Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and comple...Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet ...Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.展开更多
Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This st...Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.展开更多
Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially...Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially leading to false positives or missed detections.To solve these problems,the YOLOv8 network is enhanced by adding deformable convolution and atrous spatial pyramid pooling(ASPP),along with the integration of a coordinate attention(CA)mechanism.This allows the network to focus on small targets while expanding the receptive field without losing resolution.At the same time,context information on the target is gathered and feature expression is enhanced by attention modules in different directions.It effectively improves the positioning accuracy and achieves good results on the LUNA16 dataset.Compared with other detection algorithms,it improves the accuracy of pulmonary nodule detection to a certain extent.展开更多
Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and text...Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.展开更多
To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(...To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(WPD)and enhanced deep learning techniques.In the proposed method,an agent at the receiver processes the received signal using WPD to generate an initial Spectrogram Waterfall(SW),which is subsequently segmented using a sliding window to serve as the input for the jamming recognition network.The network employs a bilateral filter to preprocess the input SW,thereby enhancing the edge features of the jamming signals.To extract abstract features,depthwise separable convolution is utilized instead of traditional convolution,thereby reducing the network’s parameter count and enhancing real-time performance.A pyramid pooling layer is integrated before the fully connected layer to enable the network to process input SW of varying sizes,thus enhancing scalability.During network training,adaptive moment estimation is employed as the optimizer,allowing the network to dynamically adjust the learning rate and accelerate convergence.A comprehensive comparison between the proposed jamming recognition network and six other models is conducted,along with Ablation Experiments(AE)based on numerical simulations.Simulation results demonstrate that the proposed method based on WPD and enhanced deep learning achieves high-precision recognition of various jamming patterns while maintaining a favorable balance among prediction accuracy,network complexity,and prediction time.展开更多
Tension-compression asymmetry is a critical concern for magnesium(Mg)alloys,particularly in automo-tive crash structures.This study systematically examines the tension-compression asymmetry of a cast Mg-Gd-Y alloy at ...Tension-compression asymmetry is a critical concern for magnesium(Mg)alloys,particularly in automo-tive crash structures.This study systematically examines the tension-compression asymmetry of a cast Mg-Gd-Y alloy at various strain rates.Experimental results indicate symmetric yielding stress under both tension and compression at all strain rates,along with a reduction in the tension-compression asym-metry of ultimate stress and plastic strain as the strain rate increases.This trend arises from an unusual strain rate-dependent tension-compression asymmetry,characterized by strain rate toughening in tension and negligible strain rate effect in compression.The differing behavior is linked to the distinct twinning mechanisms under tension and compression.The suppression of twinning under tension contributes to the positive strain rate dependence of pyramidal slip,whereas the activation of abundant twins during compression means that pyramidal slip is unnecessary to accommodate c-axis strain,leading to the ab-sence of a strain rate effect in compression.Abundant twins nucleate consistently from yielding to 2%strain,but only after basal and prismaticslip have mediated microplasticity,suggesting that these slip systems reduce the nucleation stress for twinning during compression,resulting in a lower activation stress for twinning compared to tension.This study provides new insights into micromechanisms of the tension-compression asymmetry in cast Mg-Gd-Y alloys and offers practical guidance for the application of these materials in critical components that must endure both tension and compression under varying strain rates.展开更多
Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones...Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.展开更多
Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportatio...Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.展开更多
Archaeologists(考古学家)have unearthed the remains of a Mayan city nearly 3,000 years old in northern Guatemala,with pyramids(金字塔)and monuments that showcase its significance as an important ceremonial site.The May...Archaeologists(考古学家)have unearthed the remains of a Mayan city nearly 3,000 years old in northern Guatemala,with pyramids(金字塔)and monuments that showcase its significance as an important ceremonial site.The Mayan civilization arose around 2000 BC,reaching its height between 400 AD and 900 AD in what is present-day southern Mexico and Guatemala,as well as parts of Belize,El Salvador and Honduras.展开更多
Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of intersp...Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.展开更多
Pyramidal dislocations are important for ductility enhancement of magnesium alloys.In this work,molecular dynamics simulations were employed to study the gliding behavior of pyramidal(c+a)dislocations under c-axis com...Pyramidal dislocations are important for ductility enhancement of magnesium alloys.In this work,molecular dynamics simulations were employed to study the gliding behavior of pyramidal(c+a)dislocations under c-axis compressive loading and tensile loading.The Peierls stress of Py-Ⅰ dislocation shows strong tension-compression asymmetry.However,no tension-compression asymmetry is seen on the Py-Ⅱ dislocation and basal dislocation.The tension-compression asymmetry origins from the asymmetry of partial dislocations of Py-Ⅰ dislocation,which leads to the dislocation core contracted under c-axis compressive loading and expanded under tensile loading.By analyzing the forces acting on the partial dislocations,we defined a neutral direction,which deviates from the full dislocation Burgers vector by 70.3°.The neutral direction is dependent on the ratio of lattice stresses of partial dislocations.If the shear stress is applied along the neutral direction,tension-compression asymmetry is eliminated and the dislocation core is un-contracted/un-expanded.The neutral direction of symmetrical dislocations(Py-Ⅱ dislocation and basal dislocation)is just the full dislocation Burgers vector.The tension-compression asymmetry and dislocation core contraction/expansion have an important influence on the dislocation behaviors,such as cross-slip,decomposition,basaltransition and mobility,which can be used to explain the mechanical behaviors of Mg single-crystals compressed along c-axis.展开更多
Dynamic recrystallization(DRX)in inhomogeneous deformation zones,such as grain boundaries,shear bands,and deformation bands,is critical for texture modification in magnesium alloys during deformation at elevated temper...Dynamic recrystallization(DRX)in inhomogeneous deformation zones,such as grain boundaries,shear bands,and deformation bands,is critical for texture modification in magnesium alloys during deformation at elevated temperatures.This study investigates the DRX mechanisms in AZWX3100 magnesium alloy under plane strain compression at 200℃.Microstructural analysis revealed necklace-type DRX accompanied by evidence of local grain boundary bulging.Additionally,ribbons of recrystallized grains were observed withinfine deformation bands,aligned with theoretical pyramidal I and II slip traces derived from the matrix.The distribution of local misorientation within the deformed microstructure demonstrated a clear association between deformation bands and localized strain.Dislocation analysis of lamellar specimens extracted from two pyramidal slip bands revealed<c+a>dislocations,indicating a connection between<c+a>slip activation and the formation of deformation bands.Crystal plasticity simulations suggest that the orientation of deformation bands is responsible for the unique recrystallization texture of the DRX grains within these bands.The texture characteristics imply a progressive,glide-induced DRX mechanism.A fundamental understanding of the role of deformation bands in texture modification can facilitate future alloy and process design.展开更多
The grain-scale tension-compression(T-C)asymmetric slip behavior and geometrically necessary dislocation(GND)density in an aged and twin-free Mg-10Y sheet were statistically studied using slip trace analysis and elect...The grain-scale tension-compression(T-C)asymmetric slip behavior and geometrically necessary dislocation(GND)density in an aged and twin-free Mg-10Y sheet were statistically studied using slip trace analysis and electron backscatter diffraction(EBSD)analysis.A significantly asymmetric slip activity,i.e.,higher tensile slip activity and proportion of non-basal slip,was manifested.Prismatic〈a〉(37.1%)and basal〈a〉(27.6%)slips dominated the tensile deformation,followed by pyramidalⅡ〈c+a〉slip(20.0%).While during compression,basal〈a〉slip(61.9%)was the most active slip mode,and only 6.9% pyramidalⅡ〈c+a〉slip was observed.The critical resolved shear stress(CRSS)ratio was estimated based on~800 sets of the identified slip traces,which suggested that the CRSS_(pyrⅡ)/CRSS_(bas)for compression was~3 times than that of tension.The pyramidalⅡ〈c+a〉slip was more active when the slip plane was under tension than under compression,which was consistent with the calculated asymmetric CRSS_(pyrⅡ)/CRSS_(bas).The activity of multiple slip,cross slip and slip transfer,as well as the GND density were also T-C asymmetric.This work thoughtfully demonstrated the T-C asymmetric slip behavior and plastic heterogeneity in Mg alloys which was believed to be responsible for the macroscopic T-C asymmetry when twinning was absent.The present statistical results are valuable for validating and/or facilitating crystal plasticity simulations.展开更多
Germanium(Ge)-air battery,a new type of semiconductor-air battery,has garnered increasing attention owing to its environmental friendliness,safety,and excellent dynamic performance.However,the flat Ge anode is prone t...Germanium(Ge)-air battery,a new type of semiconductor-air battery,has garnered increasing attention owing to its environmental friendliness,safety,and excellent dynamic performance.However,the flat Ge anode is prone to passivation,owing to GeO_(2) accumulation on its surface,resulting in premature discharge termination.In this study,various nano-Ge pyramid structures(GePS)were prepared using chemical etching(CE)and metal-assisted chemical etching(MACE)methods to enhance the specific surface area of the Ge anode,thereby facilitating the dissolution of the passivation layer.This study revealed that the MACE method significantly accelerated the etching rate of the Ge surface,producing exceptional GePS.Furthermore,Ge-air batteries employing Ge anodes prepared using MACE demonstrated an exceptional discharge life of up to 9240 h(385 days).The peak power density reached 3.03mW/cm^(2),representing improvements of more than 2 times and 1.8 times,respectively,compared with batteries using flat Ge anodes.This study presents a straightforward approach to enhance Ge anode performance,thereby expanding the potential applications of Ge-air batteries.展开更多
The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(...The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.展开更多
The work aims to investigate the formation and transformation mechanism of non-basal texture in the extruded Mg alloys.With this purpose a pure Mg as reference and eight Mg-Gd binary alloys with the Gd concentration r...The work aims to investigate the formation and transformation mechanism of non-basal texture in the extruded Mg alloys.With this purpose a pure Mg as reference and eight Mg-Gd binary alloys with the Gd concentration ranging from 0.5 wt.%to 18 wt.%were prepared for extrusion.This study shows that the basal fiber texture in pure Mg transited into RE(rare earth)texture in diluted Mg-Gd alloys and into the abnormal C-texture in high-concentration Mg-Gd alloys.In pure Mg,discontinuous dynamic recrystallization plays a predominant role during the extrusion process,resulting in the formation of a typical basal fiber texture.Alloying with high concentration of Gd impedes the dynamic recrystallization process,facilitating the heterogeneous nucleation of shear bands as well as the dynamic recrystallization within shear bands.Dynamic recrystallized grains within shear bands nucleate with a similar orientation to the host deformed parent grains and gradually tilt their c-axis to the extrusion direction during growth by absorbing dislocations,leading to the formation of either the REtexture orientation or the C-texture orientation,depending on the stored energy within shear bands.The analysis aided by IGMA and TEM characterization reveals that the shear bands originate from the extensive but heterogeneous activation of pyramidal I slip.Tensile tests illustrate a close correlation between the fracture elongation and texture types.A comprehensive understanding of the formation and transformation mechanism of different texture components in Mg alloys holds significant importance for the design of high-performance Mg alloys by texture engineering.展开更多
Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding pro...Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.展开更多
基金supported by the National Natural Science Foundation of China(No.62203163)the Scientific Research Project of Hunan Provincial Education Department(No.24A0519)+1 种基金the Hunan Provincial Natural Science Foundation(No.2025JJ60407)the Postgraduate Scientific Research Innovation Project of Hunan Province(No.CX2024100).
文摘Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
基金partially supported by the Natural Science Foundation of Shandong Province,China(No.ZR2023ME009)the National Natural Science Foundation of China(No.51909252)。
文摘Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004)Supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korean government(MSIT)(No.RS-2022-00155885,Artificial Intelligence Convergence Innovation Human Resources Development(Hanyang University ERICA)).
文摘Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.
文摘Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially leading to false positives or missed detections.To solve these problems,the YOLOv8 network is enhanced by adding deformable convolution and atrous spatial pyramid pooling(ASPP),along with the integration of a coordinate attention(CA)mechanism.This allows the network to focus on small targets while expanding the receptive field without losing resolution.At the same time,context information on the target is gathered and feature expression is enhanced by attention modules in different directions.It effectively improves the positioning accuracy and achieves good results on the LUNA16 dataset.Compared with other detection algorithms,it improves the accuracy of pulmonary nodule detection to a certain extent.
基金Shenzhen Institute of Artificial Intelligence and Robotics for Society,Grant/Award Number:AC01202201003-02GuangDong Basic and Applied Basic Research Foundation,Grant/Award Number:2024A1515010252Longgang District Shenzhen's“Ten Action Plan”for Supporting Innovation Projects,Grant/Award Number:LGKCSDPT2024002。
文摘Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.
基金supported by National Natural Science Foundation of China under Grant U23A20279China Electronics Tian’ao Innovation Theory and Technology Group Fund under Grand 20221193-04-04.
文摘To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(WPD)and enhanced deep learning techniques.In the proposed method,an agent at the receiver processes the received signal using WPD to generate an initial Spectrogram Waterfall(SW),which is subsequently segmented using a sliding window to serve as the input for the jamming recognition network.The network employs a bilateral filter to preprocess the input SW,thereby enhancing the edge features of the jamming signals.To extract abstract features,depthwise separable convolution is utilized instead of traditional convolution,thereby reducing the network’s parameter count and enhancing real-time performance.A pyramid pooling layer is integrated before the fully connected layer to enable the network to process input SW of varying sizes,thus enhancing scalability.During network training,adaptive moment estimation is employed as the optimizer,allowing the network to dynamically adjust the learning rate and accelerate convergence.A comprehensive comparison between the proposed jamming recognition network and six other models is conducted,along with Ablation Experiments(AE)based on numerical simulations.Simulation results demonstrate that the proposed method based on WPD and enhanced deep learning achieves high-precision recognition of various jamming patterns while maintaining a favorable balance among prediction accuracy,network complexity,and prediction time.
基金the National Natural Science Foundation of China(grant Nos.11988102,52301146,51301173,51531002,52171055,52371037,51601193)the National Key Research and Development Program of China(grant No.2016YFB0301104)+1 种基金the Fundamental Research Funds for the Central Universities(grant No.2023JG007)China Postdoctoral Science Foundation(grant No.8206300226).
文摘Tension-compression asymmetry is a critical concern for magnesium(Mg)alloys,particularly in automo-tive crash structures.This study systematically examines the tension-compression asymmetry of a cast Mg-Gd-Y alloy at various strain rates.Experimental results indicate symmetric yielding stress under both tension and compression at all strain rates,along with a reduction in the tension-compression asym-metry of ultimate stress and plastic strain as the strain rate increases.This trend arises from an unusual strain rate-dependent tension-compression asymmetry,characterized by strain rate toughening in tension and negligible strain rate effect in compression.The differing behavior is linked to the distinct twinning mechanisms under tension and compression.The suppression of twinning under tension contributes to the positive strain rate dependence of pyramidal slip,whereas the activation of abundant twins during compression means that pyramidal slip is unnecessary to accommodate c-axis strain,leading to the ab-sence of a strain rate effect in compression.Abundant twins nucleate consistently from yielding to 2%strain,but only after basal and prismaticslip have mediated microplasticity,suggesting that these slip systems reduce the nucleation stress for twinning during compression,resulting in a lower activation stress for twinning compared to tension.This study provides new insights into micromechanisms of the tension-compression asymmetry in cast Mg-Gd-Y alloys and offers practical guidance for the application of these materials in critical components that must endure both tension and compression under varying strain rates.
基金supported by the National Natural Science Foundation of China(Nos.62276204 and 62203343)the Fundamental Research Funds for the Central Universities(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470).
文摘Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia through research group No.(RG-NBU-2022-1234).
文摘Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.
文摘Archaeologists(考古学家)have unearthed the remains of a Mayan city nearly 3,000 years old in northern Guatemala,with pyramids(金字塔)and monuments that showcase its significance as an important ceremonial site.The Mayan civilization arose around 2000 BC,reaching its height between 400 AD and 900 AD in what is present-day southern Mexico and Guatemala,as well as parts of Belize,El Salvador and Honduras.
基金funded by Liaoning Provincial Department of Education Project,Award number JYTMS20230418.
文摘Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.
基金financially supported by National Natural Science Foundation of China(12072211,12232008)Foundation of Key laboratory(2022JCJQLB05703)Sichuan Province Science and Technology Project(2023NSFSC0914)。
文摘Pyramidal dislocations are important for ductility enhancement of magnesium alloys.In this work,molecular dynamics simulations were employed to study the gliding behavior of pyramidal(c+a)dislocations under c-axis compressive loading and tensile loading.The Peierls stress of Py-Ⅰ dislocation shows strong tension-compression asymmetry.However,no tension-compression asymmetry is seen on the Py-Ⅱ dislocation and basal dislocation.The tension-compression asymmetry origins from the asymmetry of partial dislocations of Py-Ⅰ dislocation,which leads to the dislocation core contracted under c-axis compressive loading and expanded under tensile loading.By analyzing the forces acting on the partial dislocations,we defined a neutral direction,which deviates from the full dislocation Burgers vector by 70.3°.The neutral direction is dependent on the ratio of lattice stresses of partial dislocations.If the shear stress is applied along the neutral direction,tension-compression asymmetry is eliminated and the dislocation core is un-contracted/un-expanded.The neutral direction of symmetrical dislocations(Py-Ⅱ dislocation and basal dislocation)is just the full dislocation Burgers vector.The tension-compression asymmetry and dislocation core contraction/expansion have an important influence on the dislocation behaviors,such as cross-slip,decomposition,basaltransition and mobility,which can be used to explain the mechanical behaviors of Mg single-crystals compressed along c-axis.
基金by the Deutsche Forschungsgemeinschaft(DFG)through projects 420149269,394480829as part of the CRC1394“Structural and Chemical Atomic Complexity-From Defect Phase Diagrams to Material Properties”(project 409476157).
文摘Dynamic recrystallization(DRX)in inhomogeneous deformation zones,such as grain boundaries,shear bands,and deformation bands,is critical for texture modification in magnesium alloys during deformation at elevated temperatures.This study investigates the DRX mechanisms in AZWX3100 magnesium alloy under plane strain compression at 200℃.Microstructural analysis revealed necklace-type DRX accompanied by evidence of local grain boundary bulging.Additionally,ribbons of recrystallized grains were observed withinfine deformation bands,aligned with theoretical pyramidal I and II slip traces derived from the matrix.The distribution of local misorientation within the deformed microstructure demonstrated a clear association between deformation bands and localized strain.Dislocation analysis of lamellar specimens extracted from two pyramidal slip bands revealed<c+a>dislocations,indicating a connection between<c+a>slip activation and the formation of deformation bands.Crystal plasticity simulations suggest that the orientation of deformation bands is responsible for the unique recrystallization texture of the DRX grains within these bands.The texture characteristics imply a progressive,glide-induced DRX mechanism.A fundamental understanding of the role of deformation bands in texture modification can facilitate future alloy and process design.
基金supported by the National Natural Science Foundation of China(No.52171125)the Sichuan Science and Technology Program(No.2024NSFSC0193)。
文摘The grain-scale tension-compression(T-C)asymmetric slip behavior and geometrically necessary dislocation(GND)density in an aged and twin-free Mg-10Y sheet were statistically studied using slip trace analysis and electron backscatter diffraction(EBSD)analysis.A significantly asymmetric slip activity,i.e.,higher tensile slip activity and proportion of non-basal slip,was manifested.Prismatic〈a〉(37.1%)and basal〈a〉(27.6%)slips dominated the tensile deformation,followed by pyramidalⅡ〈c+a〉slip(20.0%).While during compression,basal〈a〉slip(61.9%)was the most active slip mode,and only 6.9% pyramidalⅡ〈c+a〉slip was observed.The critical resolved shear stress(CRSS)ratio was estimated based on~800 sets of the identified slip traces,which suggested that the CRSS_(pyrⅡ)/CRSS_(bas)for compression was~3 times than that of tension.The pyramidalⅡ〈c+a〉slip was more active when the slip plane was under tension than under compression,which was consistent with the calculated asymmetric CRSS_(pyrⅡ)/CRSS_(bas).The activity of multiple slip,cross slip and slip transfer,as well as the GND density were also T-C asymmetric.This work thoughtfully demonstrated the T-C asymmetric slip behavior and plastic heterogeneity in Mg alloys which was believed to be responsible for the macroscopic T-C asymmetry when twinning was absent.The present statistical results are valuable for validating and/or facilitating crystal plasticity simulations.
基金financially supported by the National Natural Science Foundation of China(No.61904073)Spring City Plan-Special Program for Young Talents(No.K202005007)+2 种基金Yunnan Talents Support Plan for Yong Talents(No.XDYC-QNRC-2022-0482)Yunnan Local Colleges Applied Basic Research Projects(No.202101BA070001-138)Frontier Research Team of Kunming University 2023.
文摘Germanium(Ge)-air battery,a new type of semiconductor-air battery,has garnered increasing attention owing to its environmental friendliness,safety,and excellent dynamic performance.However,the flat Ge anode is prone to passivation,owing to GeO_(2) accumulation on its surface,resulting in premature discharge termination.In this study,various nano-Ge pyramid structures(GePS)were prepared using chemical etching(CE)and metal-assisted chemical etching(MACE)methods to enhance the specific surface area of the Ge anode,thereby facilitating the dissolution of the passivation layer.This study revealed that the MACE method significantly accelerated the etching rate of the Ge surface,producing exceptional GePS.Furthermore,Ge-air batteries employing Ge anodes prepared using MACE demonstrated an exceptional discharge life of up to 9240 h(385 days).The peak power density reached 3.03mW/cm^(2),representing improvements of more than 2 times and 1.8 times,respectively,compared with batteries using flat Ge anodes.This study presents a straightforward approach to enhance Ge anode performance,thereby expanding the potential applications of Ge-air batteries.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(*MSIT)(No.2018R1A5A7059549).
文摘The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.
基金funding from the National Natural Science Foundation of China under Grant No 52275327。
文摘The work aims to investigate the formation and transformation mechanism of non-basal texture in the extruded Mg alloys.With this purpose a pure Mg as reference and eight Mg-Gd binary alloys with the Gd concentration ranging from 0.5 wt.%to 18 wt.%were prepared for extrusion.This study shows that the basal fiber texture in pure Mg transited into RE(rare earth)texture in diluted Mg-Gd alloys and into the abnormal C-texture in high-concentration Mg-Gd alloys.In pure Mg,discontinuous dynamic recrystallization plays a predominant role during the extrusion process,resulting in the formation of a typical basal fiber texture.Alloying with high concentration of Gd impedes the dynamic recrystallization process,facilitating the heterogeneous nucleation of shear bands as well as the dynamic recrystallization within shear bands.Dynamic recrystallized grains within shear bands nucleate with a similar orientation to the host deformed parent grains and gradually tilt their c-axis to the extrusion direction during growth by absorbing dislocations,leading to the formation of either the REtexture orientation or the C-texture orientation,depending on the stored energy within shear bands.The analysis aided by IGMA and TEM characterization reveals that the shear bands originate from the extensive but heterogeneous activation of pyramidal I slip.Tensile tests illustrate a close correlation between the fracture elongation and texture types.A comprehensive understanding of the formation and transformation mechanism of different texture components in Mg alloys holds significant importance for the design of high-performance Mg alloys by texture engineering.
基金the National Natural Science Foundation of China(No.12064027)。
文摘Zn vapour is easily generated on the surface by fusion welding galvanized steel sheet,resulting in the formation of defects.Rapidly developing computer vision sensing technology collects weld images in the welding process,then obtains laser fringe information through digital image processing,identifies welding defects,and finally realizes online control of weld defects.The performance of a convolutional neural network is related to its structure and the quality of the input image.The acquired original images are labeled with LabelMe,and repeated attempts are made to determine the appropriate filtering and edge detection image preprocessing methods.Two-stage convolutional neural networks with different structures are built on the Tensorflow deep learning framework,different thresholds of intersection over union are set,and deep learning methods are used to evaluate the collected original images and the preprocessed images separately.Compared with the test results,the comprehensive performance of the improved feature pyramid networks algorithm based on the basic network VGG16 is lower than that of the basic network Resnet101.Edge detection of the image will significantly improve the accuracy of the model.Adding blur will reduce the accuracy of the model slightly;however,the overall performance of the improved algorithm is still relatively good,which proves the stability of the algorithm.The self-developed software inspection system can be used for image preprocessing and defect recognition,which can be used to record the number and location of typical defects in continuous welds.
