基于改进Centerfusion的自动驾驶3D目标检测模型

针对自动驾驶路面上目标漏检和错检的问题,提出一种基于改进Centerfusion的自动驾驶3D目标检测模型。该模型通过将相机信息和雷达特征融合,构成多通道特征数据输入,从而增强目标检测网络的鲁棒性,减少漏检问题;为了能够得到更加准确丰富的3D目标检测信息,引入了改进的注意力机制,用于增强视锥网格中的雷达点云和视觉信息融合;使用改进的损失函数优化边框预测的准确度。在Nuscenes数据集上进行模型验证和对比,实验结果表明,相较于传统的Centerfusion模型,提出的模型平均检测精度均值(mean Average Precision,mAP)提高了1.3%,Nuscenes检测分数(Nuscenes Detection Scores,NDS)提高了1.2%。

Disparity estimation for multi-scale multi-sensor fusion

The perception module of advanced driver assistance systems plays a vital role.Perception schemes often use a single sensor for data processing and environmental perception or adopt the information processing results of various sensors for the fusion of the detection layer.This paper proposes a multi-scale and multi-sensor data fusion strategy in the front end of perception and accomplishes a multi-sensor function disparity map generation scheme.A binocular stereo vision sensor composed of two cameras and a light deterction and ranging(LiDAR)sensor is used to jointly perceive the environment,and a multi-scale fusion scheme is employed to improve the accuracy of the disparity map.This solution not only has the advantages of dense perception of binocular stereo vision sensors but also considers the perception accuracy of LiDAR sensors.Experiments demonstrate that the multi-scale multi-sensor scheme proposed in this paper significantly improves disparity map estimation.

A Hand Features Based Fusion Recognition Network with Enhancing Multi-Modal Correlation

Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.

Adaptation analysis and fusion correction method of CMIP6 precipitation simulation data on the Qinghai-Tibetan Plateau

In order to obtain more accurate precipitation data and better simulate the precipitation on the Tibetan Plateau,the simulation capability of 14 Coupled Model Intercomparison Project Phase 6(CMIP6)models of historical precipitation(1982-2014)on the Qinghai-Tibetan Plateau was evaluated in this study.Results indicate that all models exhibit an overestimation of precipitation through the analysis of the Taylor index,temporal and spatial statistical parameters.To correct the overestimation,a fusion correction method combining the Backpropagation Neural Network Correction(BP)and Quantum Mapping(QM)correction,named BQ method,was proposed.With this method,the historical precipitation of each model was corrected in space and time,respectively.The correction results were then analyzed in time,space,and analysis of variance(ANOVA)with those corrected by the BP and QM methods,respectively.Finally,the fusion correction method results for each model were compared with the Climatic Research Unit(CRU)data for significance analysis to obtain the trends of precipitation increase and decrease for each model.The results show that the IPSL-CM6A-LR model is relatively good in simulating historical precipitation on the Qinghai-Tibetan Plateau(R=0.7,RSME=0.15)among the uncorrected data.In terms of time,the total precipitation corrected by the fusion method has the same interannual trend and the closest precipitation values to the CRU data;In terms of space,the annual average precipitation corrected by the fusion method has the smallest difference with the CRU data,and the total historical annual average precipitation is not significantly different from the CRU data,which is better than BP and QM.Therefore,the correction effect of the fusion method on the historical precipitation of each model is better than that of the QM and BP methods.The precipitation in the central and northeastern parts of the plateau shows a significant increasing trend.The correlation coefficients between monthly precipitation and site-detected precipitation for all models after BQ correction exceed 0.8.

Neutron irradiation influence on high-power thyristor device under fusion environment

Because of their economy and applicability,high-power thyristor devices are widely used in the power supply systems for large fusion devices.When high-dose neutrons produced by deuterium–tritium(D–T)fusion reactions are irradiated on a thyristor device for a long time,the electrical characteristics of the device change,which may eventually cause irreversible damage.In this study,with the thyristor switch of the commutation circuit in the quench protection system(QPS)of a fusion device as the study object,the relationship between the internal physical structure and external electrical parameters of the irradiated thyristor is established.Subsequently,a series of targeted thyristor physical simulations and neutron irradiation experiments are conducted to verify the accuracy of the theoretical analysis.In addition,the effect of irradiated thyristor electrical characteristic changes on the entire QPS is studied by accurate simulation,providing valuable guidelines for the maintenance and renovation of the QPS.

High-Efficiency Dynamic Scanning Strategy for Powder Bed Fusion by Controlling Temperature Field of the Heat-Affected Zone

Improvement of fabrication efficiency and part performance was the main challenge for the large-scale powder bed fusion(PBF)process.In this study,a dynamic monitoring and feedback system of powder bed temperature field using an infrared thermal imager has been established and integrated into a four-laser PBF equipment with a working area of 2000 mm×2000 mm.The heat-affected zone(HAZ)temperature field has been controlled by adjusting the scanning speed dynamically.Simultaneously,the relationship among spot size,HAZ temperature,and part performance has been established.The fluctuation of the HAZ temperature in four-laser scanning areas was decreased from 30.85℃to 17.41℃.Thus,the consistency of the sintering performance of the produced large component has been improved.Based on the controllable temperature field,a dynamically adjusting strategy for laser spot size was proposed,by which the fabrication efficiency was improved up to 65.38%.The current research results were of great significance to the further industrial applications of large-scale PBF equipment.

Research on Optimal Preload Method of Controllable Rolling Bearing Based on Multisensor Fusion

Angular contact ball bearings have been widely used in machine tool spindles,and the bearing preload plays an important role in the performance of the spindle.In order to solve the problems of the traditional optimal preload prediction method limited by actual conditions and uncertainties,a roller bearing preload test method based on the improved D-S evidence theorymulti-sensor fusion method was proposed.First,a novel controllable preload system is proposed and evaluated.Subsequently,multiple sensors are employed to collect data on the bearing parameters during preload application.Finally,a multisensor fusion algorithm is used to make predictions,and a neural network is used to optimize the fitting of the preload data.The limitations of conventional preload testing methods are identified,and the integration of complementary information frommultiple sensors is used to achieve accurate predictions,offering valuable insights into the optimal preload force.Experimental results demonstrate that the multi-sensor fusion approach outperforms traditional methods in accurately measuring the optimal preload for rolling bearings.

Research on Driver’s Fatigue Detection Based on Information Fusion

Driving fatigue is a physiological phenomenon that often occurs during driving.After the driver enters a fatigued state,the attentionis lax,the response is slow,and the ability todeal with emergencies is significantly reduced,which can easily cause traffic accidents.Therefore,studying driver fatigue detectionmethods is significant in ensuring safe driving.However,the fatigue state of actual drivers is easily interfered with by the external environment(glasses and light),which leads to many problems,such as weak reliability of fatigue driving detection.Moreover,fatigue is a slow process,first manifested in physiological signals and then reflected in human face images.To improve the accuracy and stability of fatigue detection,this paper proposed a driver fatigue detection method based on image information and physiological information,designed a fatigue driving detection device,built a simulation driving experiment platform,and collected facial as well as physiological information of drivers during driving.Finally,the effectiveness of the fatigue detection method was evaluated.Eye movement feature parameters and physiological signal features of drivers’fatigue levels were extracted.The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features.Accuracy rates of the image,electroencephalogram(EEG),and blood oxygen signals were 86%,82%,and 71%,separately.Information fusion theory was presented to facilitate the fatigue detection effect;the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%.It can be seen that the fatigue driving detectionmethod based onmulti-source feature fusion effectively detected driver fatigue state,and the accuracy rate was higher than that of a single information source.In summary,fatigue drivingmonitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.

Human Gait Recognition for Biometrics Application Based on Deep Learning Fusion Assisted Framework

The demand for a non-contact biometric approach for candidate identification has grown over the past ten years.Based on the most important biometric application,human gait analysis is a significant research topic in computer vision.Researchers have paid a lot of attention to gait recognition,specifically the identification of people based on their walking patterns,due to its potential to correctly identify people far away.Gait recognition systems have been used in a variety of applications,including security,medical examinations,identity management,and access control.These systems require a complex combination of technical,operational,and definitional considerations.The employment of gait recognition techniques and technologies has produced a number of beneficial and well-liked applications.Thiswork proposes a novel deep learning-based framework for human gait classification in video sequences.This framework’smain challenge is improving the accuracy of accuracy gait classification under varying conditions,such as carrying a bag and changing clothes.The proposed method’s first step is selecting two pre-trained deep learningmodels and training fromscratch using deep transfer learning.Next,deepmodels have been trained using static hyperparameters;however,the learning rate is calculated using the particle swarmoptimization(PSO)algorithm.Then,the best features are selected from both trained models using the Harris Hawks controlled Sine-Cosine optimization algorithm.This algorithm chooses the best features,combined in a novel correlation-based fusion technique.Finally,the fused best features are categorized using medium,bi-layer,and tri-layered neural networks.On the publicly accessible dataset known as the CASIA-B dataset,the experimental process of the suggested technique was carried out,and an improved accuracy of 94.14% was achieved.The achieved accuracy of the proposed method is improved by the recent state-of-the-art techniques that show the significance of this work.

An improved particle filter indoor fusion positioning approach based on Wi-Fi/PDR/geomagnetic field

The existing indoor fusion positioning methods based on Pedestrian Dead Reckoning(PDR)and geomagnetic technology have the problems of large initial position error,low sensor accuracy,and geomagnetic mismatch.In this study,a novel indoor fusion positioning approach based on the improved particle filter algorithm by geomagnetic iterative matching is proposed,where Wi-Fi,PDR,and geomagnetic signals are integrated to improve indoor positioning performances.One important contribution is that geomagnetic iterative matching is firstly proposed based on the particle filter algorithm.During the positioning process,an iterative window and a constraint window are introduced to limit the particle generation range and the geomagnetic matching range respectively.The position is corrected several times based on geomagnetic iterative matching in the location correction stage when the pedestrian movement is detected,which made up for the shortage of only one time of geomagnetic correction in the existing particle filter algorithm.In addition,this study also proposes a real-time step detection algorithm based on multi-threshold constraints to judge whether pedestrians are moving,which satisfies the real-time requirement of our fusion positioning approach.Through experimental verification,the average positioning accuracy of the proposed approach reaches 1.59 m,which improves 33.2%compared with the existing particle filter fusion positioning algorithms.

Multimodality Medical Image Fusion Based on Pixel Significance with Edge-Preserving Processing for Clinical Applications

Multimodal medical image fusion has attained immense popularity in recent years due to its robust technology for clinical diagnosis.It fuses multiple images into a single image to improve the quality of images by retaining significant information and aiding diagnostic practitioners in diagnosing and treating many diseases.However,recent image fusion techniques have encountered several challenges,including fusion artifacts,algorithm complexity,and high computing costs.To solve these problems,this study presents a novel medical image fusion strategy by combining the benefits of pixel significance with edge-preserving processing to achieve the best fusion performance.First,the method employs a cross-bilateral filter(CBF)that utilizes one image to determine the kernel and the other for filtering,and vice versa,by considering both geometric closeness and the gray-level similarities of neighboring pixels of the images without smoothing edges.The outputs of CBF are then subtracted from the original images to obtain detailed images.It further proposes to use edge-preserving processing that combines linear lowpass filtering with a non-linear technique that enables the selection of relevant regions in detailed images while maintaining structural properties.These regions are selected using morphologically processed linear filter residuals to identify the significant regions with high-amplitude edges and adequate size.The outputs of low-pass filtering are fused with meaningfully restored regions to reconstruct the original shape of the edges.In addition,weight computations are performed using these reconstructed images,and these weights are then fused with the original input images to produce a final fusion result by estimating the strength of horizontal and vertical details.Numerous standard quality evaluation metrics with complementary properties are used for comparison with existing,well-known algorithms objectively to validate the fusion results.Experimental results from the proposed research article exhibit superior performance compared to other competing techniques in the case of both qualitative and quantitative evaluation.In addition,the proposed method advocates less computational complexity and execution time while improving diagnostic computing accuracy.Nevertheless,due to the lower complexity of the fusion algorithm,the efficiency of fusion methods is high in practical applications.The results reveal that the proposed method exceeds the latest state-of-the-art methods in terms of providing detailed information,edge contour,and overall contrast.

A review on the multi-scaled structures and mechanical/thermal properties of tool steels fabricated by laser powder bed fusion additive manufacturing

The laser powder bed fusion(LPBF) process can integrally form geometrically complex and high-performance metallic parts that have attracted much interest,especially in the molds industry.The appearance of the LPBF makes it possible to design and produce complex conformal cooling channel systems in molds.Thus,LPBF-processed tool steels have attracted more and more attention.The complex thermal history in the LPBF process makes the microstructural characteristics and properties different from those of conventional manufactured tool steels.This paper provides an overview of LPBF-processed tool steels by describing the physical phenomena,the microstructural characteristics,and the mechanical/thermal properties,including tensile properties,wear resistance,and thermal properties.The microstructural characteristics are presented through a multiscale perspective,ranging from densification,meso-structure,microstructure,substructure in grains,to nanoprecipitates.Finally,a summary of tool steels and their challenges and outlooks are introduced.

Recent research progress in the mechanism and suppression of fusion welding-induced liquation cracking of nickel based superalloys

Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at high temperatures.Fusion welding serves as an effective means for joining and repairing these alloys;however,fusion welding-induced liquation cracking has been a challenging issue.This paper comprehensively reviewed recent liquation cracking,discussing the formation mechanisms,cracking criteria,and remedies.In recent investigations,regulating material composition,changing the preweld heat treatment of the base metal,optimizing the welding process parameters,and applying auxiliary control methods are effective strategies for mitigating cracks.To promote the application of nickel-based superalloys,further research on the combination impact of multiple elements on cracking prevention and specific quantitative criteria for liquation cracking is necessary.

A Novel Multi-Stream Fusion Network for Underwater Image Enhancement

Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.

DCEL:classifier fusion model for Android malware detection

The rapid growth of mobile applications,the popularity of the Android system and its openness have attracted many hackers and even criminals,who are creating lots of Android malware.However,the current methods of Android malware detection need a lot of time in the feature engineering phase.Furthermore,these models have the defects of low detection rate,high complexity,and poor practicability,etc.We analyze the Android malware samples,and the distribution of malware and benign software in application programming interface(API)calls,permissions,and other attributes.We classify the software’s threat levels based on the correlation of features.Then,we propose deep neural networks and convolutional neural networks with ensemble learning(DCEL),a new classifier fusion model for Android malware detection.First,DCEL preprocesses the malware data to remove redundant data,and converts the one-dimensional data into a two-dimensional gray image.Then,the ensemble learning approach is used to combine the deep neural network with the convolutional neural network,and the final classification results are obtained by voting on the prediction of each single classifier.Experiments based on the Drebin and Malgenome datasets show that compared with current state-of-art models,the proposed DCEL has a higher detection rate,higher recall rate,and lower computational cost.

Influence of layer thickness on formation quality,microstructure,mechanical properties,and corrosion resistance of WE43 magnesium alloy fabricated by laser powder bed fusion

Laser powder bed fusion(L-PBF)of Mg alloys has provided tremendous opportunities for customized production of aeronautical and medical parts.Layer thickness(LT)is of great significance to the L-PBF process but has not been studied for Mg alloys.In this study,WE43 Mg alloy bulk cubes,porous scaffolds,and thin walls with layer thicknesses of 10,20,30,and 40μm were fabricated.The required laser energy input increased with increasing layer thickness and was different for the bulk cubes and porous scaffolds.Porosity tended to occur at the connection joints in porous scaffolds for LT40 and could be eliminated by reducing the laser energy input.For thin wall parts,a large overhang angle or a small wall thickness resulted in porosity when a large layer thicknesses was used,and the porosity disappeared by reducing the layer thickness or laser energy input.A deeper keyhole penetration was found in all occasions with porosity,explaining the influence of layer thickness,geometrical structure,and laser energy input on the porosity.All the samples achieved a high fusion quality with a relative density of over 99.5%using the optimized laser energy input.The increased layer thickness resulted to more precipitation phases,finer grain sizes and decreased grain texture.With the similar high fusion quality,the tensile strength and elongation of bulk samples were significantly improved from 257 MPa and 1.41%with the 10μm layer to 287 MPa and 15.12%with the 40μm layer,in accordance with the microstructural change.The effect of layer thickness on the compressive properties of porous scaffolds was limited.However,the corrosion rate of bulk samples accelerated with increasing the layer thickness,mainly attributed to the increased number of precipitation phases.

Attention Guided Multi Scale Feature Fusion Network for Automatic Prostate Segmentation

The precise and automatic segmentation of prostate magnetic resonance imaging(MRI)images is vital for assisting doctors in diagnosing prostate diseases.In recent years,many advanced methods have been applied to prostate segmentation,but due to the variability caused by prostate diseases,automatic segmentation of the prostate presents significant challenges.In this paper,we propose an attention-guided multi-scale feature fusion network(AGMSF-Net)to segment prostate MRI images.We propose an attention mechanism for extracting multi-scale features,and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder.In the decoder stage,a feature fusion module is proposed to obtain global context information.We evaluate our model on MRI images of the prostate acquired from a local hospital.The relative volume difference(RVD)and dice similarity coefficient(DSC)between the results of automatic prostate segmentation and ground truth were 1.21%and 93.68%,respectively.To quantitatively evaluate prostate volume on MRI,which is of significant clinical significance,we propose a unique AGMSF-Net.The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.

Microstructure and thermal properties of dissimilar M300–CuCr1Zr alloys by multi-material laser-based powder bed fusion

Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-conductive CuCr1Zr with hard M300 tool steel.Two interface configurations of M300 on CuCr1Zr and CuCr1Zr on M300 were investigated. Ultra-fine grains form at the interface due to the low mutual solubility of Cu and steel. The material mixing zone size is dependent on the configurations and tunable in the range of0.1–0.3 mm by introducing a separate set of parameters for the interface layers. Microcracks and pores mainly occur in the transition zone.Regardless of these defects, the thermal diffusivity of bimetallic parts with 50vol% of CuCr1Zr significantly increases by 70%–150%compared to pure M300. The thermal diffusivity of CuCr1Zr and the hardness of M300 steel can be enhanced simultaneously by applying the aging heat treatment.

Olive Leaf Disease Detection via Wavelet Transform and Feature Fusion of Pre-Trained Deep Learning Models

Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.

Spark plasma sintering of tungsten-based WTaVCr refractory high entropy alloys for nuclear fusion applications

W-based WTaVCr refractory high entropy alloys (RHEA) may be novel and promising candidate materials for plasma facing components in the first wall and diverter in fusion reactors. This alloy has been developed by a powder metallurgy process combining mechanical alloying and spark plasma sintering (SPS). The SPSed samples contained two phases, in which the matrix is RHEA with a body-centered cubic structure, while the oxide phase was most likely Ta2VO6through a combined analysis of X-ray diffraction (XRD),energy-dispersive spectroscopy (EDS), and selected area electron diffraction (SAED). The higher oxygen affinity of Ta and V may explain the preferential formation of their oxide phases based on thermodynamic calculations. Electron backscatter diffraction (EBSD) revealed an average grain size of 6.2μm. WTaVCr RHEA showed a peak compressive strength of 2997 MPa at room temperature and much higher micro-and nano-hardness than W and other W-based RHEAs in the literature. Their high Rockwell hardness can be retained to at least 1000°C.