As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic e...As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.展开更多
Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approa...Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approach in current practices.However,in complex and dynamic traffic scenes,particularly with smaller traffic sign objects,challenges such as missed and false detections can lead to reduced overall detection accuracy.To address this issue,this paper proposes a detection algorithm that integrates edge and shape information.Recognizing that traffic signs have specific shapes and distinct edge contours,this paper introduces an edge feature extraction branch within the backbone network,enabling adaptive fusion with features of the same hierarchical level.Additionally,a shape prior convolution module is designed to replaces the first two convolutional modules of the backbone network,aimed at enhancing the model's perception ability for specific shape objects and reducing its sensitivity to background noise.The algorithm was evaluated on the CCTSDB and TT100k datasets,and compared to YOLOv8s,the mAP50 values increased by 3.0%and 10.4%,respectively,demonstrating the effectiveness of the proposed method in improving the accuracy of traffic sign detection.展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random dom...With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random domain names,hiding the real IP of Command and Control(C&C)servers to build botnets.Due to the randomness and dynamics of DGA,traditional methods struggle to detect them accurately,increasing the difficulty of network defense.This paper proposes a lightweight DGA detection model based on knowledge distillation for resource-constrained IoT environments.Specifically,a teacher model combining CharacterBERT,a bidirectional long short-term memory(BiLSTM)network,and attention mechanism(ATT)is constructed:it extracts character-level semantic features viaCharacterBERT,captures sequence dependencieswith the BiLSTM,and integrates theATT for key feature weighting,formingmulti-granularity feature fusion.An improved knowledge distillation approach transfers the teacher model’s learned knowledge to the simplified DistilBERT student model.Experimental results show the teacher model achieves 98.68%detection accuracy.The student modelmaintains slightly improved accuracy while significantly compressing parameters to approximately 38.4%of the teacher model’s scale,greatly reducing computational overhead for IoT deployment.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
The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing pr...The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing presents substantial security challenges,rendering it a prominent target for sophisticated malware attacks.Existing signature-based and behavior-based detection methods are ineffective against the swiftly evolving nature of malware threats and are constrained by the availability of resources.This paper suggests the Genetic Encoding for Novel Optimization of Malware Evaluation(GENOME)framework,a novel solution that is intended to improve the performance of malware detection and classification in peripheral computing environments.GENOME optimizes data storage and computa-tional efficiency by converting malware artifacts into compact,structured sequences through a Deoxyribonucleic Acid(DNA)encoding mechanism.The framework employs two DNA encoding algorithms,standard and compressed,which substantially reduce data size while preserving high detection accuracy.The Edge-IIoTset dataset was used to conduct experiments that showed that GENOME was able to achieve high classification performance using models such as Random Forest and Logistic Regression,resulting in a reduction of data size by up to 42%.Further evaluations with the CIC-IoT-23 dataset and Deep Learning models confirmed GENOME’s scalability and adaptability across diverse datasets and algorithms.The potential of GENOME to address critical challenges,such as the rapid mutation of malware,real-time processing demands,and resource limitations,is emphasized in this study.GENOME offers comprehensive protection for peripheral computing environments by offering a security solution that is both efficient and scalable.展开更多
In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address t...In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address these challenges,this paper proposes an improved detection algorithm based on YOLOv11n.First,a Dynamic Multi-Scale Feature Fusion and Adaptive Weighting approach is employed to design an Adaptive Focused Diffusion Pyramid Network(AFDPN),which enhances the feature expression and transmission capability of shallow small targets,thereby reducing the loss of detailed information.Then,combined with an Edge Enhancement(EE)module,the model improves the extraction of infrared small target edge features through low-frequency suppression and high-frequency enhancement strategies.Experimental results on the publicly available HIT-UAV dataset show that the improved model achieves a 3.8%increase in average detection accuracy and a 3.0%improvement in recall rate compared to YOLOv11n,with a computational cost of only 9.1 GFLOPS.In comparison experiments,the detection accuracy and model size balance achieved the optimal solution,meeting the lightweight deployment requirements for drone-based systems.This method provides a high-precision,lightweight solution for small target detection in drone-based infrared imagery.展开更多
Edge computing(EC)combined with the Internet of Things(IoT)provides a scalable and efficient solution for smart homes.Therapid proliferation of IoT devices poses real-time data processing and security challenges.EC ha...Edge computing(EC)combined with the Internet of Things(IoT)provides a scalable and efficient solution for smart homes.Therapid proliferation of IoT devices poses real-time data processing and security challenges.EC has become a transformative paradigm for addressing these challenges,particularly in intrusion detection and anomaly mitigation.The widespread connectivity of IoT edge networks has exposed them to various security threats,necessitating robust strategies to detect malicious activities.This research presents a privacy-preserving federated anomaly detection framework combined with Bayesian game theory(BGT)and double deep Q-learning(DDQL).The proposed framework integrates BGT to model attacker and defender interactions for dynamic threat level adaptation and resource availability.It also models a strategic layout between attackers and defenders that takes into account uncertainty.DDQL is incorporated to optimize decision-making and aids in learning optimal defense policies at the edge,thereby ensuring policy and decision optimization.Federated learning(FL)enables decentralized and unshared anomaly detection for sensitive data between devices.Data collection has been performed from various sensors in a real-time EC-IoT network to identify irregularities that occurred due to different attacks.The results reveal that the proposed model achieves high detection accuracy of up to 98%while maintaining low resource consumption.This study demonstrates the synergy between game theory and FL to strengthen anomaly detection in EC-IoT networks.展开更多
Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of t...Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of the searched point to determine the next search point during the search process,reducing the uncertainty in the random search process.Due to the ability of the Bayesian algorithm to reduce uncertainty,a Bayesian ACO algorithm is proposed in this paper to increase the convergence speed of the conventional ACO algorithm for image edge detection.In addition,this paper has the following two innovations on the basis of the classical algorithm,one of which is to add random perturbations after completing the pheromone update.The second is the use of adaptive pheromone heuristics.Experimental results illustrate that the proposed Bayesian ACO algorithm has faster convergence and higher precision and recall than the traditional ant colony algorithm,due to the improvement of the pheromone utilization rate.Moreover,Bayesian ACO algorithm outperforms the other comparative methods in edge detection task.展开更多
By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components ...By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components in different transformed sub-images corresponding to a pixel are employed to form a feature vector of the pixel. All the feature vectors are classified with unsupervised fuzzy c-means to segment the image, and then the edge pixels are checked out by the Canny detector. A series of images contaminated with different intensive Gaussian noises are used to test the novel algorithm. Experiments show that fairly precise edges can be checked out robustly from those images with fairly intensive noise by the proposed algorithm.展开更多
Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies...Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies. Large deviations between model and true edges are common because of the interference of depth and errors in computing the derivatives; thus, edge detection methods cannot provide information about the depth of the source. To simultaneously obtain the horizontal extent and depth of geophysical anomalies, we use normalized edge detection filters, which normalize the edge detection function at different depths, and the maxima that correspond to the location of the source. The errors between model and actual edges are minimized as the depth of the source decreases and the normalized edge detection method recognizes the extent of the source based on the maxima, allowing for reliable model results. We demonstrate the applicability of the normalized edge detection filters in defining the horizontal extent and depth using synthetic and actual aeromagnetic data.展开更多
This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. ...This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. It not only has higher speed but also can extract the edge better. Finally, an example of 2D image is given to demonstrate the usefulness and advantages of the algorithm.展开更多
Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fu...Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fuzzy probability and fuzzy partition. The relation of the probability partition and the fuzzy c-partition of the image gradient are used in the algorithm. Secondly, based on the conditional probabilities and the fuzzy partition, the optimal thresholding is searched adaptively through the maximum fuzzy entropy principle, and then the edge image is obtained. Lastly, an edge-enhancing procedure is executed on the edge image. The experimental results show that the proposed approach performs well.展开更多
Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduce...Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduces the classical edge detection Methods,bug method is used to track the boundaries of tobacco leaf extractly.The test shows that the algorithm has a good edge extraction capability.展开更多
This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge det...This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge detection process. The way of marking edge point coordinates and stability of moving image also is analyzed. The method reforms the conventional design of the 2-D vision detection system. Moreover,it facilitates the design of the systematic mechanical construction,is convenient to compile instrument systemsoftware,and realizes to detect and track display image simultaneously. By the work,the tool detection system is improved to practical application.展开更多
Due to the growth of smart cities,many real-time systems have been developed to support smart cities using Internet of Things(IoT)and emerging technologies.They are formulated to collect the data for environment monit...Due to the growth of smart cities,many real-time systems have been developed to support smart cities using Internet of Things(IoT)and emerging technologies.They are formulated to collect the data for environment monitoring and automate the communication process.In recent decades,researchers have made many efforts to propose autonomous systems for manipulating network data and providing on-time responses in critical operations.However,the widespread use of IoT devices in resource-constrained applications and mobile sensor networks introduces significant research challenges for cybersecurity.These systems are vulnerable to a variety of cyberattacks,including unauthorized access,denial-of-service attacks,and data leakage,which compromise the network’s security.Additionally,uneven load balancing between mobile IoT devices,which frequently experience link interferences,compromises the trustworthiness of the system.This paper introduces a Multi-Agent secured framework using lightweight edge computing to enhance cybersecurity for sensor networks,aiming to leverage artificial intelligence for adaptive routing and multi-metric trust evaluation to achieve data privacy and mitigate potential threats.Moreover,it enhances the efficiency of distributed sensors for energy consumption through intelligent data analytics techniques,resulting in highly consistent and low-latency network communication.Using simulations,the proposed framework reveals its significant performance compared to state-of-the-art approaches for energy consumption by 43%,latency by 46%,network throughput by 51%,packet loss rate by 40%,and denial of service attacks by 42%.展开更多
Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named c...Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named correlation coefficient of multidirectional standard deviations（CCMS） that is solely based on statistics. First, we prove the reliability of the proposed method using a single model and then a combination of models. The proposed method is evaluated by comparing the results with those obtained by other edge-detection methods. The CCMS method offers outstanding recognition, retains the sharpness of details, and has low sensitivity to noise. We also applied the CCMS method to Bouguer anomaly data of a potash deposit in Laos. The applicability of the CCMS method is shown by comparing the inferred tectonic framework to that inferred from remote sensing（RS） data.展开更多
A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled conto...A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.展开更多
Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method ...Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.展开更多
To cope with the problems that edge detection operators are liable to make the detected edges too blurry for synthetic aperture radar(SAR)images,an edge detection method for detecting river in SAR images is proposed b...To cope with the problems that edge detection operators are liable to make the detected edges too blurry for synthetic aperture radar(SAR)images,an edge detection method for detecting river in SAR images is proposed based on contourlet modulus maxima and improved mathematical morphology.The SAR image is firstly transformed to a contourlet domain.According to the directional information and gradient information of directional subband of contourlet transform,the modulus maximum and the improved mathematical morphology are used to detect high frequency and low frequency sub-image edges,respectively.Subsequently,the edges of river in SAR image are obtained after fusing the high frequency sub-image and the low frequency sub-image.Experimental results demonstrate that the proposed edge detection method can obtain more accurate edge location and reduce false edges,compared with the Canny method,the method based on wavelet and Canny,the method based on contourlet modulus maxima,and the method based on improved(ROEWA).The obtained river edges are complete and clear.展开更多
基金supported by the National Natural Science Foundation of China 62402171.
文摘As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.
基金supported by the National Natural Science Foundation of China(Grant Nos.62572057,62272049,U24A20331)Beijing Natural Science Foundation(Grant Nos.4232026,4242020)Academic Research Projects of Beijing Union University(Grant No.ZK10202404).
文摘Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approach in current practices.However,in complex and dynamic traffic scenes,particularly with smaller traffic sign objects,challenges such as missed and false detections can lead to reduced overall detection accuracy.To address this issue,this paper proposes a detection algorithm that integrates edge and shape information.Recognizing that traffic signs have specific shapes and distinct edge contours,this paper introduces an edge feature extraction branch within the backbone network,enabling adaptive fusion with features of the same hierarchical level.Additionally,a shape prior convolution module is designed to replaces the first two convolutional modules of the backbone network,aimed at enhancing the model's perception ability for specific shape objects and reducing its sensitivity to background noise.The algorithm was evaluated on the CCTSDB and TT100k datasets,and compared to YOLOv8s,the mAP50 values increased by 3.0%and 10.4%,respectively,demonstrating the effectiveness of the proposed method in improving the accuracy of traffic sign detection.
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
基金supported by the following projects:National Natural Science Foundation of China(62461041)Natural Science Foundation of Jiangxi Province China(20242BAB25068).
文摘With the large-scale deployment of the Internet ofThings(IoT)devices,their weak securitymechanisms make them prime targets for malware attacks.Attackers often use Domain Generation Algorithm(DGA)to generate random domain names,hiding the real IP of Command and Control(C&C)servers to build botnets.Due to the randomness and dynamics of DGA,traditional methods struggle to detect them accurately,increasing the difficulty of network defense.This paper proposes a lightweight DGA detection model based on knowledge distillation for resource-constrained IoT environments.Specifically,a teacher model combining CharacterBERT,a bidirectional long short-term memory(BiLSTM)network,and attention mechanism(ATT)is constructed:it extracts character-level semantic features viaCharacterBERT,captures sequence dependencieswith the BiLSTM,and integrates theATT for key feature weighting,formingmulti-granularity feature fusion.An improved knowledge distillation approach transfers the teacher model’s learned knowledge to the simplified DistilBERT student model.Experimental results show the teacher model achieves 98.68%detection accuracy.The student modelmaintains slightly improved accuracy while significantly compressing parameters to approximately 38.4%of the teacher model’s scale,greatly reducing computational overhead for IoT deployment.
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supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)(Project Nos.RS-2024-00438551,30%,2022-11220701,30%,2021-0-01816,30%)the National Research Foundation of Korea(NRF)grant funded by the Korean Government(Project No.RS2023-00208460,10%).
文摘The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing presents substantial security challenges,rendering it a prominent target for sophisticated malware attacks.Existing signature-based and behavior-based detection methods are ineffective against the swiftly evolving nature of malware threats and are constrained by the availability of resources.This paper suggests the Genetic Encoding for Novel Optimization of Malware Evaluation(GENOME)framework,a novel solution that is intended to improve the performance of malware detection and classification in peripheral computing environments.GENOME optimizes data storage and computa-tional efficiency by converting malware artifacts into compact,structured sequences through a Deoxyribonucleic Acid(DNA)encoding mechanism.The framework employs two DNA encoding algorithms,standard and compressed,which substantially reduce data size while preserving high detection accuracy.The Edge-IIoTset dataset was used to conduct experiments that showed that GENOME was able to achieve high classification performance using models such as Random Forest and Logistic Regression,resulting in a reduction of data size by up to 42%.Further evaluations with the CIC-IoT-23 dataset and Deep Learning models confirmed GENOME’s scalability and adaptability across diverse datasets and algorithms.The potential of GENOME to address critical challenges,such as the rapid mutation of malware,real-time processing demands,and resource limitations,is emphasized in this study.GENOME offers comprehensive protection for peripheral computing environments by offering a security solution that is both efficient and scalable.
文摘In the context of target detection under infrared conditions for drones,the common issues of high missed detection rates,low signal-to-noise ratio,and blurred edge features for small targets are prevalent.To address these challenges,this paper proposes an improved detection algorithm based on YOLOv11n.First,a Dynamic Multi-Scale Feature Fusion and Adaptive Weighting approach is employed to design an Adaptive Focused Diffusion Pyramid Network(AFDPN),which enhances the feature expression and transmission capability of shallow small targets,thereby reducing the loss of detailed information.Then,combined with an Edge Enhancement(EE)module,the model improves the extraction of infrared small target edge features through low-frequency suppression and high-frequency enhancement strategies.Experimental results on the publicly available HIT-UAV dataset show that the improved model achieves a 3.8%increase in average detection accuracy and a 3.0%improvement in recall rate compared to YOLOv11n,with a computational cost of only 9.1 GFLOPS.In comparison experiments,the detection accuracy and model size balance achieved the optimal solution,meeting the lightweight deployment requirements for drone-based systems.This method provides a high-precision,lightweight solution for small target detection in drone-based infrared imagery.
基金The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through the Large Group Project under grant number(RGP2/337/46)The research team thanks the Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/SERC/13/352-4.
文摘Edge computing(EC)combined with the Internet of Things(IoT)provides a scalable and efficient solution for smart homes.Therapid proliferation of IoT devices poses real-time data processing and security challenges.EC has become a transformative paradigm for addressing these challenges,particularly in intrusion detection and anomaly mitigation.The widespread connectivity of IoT edge networks has exposed them to various security threats,necessitating robust strategies to detect malicious activities.This research presents a privacy-preserving federated anomaly detection framework combined with Bayesian game theory(BGT)and double deep Q-learning(DDQL).The proposed framework integrates BGT to model attacker and defender interactions for dynamic threat level adaptation and resource availability.It also models a strategic layout between attackers and defenders that takes into account uncertainty.DDQL is incorporated to optimize decision-making and aids in learning optimal defense policies at the edge,thereby ensuring policy and decision optimization.Federated learning(FL)enables decentralized and unshared anomaly detection for sensitive data between devices.Data collection has been performed from various sensors in a real-time EC-IoT network to identify irregularities that occurred due to different attacks.The results reveal that the proposed model achieves high detection accuracy of up to 98%while maintaining low resource consumption.This study demonstrates the synergy between game theory and FL to strengthen anomaly detection in EC-IoT networks.
基金supported by the National Natural Science Foundation of China(62276055).
文摘Ant colony optimization(ACO)is a random search algorithm based on probability calculation.However,the uninformed search strategy has a slow convergence speed.The Bayesian algorithm uses the historical information of the searched point to determine the next search point during the search process,reducing the uncertainty in the random search process.Due to the ability of the Bayesian algorithm to reduce uncertainty,a Bayesian ACO algorithm is proposed in this paper to increase the convergence speed of the conventional ACO algorithm for image edge detection.In addition,this paper has the following two innovations on the basis of the classical algorithm,one of which is to add random perturbations after completing the pheromone update.The second is the use of adaptive pheromone heuristics.Experimental results illustrate that the proposed Bayesian ACO algorithm has faster convergence and higher precision and recall than the traditional ant colony algorithm,due to the improvement of the pheromone utilization rate.Moreover,Bayesian ACO algorithm outperforms the other comparative methods in edge detection task.
文摘By combining multiscale stationary wavelet analysis with fuzzy c-means, a robust edge detection algorithm is presented. Based on the translation invafiance built in multiscale stationary wavelet transform, components in different transformed sub-images corresponding to a pixel are employed to form a feature vector of the pixel. All the feature vectors are classified with unsupervised fuzzy c-means to segment the image, and then the edge pixels are checked out by the Canny detector. A series of images contaminated with different intensive Gaussian noises are used to test the novel algorithm. Experiments show that fairly precise edges can be checked out robustly from those images with fairly intensive noise by the proposed algorithm.
基金supported by the China Postdoctoral Science Foundation (No.2014M551188)the Deep Exploration in China Sinoprobe-09-01 (No.201011078)
文摘Edge detection is an image processing technique for finding the boundaries of objects within images. It is typically used to interpret gravity and magnetic data, and find the horizontal boundaries of geological bodies. Large deviations between model and true edges are common because of the interference of depth and errors in computing the derivatives; thus, edge detection methods cannot provide information about the depth of the source. To simultaneously obtain the horizontal extent and depth of geophysical anomalies, we use normalized edge detection filters, which normalize the edge detection function at different depths, and the maxima that correspond to the location of the source. The errors between model and actual edges are minimized as the depth of the source decreases and the normalized edge detection method recognizes the extent of the source based on the maxima, allowing for reliable model results. We demonstrate the applicability of the normalized edge detection filters in defining the horizontal extent and depth using synthetic and actual aeromagnetic data.
文摘This paper presents an algorithm of edge detection in image processing. A new entropy operator and threshold estimation technique are effectively proposed. The algorithm overcomes some drawbacks of Shiozaki operator. It not only has higher speed but also can extract the edge better. Finally, an example of 2D image is given to demonstrate the usefulness and advantages of the algorithm.
文摘Based upon the maximum entropy theorem of information theory, a novel fuzzy approach for edge detection is presented. Firstly, a definition of fuzzy partition entropy is proposed after introducing the concepts of fuzzy probability and fuzzy partition. The relation of the probability partition and the fuzzy c-partition of the image gradient are used in the algorithm. Secondly, based on the conditional probabilities and the fuzzy partition, the optimal thresholding is searched adaptively through the maximum fuzzy entropy principle, and then the edge image is obtained. Lastly, an edge-enhancing procedure is executed on the edge image. The experimental results show that the proposed approach performs well.
基金Supported by Key Technologies R & D Program of Henan Province(082102210065)Natural Science Research Project of Henan Educational Committee(2007210005)~~
文摘Tobacco leaf shapes including the length,width,area,perimeter and roundness parameters and so on,Only obtain exact boundaries of the leaf information to calculate a large number of leaf parameters.This paper introduces the classical edge detection Methods,bug method is used to track the boundaries of tobacco leaf extractly.The test shows that the algorithm has a good edge extraction capability.
文摘This paper describes a technology of dynamic display moving image by computer monitor,which is initially used in the design of tool detection system. The paper presents the hardware and software principie and edge detection process. The way of marking edge point coordinates and stability of moving image also is analyzed. The method reforms the conventional design of the 2-D vision detection system. Moreover,it facilitates the design of the systematic mechanical construction,is convenient to compile instrument systemsoftware,and realizes to detect and track display image simultaneously. By the work,the tool detection system is improved to practical application.
基金supported by the Deanship of Graduate Studies and Scientific Research at Jouf University.
文摘Due to the growth of smart cities,many real-time systems have been developed to support smart cities using Internet of Things(IoT)and emerging technologies.They are formulated to collect the data for environment monitoring and automate the communication process.In recent decades,researchers have made many efforts to propose autonomous systems for manipulating network data and providing on-time responses in critical operations.However,the widespread use of IoT devices in resource-constrained applications and mobile sensor networks introduces significant research challenges for cybersecurity.These systems are vulnerable to a variety of cyberattacks,including unauthorized access,denial-of-service attacks,and data leakage,which compromise the network’s security.Additionally,uneven load balancing between mobile IoT devices,which frequently experience link interferences,compromises the trustworthiness of the system.This paper introduces a Multi-Agent secured framework using lightweight edge computing to enhance cybersecurity for sensor networks,aiming to leverage artificial intelligence for adaptive routing and multi-metric trust evaluation to achieve data privacy and mitigate potential threats.Moreover,it enhances the efficiency of distributed sensors for energy consumption through intelligent data analytics techniques,resulting in highly consistent and low-latency network communication.Using simulations,the proposed framework reveals its significant performance compared to state-of-the-art approaches for energy consumption by 43%,latency by 46%,network throughput by 51%,packet loss rate by 40%,and denial of service attacks by 42%.
基金supported by the National Hi-Tech Research and Development Program of China(863 Program)(No.2006AA06Z107)the National Natural Science Foundation of China(No.40930314)
文摘Most edge-detection methods rely on calculating gradient derivatives of the potential field, a process that is easily affected by noise and is therefore of low stability. We propose a new edge-detection method named correlation coefficient of multidirectional standard deviations（CCMS） that is solely based on statistics. First, we prove the reliability of the proposed method using a single model and then a combination of models. The proposed method is evaluated by comparing the results with those obtained by other edge-detection methods. The CCMS method offers outstanding recognition, retains the sharpness of details, and has low sensitivity to noise. We also applied the CCMS method to Bouguer anomaly data of a potash deposit in Laos. The applicability of the CCMS method is shown by comparing the inferred tectonic framework to that inferred from remote sensing（RS） data.
基金The National Key Technologies R&D Program during the 12th Five-Year Period of China(No.2012BAJ23B02)Science and Technology Support Program of Jiangsu Province(No.BE2010606)
文摘A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.
文摘Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.
基金Supported by the CRSRI Open Research Program(CKWV2013225/KY)the Open Project Foundation of Key Laboratory of the Yellow River Sediment of Ministry of Water Resource(2014006)+2 种基金the Open Project Foundation of Key Lab of Port,Waterway and Sedimentation Engineering of the Ministry of Transportthe State Key Lab of Urban Water Resource and Environment(HIT)(ES201409)the Priority Academic Program Development of Jiangsu Higher Education Institution
文摘To cope with the problems that edge detection operators are liable to make the detected edges too blurry for synthetic aperture radar(SAR)images,an edge detection method for detecting river in SAR images is proposed based on contourlet modulus maxima and improved mathematical morphology.The SAR image is firstly transformed to a contourlet domain.According to the directional information and gradient information of directional subband of contourlet transform,the modulus maximum and the improved mathematical morphology are used to detect high frequency and low frequency sub-image edges,respectively.Subsequently,the edges of river in SAR image are obtained after fusing the high frequency sub-image and the low frequency sub-image.Experimental results demonstrate that the proposed edge detection method can obtain more accurate edge location and reduce false edges,compared with the Canny method,the method based on wavelet and Canny,the method based on contourlet modulus maxima,and the method based on improved(ROEWA).The obtained river edges are complete and clear.
