting can suffer from a number of image quality degradation phenomena due to insufficient exposure. These include reduced brightness, loss of transfer information, noise, and color distortion. In order to solve the above problems, researchers have proposed many deep learning-based methods to improve the illumination of images. However, most existing methods face the problem of difficulty in obtaining paired training data. In this context, a zero-reference image enhancement network for low light conditions is proposed in this paper. First, the improved Encoder-Decoder structure is used to extract image features to generate feature maps and generate the parameter matrix of the enhancement factor from the feature maps. Then, the enhancement curve is constructed using the parameter matrix. The image is iteratively enhanced using the enhancement curve and the enhancement parameters. Second, the unsupervised algorithm needs to design an image non-reference loss function in training. Four non-reference loss functions are introduced to train the parameter estimation network. Experiments on several datasets with only low-light images show that the proposed network has improved performance compared with other methods in NIQE, PIQE, and BRISQUE non-reference evaluation index, and ablation experiments are carried out for key parts, which proves the effectiveness of this method. At the same time, the performance data of the method on PC devices and mobile devices are investigated, and the experimental analysis is given. This proves the feasibility of the method in this paper in practical application. [ABSTRACT FROM AUTHOR]

To solve the problem of inflexibility of offline hand–eye calibration in "eye-in-hand" modes, an online hand–eye calibration method based on the ChArUco board is proposed in this paper. Firstly, a hand–eye calibration model based on the ChArUco board is established, by analyzing the mathematical model of hand–eye calibration, and the image features of the ChArUco board. According to the advantages of the ChArUco board, with both the checkerboard and the ArUco marker, an online hand–eye calibration algorithm based on the ChArUco board is designed. Then, the online hand–eye calibration algorithm, based on the ChArUco board, is used to realize the dynamic adjustment of the hand–eye position relationship. Finally, the hand–eye calibration experiment is carried out to verify the accuracy of the hand–eye calibration based on the ChArUco board. The robustness and accuracy of the proposed method are verified by online hand–eye calibration experiments. The experimental results show that the accuracy of the online hand–eye calibration method proposed in this paper is between 0.4 mm and 0.6 mm, which is almost the same as the offline hand–eye calibration accuracy. The method in this paper utilizes the advantages of the ChArUco board to realize online hand–eye calibration, which improves the flexibility and robustness of hand–eye calibration. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to propose a novel transfer learning regularization method based on knowledge distillation. Recently, transfer learning methods have been used in various fields. However, problems such as knowledge loss still occur during the process of transfer learning to a new target dataset. To solve these problems, there are various regularization methods based on knowledge distillation techniques. In this paper, we propose a transfer learning regularization method based on feature map alignment used in the field of knowledge distillation. The proposed method is composed of two attention-based submodules: self-pixel attention (SPA) and global channel attention (GCA). The self-pixel attention submodule utilizes both the feature maps of the source and target models, so that it provides an opportunity to jointly consider the features of the target and the knowledge of the source. The global channel attention submodule determines the importance of channels through all layers, unlike the existing methods that calculate these only within a single layer. Accordingly, transfer learning regularization is performed by considering both the interior of each single layer and the depth of the entire layer. Consequently, the proposed method using both of these submodules showed overall improved classification accuracy than the existing methods in classification experiments on commonly used datasets. [ABSTRACT FROM AUTHOR]

Rotating machinery condition monitoring and fault diagnosis are important bases for maintenance decisions, as the vibrations generated during operation are usually imperceptible to the naked eye. Eulerian video motion magnification (EVMM) can reveal subtle changes and has been widely used in various fields such as medicine, structural analysis, and fault diagnosis, etc. However, the method has a bound relationship among three parameters: spatial wavelength, amplification factor, and displacement function, so it is necessary to adjust the parameters manually in practical applications. In this paper, on the basis of the original method, an automatic solution of spatial cutoff wavelength based on brightness is proposed. First, an input video is decomposed into image sequences, their RGB color spaces are transformed into HSV color spaces, and the Value channel image representing brightness is selected to automatically calculate the spatial cutoff frequency, and then the spatial cutoff wavelength is determined, and the motion magnification video in the specified frequency band is obtained by substituting it into the original method. Then, a publicly available video is taken as an example for simulation analysis. By comparing the time-brightness curves of the three videos (original video, motion magnification video obtained by the original method and the improved method), it is apparent that the proposed method exhibits the most significant brightness variation. Finally, taking an overhung rotor-bearing test device as the object, five conditions are set, respectively: normal, rotor unbalance, loosened anchor bolt of the bearing seat, compound fault, rotor misalignment. The proposed method is adopted to magnify the motion of the characteristic frequency bands including 1X frequency and 2X frequency. The results show that no obvious displacement is found in normal working conditions, and that the rotor unbalance fault has an overall axial shaking, the bearing seat at the loose place has an obvious vertical displacement, while the compound fault combines the both fault characteristics, and the rotor misalignment fault has an obvious axial displacement of the free-end bearing seat. The method proposed in this paper can automatically obtain the space cutoff wavelength, which solves the problem of defects arising from manually adjusting the parameters in the original method, and provides a new method for rotating machinery fault diagnosis and other fields of application. [ABSTRACT FROM AUTHOR]

Although the cost-reference particle filter (CRPF) has a good advantage in solving the state estimation problem with unknown noise statistical characteristics, its estimation accuracy is still affected by the lack of particle diversity and sensitivity to the particles' initial value. In order to solve these problems of the CRPF, this paper proposed an intelligent cost-reference particle filter algorithm based on multi-population cooperation. A multi-population cooperative resampling strategy based on ring structure was designed. The particles were divided into multiple independent populations upon initialization, and each population generated particles with a different initial distribution. The particles in each population were divided into three different particle sets with high, medium and low weights by the golden section ratio according to the weight. The particle sets with high and medium weights were retained. Then, a cooperative strategy based on Gaussian mutation was designed to resample the low-weight particle set of each population. The high-weight particles of the previous population in the ring structure were randomly selected for Gaussian mutation to replace the low-weight particles in the current population. The low-weight particles of all populations were resampled in turn. The simulation results show that the intelligent CRPF based on multi-population cooperation proposed in this paper can reduce the sensitivity of the CRPF to the particles' initial value and improve the particle diversity in resampling. Compared with the general CRPF and intelligent CRPF with adaptive MH resampling (MH-CRPF), the RMSE and MAE of the proposed method are lower. [ABSTRACT FROM AUTHOR]

Logging network traffic offers valuable insights into data flow, enabling the proactive analysis and troubleshooting of issues as they arise. Moreover, it provides a means to access and examine the exchanged information among network users that would otherwise be inaccessible. To enhance network traffic analysis, the integration of innovative technologies that facilitate real-time querying and pattern matching proves indispensable. This research paper presents a system that exemplifies such advancements—an innovative network traffic logging tool. The tool specifically focuses on performing real-time network packet transfer to Apache Kafka and ksqlDB, leveraging their capabilities to ensure swift and dependable storage of network packets in Apache Kafka topics. By showcasing this solution, the paper demonstrates the benefits and effectiveness of employing modern technologies for network traffic analysis and management. [ABSTRACT FROM AUTHOR]

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved. [ABSTRACT FROM AUTHOR]

Time-Sensitive Networking (TSN) and edge computing are promising networking technologies for the future of the Industrial Internet. TSN provides a reliable and deterministic low-latency communication service for edge computing. The Frame Replication and Elimination for Reliability (FRER) mechanism is important for improving the network reliability of TSN. It achieves high reliability by transmitting identical frames in parallel on two disjoint paths, while eliminating duplicated frames at the destination node. However, there are two problems with the FRER mechanism. One problem is that it does not consider the path reliability, and the other one is that it is difficult to find two completely disjoint path pairs in some cases. To solve the above problems, this paper proposes a method to find edge-disjoint path pairs considering path reliability for FRER in TSN. The method includes two parts: one is building a reliability model for paths, and the other one is computing a working path and a redundant path with the Edge-Disjoint Path Pairs Selection (EDPPS) algorithm. Theoretical and simulation results show that the proposed method effectively improves path reliability while reducing the delay jitter of frames. Compared with the traditional FRER mechanism, the proposed method reduces delay jitter by 15.6% when the network load is 0.9. [ABSTRACT FROM AUTHOR]

With the application of encoders in artificial intelligence and aerospace, the demand for the miniaturization and high measurement accuracy of encoders is increasing. To solve this problem, a new absolute matrix encoder is proposed in this paper, which can realize 19-bit matrix coding by engraving two circles of matrix code, and has the advantages of fewer circles of code disk engraving and higher measurement accuracy. This article mainly focuses on the design of a new matrix code disk, encoding and decoding methods, decoding circuit design, Matlab simulation analysis, and experimental error analysis. The experimental results show that the encoder designed in this paper achieves ultra-small volume Φ30 mm × 20 mm, and the angle measurement accuracy is 2.57". [ABSTRACT FROM AUTHOR]

To solve the problem of the large size of traditional industrial frequency phase-shift transformers and the harmonic distortion of multi-pulse wave rectifier systems, this paper proposes a three-stage shunt zigzag power electronic phase-shift transformer based on a double-tap multi-pulse wave rectifier, which combines the power factor correction (PFC) converter with the voltage-type SPWM inverter circuit to form a power electronic converter to realize the frequency boost and power factor correction. Through AC–DC–AC conversion, the frequency of the three-phase AC input voltage is increased, the number of core and coil turns in the transformer is reduced to reduce the size of the phase-shifter transformer, a zigzag structure of the phase-shifter transformer is used to solve the unbalanced distribution of current between the diode bridges, and a passive harmonic suppression method on the DC side is used to generate a loop current by using a group of single-phase rectifier bridges to regulate the input line current of the phase-shifter transformer. The phase-shifted voltage is input into two three-phase diode rectifier bridges to rectify and supply power to the load. Simulation and semi-physical test results show that the proposed method reduces the total harmonic distortion (THD) value of the input current of the phase-shifted transformer to 7.17%, and the THD value of the grid-side input current is further reduced to 2.49%, which meets the harmonic standard and realizes the purpose of power factor correction as well as being more suitable for high-power applications. [ABSTRACT FROM AUTHOR]

In the high-precision optoelectronic tracking system (OTS) based on a charge-coupled device (CCD), the boresight error extracted from the tracking image contains an undeniable delay, which directly limits the control bandwidth of visual tracking. High bandwidth means high response speed and tracking accuracy. Generally, a model-based delay compensation control method called the Smith predictor is utilized to separate time delay from the closed loop to promote the control bandwidth. However, due to the existence of errors between the established model and the real object, the improvement in the bandwidth is still limited to ensure system stability, resulting in insufficient tracking performance. In this paper, to solve the problem, a Smith predictor modified with pseudo feedforward control for the OTS is proposed. The experimental results demonstrate that the proposed method achieves significant improvements in tracking performance, reducing the maximum residual error at 1 Hz from 365 arcseconds (using the classic Smith predictor) to 283 arcseconds, a 22.5% improvement. Across the main frequency band (0.2 Hz to 2 Hz), the residual errors were consistently lower using the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive approach to detect violent events in videos by combining CrimeNet, a Vision Transformer (ViT) model with structured neural learning and adversarial regularization, with an adaptive threshold sliding window model based on the Transformer architecture. CrimeNet demonstrates exceptional performance on all datasets (XD-Violence, UCF-Crime, NTU-CCTV Fights, UBI-Fights, Real Life Violence Situations, MediEval, RWF-2000, Hockey Fights, Violent Flows, Surveillance Camera Fights, and Movies Fight), achieving high AUC ROC and AUC PR values (up to 99% and 100%, respectively). However, the generalization of CrimeNet to cross-dataset experiments posed some problems, resulting in a 20–30% decrease in performance, for instance, training in UCF-Crime and testing in XD-Violence resulted in 70.20% in AUC ROC. The sliding window model with adaptive thresholding effectively solves these problems by automatically adjusting the violence detection threshold, resulting in a substantial improvement in detection accuracy. By applying the sliding window model as post-processing to CrimeNet results, we were able to improve detection accuracy by 10% to 15% in cross-dataset experiments. Future lines of research include improving generalization, addressing data imbalance, exploring multimodal representations, testing in real-world applications, and extending the approach to complex human interactions. [ABSTRACT FROM AUTHOR]

A two-axis semi-strapdown stabilized platform is a device designed to eliminate aircraft disturbances and ensure the stability of the sensor's orientation. A traditional two-axis semi-strapdown stabilization platform for aircraft can effectively control disturbance in pitch and yaw channel, but it cannot achieve ideal disturbance control in the roll channel. In order to solve this problem, an adaptive control method based on disturbance transformation and LWOA-PID is proposed. Disturbance transformation is the process of integrating the angular position disturbance of the roll from the previous moment into the combined disturbance of the pitch and yaw at the current moment. This is followed by decoupling the combined disturbance of the pitch and yaw at the current moment, thereby eliminating the disturbance caused by the roll from the previous moment. This process is repeated to achieve the goal of eliminating roll channel disturbances. To ensure the line of sight (LOS) pointing accuracy stability in the two-axis semi-strapdown stabilized platform system for aircraft, a whale optimization adaptive proportional–integral–derivative (LWOA-PID) controller based on Latin hypercube sampling is designed. It is then compared with the classical PID controller in Matlab/Simulink. The simulation results indicate that the disturbance conversion module proposed in this paper can eliminate the impact of roll axis disturbances on the LOS pointing accuracy of the two-axis semi-strapdown stabilized platform for aircraft. Compared to the classical PID controller, the LWOA-PID controller reduces tracking errors for step and sinusoidal signals by 50% and 75%, respectively. It also shortens optimization time by 37.5% compared to the WOA-PID while maintaining the same level of accuracy. Furthermore, when combined with the conversion module, the tracking error is reduced by an additional order of magnitude. [ABSTRACT FROM AUTHOR]

Low-altitude airspace is developing rapidly, but the utilization rate of airspace resources is low. Therefore, in order to solve the problem of the safe operation of the fusion of large UAVs and manned aircraft in the same airspace, this paper analyzes the theoretical calculation of the collision risk of the fusion operation of manned aircraft and UAVs at Feng Ming Airport in Zigong, verifying that while assessing the safety spacing of 10 km in the lateral direction, it further simulates the possibility of calculating the theoretical smaller safety spacing. The study will propose a new theory of error spacing safety margin and improve it according to the traditional Event collision risk model, combining the error spacing safety margin to establish an improved collision model more suitable for the fusion operation of manned and unmanned aircraft and reduce the redundancy of calculation. The error factors affecting manned and unmanned aircraft at Zigong Airport are analyzed, and theoretical calculations are analyzed by combining the actual data of Zigong Airport. Finally, the Monte Carlo simulation method is used to solve the error, substitute the calculation results, and simulate a section of the trajectory of the fusion operation for the reverse argument. The theoretical calculation results show that the collision risk from 10 km to 8 km satisfies the lateral target safety level (TSL) specified by ICAO under both traditional and improved models. The collision risk calculated by the improved model incorporating the error spacing safety margin is smaller, which enhances the safety of the model calculations. The results of the study can provide theoretical references for the fusion operation of manned and unmanned aircraft. [ABSTRACT FROM AUTHOR]

Although the field of geomatics has seen multiple technological advances in recent years which enabled new applications and simplified the consolidated ones, some tasks remain challenging, inefficient, and time- and cost-consuming. This is the case of accurate tridimensional surveys of narrow spaces. Static laser scanning is an accurate and reliable approach but impractical for extensive tunnel environments; on the other hand, portable laser scanning is time-effective and efficient but not very reliable without ground control constraints. This paper describes the development process of a novel image-based multi-camera system meant to solve this specific problem: delivering accurate, reliable, and efficient results. The development is illustrated from the system conceptualization and initial investigations to the design choices and requirements for accuracy. The resulting working prototype has been put to the test to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Localization is a keystone for a robot to work within its environment and with other robots. There have been many methods used to solve this problem. This paper deals with the use of beacon-based localization to answer the research question: Can ultra-wideband technology be used to effectively localize a robot with sensor fusion? This paper has developed an innovative solution for creating a sensor fusion platform that uses ultra-wideband communication as a localization method to allow an environment to be perceived and inspected in three dimensions from multiple perspectives simultaneously. A series of contributions have been presented, supported by an in-depth literature review regarding topics in this field of knowledge. The proposed method was then designed, built, and tested successfully in two different environments exceeding its required tolerances. The result of the testing and the ideas formulated throughout the paper were discussed and future work outlined on how to build upon this work in potential academic papers and projects. [ABSTRACT FROM AUTHOR]

Chip pad inspection is of great practical importance for chip alignment inspection and correction. It is one of the key technologies for automated chip inspection in semiconductor manufacturing. When applying deep learning methods for chip pad inspection, the main problem to be solved is how to ensure the accuracy of small target pad detection and, at the same time, achieve a lightweight inspection model. The attention mechanism is widely used to improve the accuracy of small target detection by finding the attention region of the network. However, conventional attention mechanisms capture feature information locally, which makes it difficult to effectively improve the detection efficiency of small targets from complex backgrounds in target detection tasks. In this paper, an OCAM (Object Convolution Attention Module) attention module is proposed to build long-range dependencies between channel features and position features by constructing feature contextual relationships to enhance the correlation between features. By adding the OCAM attention module to the feature extraction layer of the YOLOv5 network, the detection performance of chip pads is effectively improved. In addition, a design guideline for the attention layer is proposed in the paper. The attention layer is adjusted by network scaling to avoid network characterization bottlenecks, balance network parameters, and network detection performance, and reduce the hardware device requirements for the improved YOLOv5 network in practical scenarios. Extensive experiments on chip pad datasets, VOC datasets, and COCO datasets show that the approach in this paper is more general and superior to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Due to the rapid development of industrial internet technology, the traditional manufacturing industry is in urgent need of digital transformation, and one of the key technologies to achieve this is multi-source data fusion. For this problem, this paper proposes an improved entropy-weighted topsis method for a multi-source data fusion evaluation system. It adds a fusion evaluation system based on the decision-level fusion algorithm and proposes a dynamic fusion strategy. The fusion evaluation system effectively solves the problem of data scale inconsistency among multi-source data, which leads to difficulties in fusing models and low fusion accuracy, and obtains optimal fusion results. The paper then verifies the effectiveness of the fusion evaluation system through experiments on the multilayer feature fusion of single-source data and the decision-level fusion of multi-source data, respectively. The results of this paper can be used in intelligent production and assembly plants in the discrete industry and provide the corresponding management and decision support with a certain practical value. [ABSTRACT FROM AUTHOR]

This paper proposes a tracking method combining feature enhancement and template update, aiming to solve the problems of existing trackers lacking global information attention, weak feature characterization ability, and not being well adapted to the changing appearance of the target. Pre-extracted features are enhanced in context and on channels through a feature enhancement network consisting of channel attention and transformer architectures. The enhanced feature information is input into classification and regression networks to achieve the final target state estimation. At the same time, the template update strategy is introduced to update the sample template judiciously. Experimental results show that the proposed tracking method exhibits good tracking performance on the OTB100, LaSOT, and GOT-10k benchmark datasets. [ABSTRACT FROM AUTHOR]

The widespread use of the internet and the exponential growth in small hardware diversity enable the development of Internet of things (IoT)-based localization systems. We review machine-learning-based approaches for IoT localization systems in this paper. Because of their high prediction accuracy, machine learning methods are now being used to solve localization problems. The paper's main goal is to provide a review of how learning algorithms are used to solve IoT localization problems, as well as to address current challenges. We examine the existing literature for published papers released between 2020 and 2022. These studies are classified according to several criteria, including their learning algorithm, chosen environment, specific covered IoT protocol, and measurement technique. We also discuss the potential applications of learning algorithms in IoT localization, as well as future trends. [ABSTRACT FROM AUTHOR]

Point cloud registration is widely used in autonomous driving, SLAM, and 3D reconstruction, and it aims to align point clouds from different viewpoints or poses under the same coordinate system. However, point cloud registration is challenging in complex situations, such as a large initial pose difference, high noise, or incomplete overlap, which will cause point cloud registration failure or mismatching. To address the shortcomings of the existing registration algorithms, this paper designed a new coarse-to-fine registration two-stage point cloud registration network, CCRNet, which utilizes an end-to-end form to perform the registration task for point clouds. The multi-scale feature extraction module, coarse registration prediction module, and fine registration prediction module designed in this paper can robustly and accurately register two point clouds without iterations. CCRNet can link the feature information between two point clouds and solve the problems of high noise and incomplete overlap by using a soft correspondence matrix. In the standard dataset ModelNet40, in cases of large initial pose difference, high noise, and incomplete overlap, the accuracy of our method, compared with the second-best popular registration algorithm, was improved by 7.0%, 7.8%, and 22.7% on the MAE, respectively. Experiments showed that our CCRNet method has advantages in registration results in a variety of complex conditions. [ABSTRACT FROM AUTHOR]

Simultaneous location and mapping (SLAM) technology is key in robot autonomous navigation. Most visual SLAM (VSLAM) algorithms for dynamic environments cannot achieve sufficient positioning accuracy and real-time performance simultaneously. When the dynamic object proportion is too high, the VSLAM algorithm will collapse. To solve the above problems, this paper proposes an indoor dynamic VSLAM algorithm called YDD-SLAM based on ORB-SLAM3, which introduces the YOLOv5 object detection algorithm and integrates deep information. Firstly, the objects detected by YOLOv5 are divided into eight subcategories according to their motion characteristics and depth values. Secondly, the depth ranges of the dynamic object and potentially dynamic object in the moving state in the scene are calculated. Simultaneously, the depth value of the feature point in the detection box is compared with that of the feature point in the detection box to determine whether the point is a dynamic feature point; if it is, the dynamic feature point is eliminated. Further, multiple feature point optimization strategies were developed for VSLAM in dynamic environments. A public data set and an actual dynamic scenario were used for testing. The accuracy of the proposed algorithm was significantly improved compared to that of ORB-SLAM3. This work provides a theoretical foundation for the practical application of a dynamic VSLAM algorithm. [ABSTRACT FROM AUTHOR]

Intelligent defect detection technology combined with deep learning has gained widespread attention in recent years. However, the small number, and diverse and random nature, of defects on industrial surfaces pose a significant challenge to deep learning-based methods. Generating defect images can effectively solve this problem. This paper investigates and summarises traditional defect generation and deep learning-based methods. It analyses the various advantages and disadvantages of these methods and establishes a benchmark through classical adversarial networks and diffusion models. The performance of these methods in generating defect images is analysed through various indices. This paper discusses the existing methods, highlights the shortcomings and challenges in the field of defect image generation, and proposes future research directions. Finally, the paper concludes with a summary. [ABSTRACT FROM AUTHOR]

With humanity entering the age of intelligence, text detection technology has been gradually applied in the industry. However, text detection in a complex background is still a challenging problem for researchers to overcome. Most of the current algorithms are not robust enough to locate text regions, and the problem of the misdetection of adjacent text instances still exists. In order to solve the above problems, this paper proposes a multi-level residual feature pyramid network (MR-FPN) based on a self-attention environment, which can accurately separate adjacent text instances. Specifically, the framework uses ResNet50 as the backbone network, which is improved on the feature pyramid network (FPN). A self-attention module (SAM) is introduced to capture pixel-level relations, increase context connection, and obtain efficient features. At the same time, the multi-scale enhancement module (MEM) improves the expression ability of text information, extracting strong semantic information and integrating the multi-scale features generated by the feature pyramid. In addition, information regarding the upper features will cause loss when the feature pyramid is passed down step by step, and multi-level residuals can effectively solve this problem. The proposed model can effectively improve the fusion ability of the feature pyramid, provide more refined features for text detection, and improve the robustness of text detection. This model was evaluated on CTW1500, Total-Text, ICDAR2015, and MSRA-TD500 datasets of different kinds and achieved varying degrees of improvement. It is worth mentioning that the F-measure of 83.31% obtained by this paper on the Total-Text dataset exceeds that of the baseline system by 5%. [ABSTRACT FROM AUTHOR]

In space-time adaptive processing (STAP), the coprime sampling structure can obtain better clutter suppression capabilities at a lower hardware cost than the uniform linear sampling structure. However, in practical applications, the performance of the algorithm is often limited by the number of training samples. To solve this problem, this paper proposes a fast iterative coprime STAP algorithm based on truncated kernel norm minimization (TKNM). This method establishes a virtual clutter covariance matrix (CCM), introduces truncated kernel norm regularization technology to ensure the low rank of the CCM, and transforms the non-convex problem into a convex optimization problem. Finally, a fast iterative solution method based on the alternating direction method is presented. The effectiveness and accuracy of the proposed algorithm are verified through simulation experiments. [ABSTRACT FROM AUTHOR]

For the RRT* algorithm, there are problems such as greater randomness, longer time consumption, more redundant nodes, and inability to perform local obstacle avoidance when encountering unknown obstacles in the path planning process of autonomous vehicles. And the artificial potential field method (APF) applied to autonomous vehicles is prone to problems such as local optimality, unreachable targets, and inapplicability to global scenarios. A fusion algorithm combining the improved RRT* algorithm and the improved artificial potential field method is proposed. First of all, for the RRT* algorithm, the concept of the artificial potential field and probability sampling optimization strategy are introduced, and the adaptive step size is designed according to the road curvature. The path post-processing of the planned global path is carried out to reduce the redundant nodes of the generated path, enhance the purpose of sampling, solve the problem where oscillation may occur when expanding near the target point, reduce the randomness of RRT* node sampling, and improve the efficiency of path generation. Secondly, for the artificial potential field method, by designing obstacle avoidance constraints, adding a road boundary repulsion potential field, and optimizing the repulsion function and safety ellipse, the problem of unreachable targets can be solved, unnecessary steering in the path can be reduced, and the safety of the planned path can be improved. In the face of U-shaped obstacles, virtual gravity points are generated to solve the local minimum problem and improve the passing performance of the obstacles. Finally, the fusion algorithm, which combines the improved RRT* algorithm and the improved artificial potential field method, is designed. The former first plans the global path, extracts the path node as the temporary target point of the latter, guides the vehicle to drive, and avoids local obstacles through the improved artificial potential field method when encountered with unknown obstacles, and then smooths the path planned by the fusion algorithm, making the path satisfy the vehicle kinematic constraints. The simulation results in the different road scenes show that the method proposed in this paper can quickly plan a smooth path that is more stable, more accurate, and suitable for vehicle driving. [ABSTRACT FROM AUTHOR]

The remarkable human ability to predict others' intent during physical interactions develops at a very early age and is crucial for development. Intent prediction, defined as the simultaneous recognition and generation of human–human interactions, has many applications such as in assistive robotics, human–robot interaction, video and robotic surveillance, and autonomous driving. However, models for solving the problem are scarce. This paper proposes two attention-based agent models to predict the intent of interacting 3D skeletons by sampling them via a sequence of glimpses. The novelty of these agent models is that they are inherently multimodal, consisting of perceptual and proprioceptive pathways. The action (attention) is driven by the agent's generation error, and not by reinforcement. At each sampling instant, the agent completes the partially observed skeletal motion and infers the interaction class. It learns where and what to sample by minimizing the generation and classification errors. Extensive evaluation of our models is carried out on benchmark datasets and in comparison to a state-of-the-art model for intent prediction, which reveals that classification and generation accuracies of one of the proposed models are comparable to those of the state of the art even though our model contains fewer trainable parameters. The insights gained from our model designs can inform the development of efficient agents, the future of artificial intelligence (AI). [ABSTRACT FROM AUTHOR]

To solve the problem of a low signal-to-noise ratio of fault signals and the difficulty in effectively and accurately identifying the fault state in the early stage of motor bearing fault occurrence, this paper proposes an early fault diagnosis method for bearings based on the Differential Local Mean Decomposition (DLMD) and fusion of current–vibration signals. This method uses DLMD to decompose the current signal and vibration signal, respectively, and weights the decomposed product function (PF) according to the kurtosis value to reconstruct the signal, and then fuses the reconstructed signals to obtain the current–vibration fusion signal after normalization, and then analyzes the fusion signal spectrally through the Hilbert envelope spectrum. Finally, the fusion signal is analyzed by the Hilbert envelope spectrum, and a clear fault characteristic frequency is obtained. The experimental results demonstrate that compared to traditional bearing fault diagnosis methods, the proposed method significantly improves the signal-to-noise ratio of fault signals, effectively enhances the sensitivity of early-stage fault detection in motor bearings, and improves the accuracy of fault identification. [ABSTRACT FROM AUTHOR]

Energy efficiency and data reliability are important indicators to measure network performance in wireless sensor networks. In existing research schemes of routing protocols, the impact of node coverage on the network is often ignored, and the possibility that multiple sensor nodes may sense the same spatial point is not taken into account, which results in a waste of network resources, especially in large-scale networks. Apart from that, the blindness of geographic routing in data transmission has been troubling researchers, which means that the nodes are unable to determine the validity of data transmission. In order to solve the above problems, this paper innovatively combines the routing protocol with the coverage control technique and proposes the node collaborative scheduling algorithm, which fully considers the correlation characteristics between sensor nodes to reduce the number of active working nodes and the number of packets generated, to further reduce energy consumption and network delay and improve packet delivery rate. In order to solve the problem of unreliability of geographic routing, a highly reliable link detection and repair scheme is proposed to check the communication link status and repair the invalid link, which can greatly improve the packet delivery rate and throughput of the network, and has good robustness. A large number of experiments demonstrate the effectiveness and superiority of our proposed scheme and algorithm. [ABSTRACT FROM AUTHOR]

With the rapid development of the intelligent driving technology, achieving accurate path planning for unmanned vehicles has become increasingly crucial. However, path planning algorithms face challenges when dealing with complex and ever-changing road conditions. In this paper, aiming at improving the accuracy and robustness of the generated path, a global programming algorithm based on optimization is proposed, while maintaining the efficiency of the traditional A* algorithm. Firstly, turning penalty function and obstacle raster coefficient are integrated into the search cost function to increase the adaptability and directionality of the search path to the map. Secondly, an efficient search strategy is proposed to solve the problem that trajectories will pass through sparse obstacles while reducing spatial complexity. Thirdly, a redundant node elimination strategy based on discrete smoothing optimization effectively reduces the total length of control points and paths, and greatly reduces the difficulty of subsequent trajectory optimization. Finally, the simulation results, based on real map rasterization, highlight the advanced performance of the path planning and the comparison among the baselines and the proposed strategy showcases that the optimized A* algorithm significantly enhances the security and rationality of the planned path. Notably, it reduces the number of traversed nodes by 84%, the total turning angle by 39%, and shortens the overall path length to a certain extent. [ABSTRACT FROM AUTHOR]

An online measurement method is proposed in this paper, and a system is established for detecting the excitation impedance of current transformers (CTs) based on Norton's theorem. The theorem is carried out by connecting a resistance and an inductance at the secondary side port of the CT to get the equations for calculating the impedance. The iterative method is used to solve the equations, and the solution is revised to consider the nonlinearity of the core. The main variable in the equations is the variation of the secondary current with the resistance or inductance. To obtain the secondary current variation accurately, which is less than 1‰ of the current, a differential method is proposed, which is based on charging two capacitors and measuring the difference of their voltages instead of measuring each current separately first and then obtaining the current variation by subtraction. This is equivalent to saving two currents first and then measuring the current difference. The differential method avoids the problem of error amplification in the process of measuring two currents separately first and then subtracting them to obtain the current variation and solves the problem that two currents do not appear simultaneously. The results verify the correctness and accuracy of the proposed method and system. The acquisition of the excitation impedance is the basis for obtaining the working characteristics of CT cores, including magnetic and loss characteristics, as well as the error of CTs. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) infrared detection has problems such as weak and small targets, complex backgrounds, and poor real-time detection performance. It is difficult for general target detection algorithms to achieve the requirements of a high detection rate, low missed detection rate, and high real-time performance. In order to solve these problems, this paper proposes an improved small target detection method based on Picodet. First, to address the problem of poor real-time performance, an improved lightweight LCNet network was introduced as the backbone network for feature extraction. Secondly, in order to solve the problems of high false detection rate and missed detection rate due to weak targets, the Squeeze-and-Excitation module was added and the feature pyramid structure was improved. Experimental results obtained on the HIT-UAV public dataset show that the improved detection model's real-time frame rate increased by 31 fps and the average accuracy (MAP) increased by 7%, which proves the effectiveness of this method for UAV infrared small target detection. [ABSTRACT FROM AUTHOR]

Diesel engines have a wide range of functions in the industrial and military fields. An urgent problem to be solved is how to diagnose and identify their faults effectively and timely. In this paper, a diesel engine acoustic fault diagnosis method based on variational modal decomposition mapping Mel frequency cepstral coefficients (MFCC) and long-short-term memory network is proposed. Variational mode decomposition (VMD) is used to remove noise from the original signal and differentiate the signal into multiple modes. The sound pressure signals of different modes are mapped to the Mel filter bank in the frequency domain, and then the Mel frequency cepstral coefficients of the respective mode signals are calculated in the mapping range of frequency domain, and the optimized Mel frequency cepstral coefficients are used as the input of long and short time memory network (LSTM) which is trained and verified, and the fault diagnosis model of the diesel engine is obtained. The experimental part compares the fault diagnosis effects of different feature extraction methods, different modal decomposition methods and different classifiers, finally verifying the feasibility and effectiveness of the method proposed in this paper, and providing solutions to the problem of how to realise fault diagnosis using acoustic signals. [ABSTRACT FROM AUTHOR]

Sugarcane stem node identification is the core technology required for the intelligence and mechanization of the sugarcane industry. However, detecting stem nodes quickly and accurately is still a significant challenge. In this paper, in order to solve this problem, a new algorithm combining YOLOv3 and traditional methods of computer vision is proposed, which can improve the identification rate during automated cutting. First, the input image is preprocessed, during which affine transformation is used to correct the posture of the sugarcane and a rotation matrix is established to obtain the region of interest of the sugarcane. Then, a dataset is built to train the YOLOv3 network model and the position of the stem nodes is initially determined using the YOLOv3 model. Finally, the position of the stem nodes is further located accurately. In this step, a new gradient operator is proposed to extract the edge of the image after YOLOv3 recognition. Then, a local threshold determination method is proposed, which is used to binarize the image after edge extraction. Finally, a localization algorithm for stem nodes is designed to accurately determine the number and location of the stem nodes. The experimental results show that the precision rate, recall rate, and harmonic mean of the stem node recognition algorithm in this paper are 99.68%, 100%, and 99.84%, respectively. Compared to the YOLOv3 network, the precision rate and the harmonic mean are improved by 2.28% and 1.13%, respectively. Compared to other methods introduced in this paper, this algorithm has the highest recognition rate. [ABSTRACT FROM AUTHOR]

Small object detection has always been a difficult direction in the field of object detection, especially the detection of small objects in UAV aerial images. The images captured by UAVs have the characteristics of small objects and dense objects. In order to solve these two problems, this paper improves the performance of object detection from the aspects of data and network structure. In terms of data, the data augmentation strategy and image pyramid mechanism are mainly used. The data augmentation strategy adopts the method of image division, which can greatly increase the number of small objects, making it easier for the algorithm to be fully trained during the training process. Since the object is denser, the image pyramid mechanism is used. During the training process, the divided images are up-sampled into three different sizes, and then sent to three different detectors respectively. Finally, the detection results of the three detectors are fused to obtain the final detection results. The small object itself has few pixels and few features. In order to improve the detection performance, it is necessary to use context. This paper adds attention mechanism to the yolov5 network structure, while adding a detection head to the underlying feature map to make the network structure pay more attention to small objects. By using data augmentation and improved network structure, the detection performance of small objects can be significantly improved. The experiment in this paper is carried out on the Visdrone2019 dataset and DOTA dataset. Through experimental verification, our proposed method can significantly improve the performance of small object detection. [ABSTRACT FROM AUTHOR]

In MOOC learning, learners' emotions have an important impact on the learning effect. In order to solve the problem that learners' emotions are not obvious in the learning process, we propose a method to identify learner emotion by combining eye movement features and scene features. This method uses an adaptive window to partition samples and enhances sample features through fine-grained feature extraction. Using an adaptive window to partition samples can make the eye movement information in the sample more abundant, and fine-grained feature extraction from an adaptive window can increase discrimination between samples. After adopting the method proposed in this paper, the four-category emotion recognition accuracy of the single modality of eye movement reached 65.1% in MOOC learning scenarios. Both the adaptive window partition method and the fine-grained feature extraction method based on eye movement signals proposed in this paper can be applied to other modalities. [ABSTRACT FROM AUTHOR]

In the process of dynamic Measurement While Drilling (MWD), the strong vibration and rapid rotation of the Bottom Hole Assembly (BHA) lead to multi-frequency and high-amplitude noise interference in the attitude measurement signal. The weak original signal and extremely low signal-to-noise ratio (SNR) are always the technical difficulties of dynamic MWD. To solve this problem, this paper uses the chaotic effect of the Duffing system, which takes the expression (−x3 + x5) as a nonlinear restoring force to detect the weak characteristic signal of downhole dynamic MWD. First of all, in order to meet the limit condition of the chaotic phase transition of the system output, the frequency value of the characteristic signal is reconstructed and transformed based on the variable scale theory. Then, in order to solve the influence of the initial phase of the characteristic signal on the detection accuracy, a detection model based on the array Duffing system is presented, and a frequency-detection scheme with all-phase coverage is given. Finally, another array Duffing system is designed for the parameter estimation of the characteristic signal. The critical value of chaotic phase transition is determined by adjusting the amplitude of the driving signal of the array Duffing system, and then the amplitude and phase parameters of the characteristic signal are synchronously estimated. The experimental results show that the proposed method can effectively extract the weak characteristic signal within the strong noise, and the SNR of the characteristic signal can be as low as −21 dB. Through the attitude calculation for the extracted characteristic signal, it can be seen that the proposed method can improve the accuracy of the inclination of the drilling tool significantly, which proves the feasibility and effectiveness of the method proposed in this paper. [ABSTRACT FROM AUTHOR]

Satellite signals are easily lost in urban areas, which causes difficulty in vehicles being located with high precision. Visual odometry has been increasingly applied in navigation systems to solve this problem. However, visual odometry relies on dead-reckoning technology, where a slight positioning error can accumulate over time, resulting in a catastrophic positioning error. Thus, this paper proposes a road-network-map-assisted vehicle positioning method based on the theory of pose graph optimization. This method takes the dead-reckoning result of visual odometry as the input and introduces constraints from the point-line form road network map to suppress the accumulated error and improve vehicle positioning accuracy. We design an optimization and prediction model, and the original trajectory of visual odometry is optimized to obtain the corrected trajectory by introducing constraints from map correction points. The vehicle positioning result at the next moment is predicted based on the latest output of the visual odometry and corrected trajectory. The experiments carried out on the KITTI and campus datasets demonstrate the superiority of the proposed method, which can provide stable and accurate vehicle position estimation in real-time, and has higher positioning accuracy than similar map-assisted methods. [ABSTRACT FROM AUTHOR]

Space-borne gravitational wave detection satellite confronts many uncertain perturbations, such as solar pressure, dilute atmospheric drag, etc. To realize an ultra-static and ultra-stable inertial benchmark achieved by a test-mass (TM) being free to move inside a spacecraft (S/C), the drag-free control system of S/C requires super high steady-state accuracies and dynamic performances. The Active Disturbance Rejection Control (ADRC) technique has a certain capability in solving problems with common perturbations, while there is still room for optimization in dealing with the complicated drag-free control problem. When faced with complex noises, the steady-state accuracy of the traditional control method is not good enough and the convergence speed of regulating process is not fast enough. In this paper, the optimized Active Disturbance Rejection Control technique is applied. With the extended state Kalman filter (ESKF) estimating the states and disturbances in real time, a novel closed-loop control structure is designed by combining the linear quadratic regulator (LQR) and ESKF, which can satisfy the design targets competently. The comparative analysis and simulation results show that the LQR controller designed in this paper has a faster response and a higher accuracy compared with the traditional nonlinear state error feedback (NSEF), which uses a deformation of weighting components of classical PID. The new drag-free control structure proposed in the paper can be used in future gravitational wave detection satellites. [ABSTRACT FROM AUTHOR]

Smart security based on object detection is one of the important applications of edge computing in IoT. Anchors in object detection refer to points on the feature map, which can be used to generate anchor boxes and serve as training samples. Current object detection models do not consider the aspect ratio of the ground-truth boxes in anchor assignment and are not well-adapted to objects with very different shapes. Therefore, this paper proposes the Lightweight Anchor Dynamic Assignment algorithm (LADA) for object detection. LADA does not change the structure of the original detection model; first, it selects an equal proportional center region based on the aspect ratio of the ground-truth box, then calculates the combined loss of anchors, and finally divides the positive and negative samples more efficiently by dynamic loss threshold without additional models. The algorithm solves the problems of poor adaptability and difficulty in the selection of the best positive samples based on IoU assignment, and the sample assignment for eccentric objects and objects with different aspect ratios was more reasonable. Compared with existing sample assignment algorithms, the LADA algorithm outperforms the MS COCO dataset by 1.66% over the AP of the baseline FCOS, and 0.76% and 0.24% over the AP of the ATSS algorithm and the PAA algorithm, respectively, with the same model structure, which demonstrates the effectiveness of the LADA algorithm. [ABSTRACT FROM AUTHOR]

The paper proposes a topology-free specification of distributed control systems by means of a process-oriented programming paradigm. The proposed approach was characterized, on the one hand, by a topologically independent specification of the control algorithm and, on the other hand, by the possibility of using existing formal verification methods by preserving the semantics of a centralized process-oriented program. The paper discusses the advantages of a topologically independent specification of distributed control systems, outlines the features of control software, argues why the use of a process-oriented approach to the development of the automation of cyber-physical systems is suitable for solving these problems, describes a general scheme for implementing a distributed control system according to a process-oriented specification, and proposes a formal heuristic algorithm for partitioning a sequential process-oriented program into independent clusters. We illustrate our algorithm with bottle-filling and sluice case studies. [ABSTRACT FROM AUTHOR]

Most deep-learning-based object detection algorithms exhibit low speeds and accuracy in gear surface defect detection due to their high computational costs and complex structures. To solve this problem, a lightweight model for gear surface defect detection, namely STMS-YOLOv5, is proposed in this paper. Firstly, the ShuffleNetv2 module is employed as the backbone to reduce the giga floating-point operations per second and the number of parameters. Secondly, transposed convolution upsampling is used to enhance the learning capability of the network. Thirdly, the max efficient channel attention mechanism is embedded in the neck to compensate for the accuracy loss caused by the lightweight backbone. Finally, the SIOU_Loss is adopted as the bounding box regression loss function in the prediction part to speed up the model convergence. Experiments show that STMS-YOLOv5 achieves frames per second of 130.4 and 133.5 on the gear and NEU-DET steel surface defect datasets, respectively. The number of parameters and GFLOPs are reduced by 44.4% and 50.31%, respectively, while the mAP@0.5 reaches 98.6% and 73.5%, respectively. Extensive ablation and comparative experiments validate the effectiveness and generalization capability of the model in industrial defect detection. [ABSTRACT FROM AUTHOR]

The automatic parking system based on vision is greatly affected by uneven lighting, which is difficult to make an accurate judgment on parking spaces in the case of complex image information. To solve this problem, this paper proposes a parking space visual detection and image processing method based on deep learning. Firstly, a 360-degree panoramic system was designed to photograph the vehicle environment. The image has been processed to obtain a panoramic aerial view, which was input as the original image of the parking space detection system. Secondly, the Faster R-CNN (Region-Convolutional Neural Network) parking detection model was established based on deep learning. It was aimed to detect and extract the parking space from the input image. Thirdly, the problems of uneven illumination and complex background were solved effectively by removing the background light from the image. Finally, a parking space extraction method based on the connected region has been designed, which further simplified the parking space extraction and image processing. The experiment results show that the mAP (mean Average Precision) value of the Faster R-CNN model using 101-Floor ResNet as the feature extraction network is 89.30%, which is 2.28% higher than that of the Faster R-CNN model using 50-Floor ResNet as the feature extraction network. The model built in this paper can detect most parking spaces well. The position of the output target box is accurate. In some test scenarios, the confidence of parking space recognition can even reach 100%. In summary, the proposed method can realize the effective identification and accurate positioning of parking spaces. [ABSTRACT FROM AUTHOR]