期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到81,835篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
TQU-GraspingObject:3D Common Objects Detection,Recognition,and Localization on Point Cloud for Hand Grasping in Sharing Environments 认领 引用
1
作者 Thi-Loan Nguyen Huy-Nam Chu +2 位作者 The-Thanh Hua Trung-Nghia Phung Van-Hung Le 《Computers, Materials & Continua》 SCIE EI 2026年第5期1701-1722,共22页
To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determ... To support the process of grasping objects on a tabletop for the blind or robotic arm,it is necessary to address fundamental computer vision tasks,such as detecting,recognizing,and locating objects in space,and determining the position of the grasping information.These results can then be used to guide the visually impaired or to execute grasping tasks with a robotic arm.In this paper,we collected,annotated,and published the benchmark TQUGraspingObject dataset for testing,validation,and evaluation of deep learning(DL)models for detecting,recognizing,and localizing grasping objects in 2D and 3D space,especially 3D point cloud data.Our dataset is collected in a shared room,with common everyday objects placed on the tabletop in jumbled positions by Intel RealSense D435(IR-D435).This dataset includes more than 63k RGB-D pairs and related data such as normalized 3D object point cloud,3D object point cloud segmented,coordinate system normalizationmatrix,3D object point cloud normalized,and hand pose for grasping each object.At the same time,we also conducted experiments on fourDL networks with the best performance:SSD-MobileNetV3,ResNet50-Transformer,ResNet101-Transformer,and YOLOv12.The results present that YOLOv12 has the most suitable results in detecting and recognizing objects in images.All data,annotations,toolkit,source code,point cloud data,and results are publicly available on our project website:http://gffzz188fe103f8f1460as9w9ovbffw9cf6xn9.ffgz.tsg.suse.edu.cn/HuaTThanhIT2327Tqu/datasetv2. 展开更多
关键词 Grasping object of blind/Robot arm TQU-graspingobject benchmark dataset 3D point cloud data deep learning(DL) object detectionecognition intel realsense D435(IR-D435)
暂未订购 下载PDF
SAA-O2DINO:Oriented object detection transformer with improved denoising anchor boxes and shape-adaptive assigner 认领 引用 被引量：1
2
作者 Ruijiao JIN Kun WANG +2 位作者 Zhang LI Xichao TENG Minhao LIU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第5期547-560,共14页
In contrast to the nearly fixed flying altitude of satellite remote sensing platforms,aerial remote sensing(e.g.,unmanned aerial vehicles)often employs oblique photography at varying flying altitudes to observe object... In contrast to the nearly fixed flying altitude of satellite remote sensing platforms,aerial remote sensing(e.g.,unmanned aerial vehicles)often employs oblique photography at varying flying altitudes to observe objects from multiple angles and distances in real time.While the existing oriented object detection methods have already demonstrated reliable results in most satellite remote sensing scenarios and achieved high detection precision on large public datasets,such as DOTA-v1.0 and DIOR-R,these methods tend to perform suboptimally on aerial remote sensing images.This performance gap is primarily due to the following two challenges:(A)significant shape variation of objects under multi-view imaging scenarios and(B)substantial object scale variation under multi-distance imaging conditions.To address these issues,we propose the SAA-O2DINO(oriented object detection transformer with improved denoising anchor boxes and shape-adaptive assigner)method for aerial remote sensing in this paper.The proposed method is based on the recently developed AO2DINO framework.It introduces an enhanced Shape-Adaptive Assigner(SAA)that incorporates object shape information into the threshold estimation,allowing for more accurate separation of positive and negative samples,thereby improving the model's adaptability to significant shape changes across different imaging angles.Additionally,a Gradient Calibration Loss(GCL)is introduced to mitigate the problem of object scale variation.The GCL employs a gradient scaling strategy to reduce scale sensitivity during the optimisation process.We comprehensively compare the proposed method against typical oriented object detection approaches on the DOTA-v1.0 and VSAI datasets.The results show that the proposed method has substantial improvement in detection performance across all datasets,particularly for aerial remote sensing images,validating the generalisation capabilities of our model. 展开更多
关键词 Aerial remote sensing imagery DETR Oriented Object Detection Rotate IoU loss Shape-adaptive assigner
暂未订购 下载PDF
Global-local feature optimization based RGB-IR fusion object detection on drone view 认领 引用 被引量：1
3
作者 Zhaodong CHEN Hongbing JI Yongquan ZHANG 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第1期436-453,共18页
Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still st... Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at http://gffzz188fe103f8f1460as9w9ovbffw9cf6xn9.ffgz.tsg.suse.edu.cn/lao chen330/GLFDet. 展开更多
关键词 Object detection Deep learning RGB-IR fusion Drones Global feature Local feature
暂未订购 下载PDF
CAGE-YOLO:A Dense Small Object Detection Model for Aquaculture Net Cages Based on Remote Sensing Images 认领 引用 被引量：1
4
作者 ZHANG Wenbo JIANG Yijue +2 位作者 SONG Wei HE Qi ZHANG Wenbo 《智慧农业（中英文）》 CSCD 2026年第2期98-117,共20页
[Objective]Detecting dense and small aquaculture net cages in complex backgrounds is difficult,the purpose of this study is to build a specialized dataset and design a targeted detection model that enhances recognitio... [Objective]Detecting dense and small aquaculture net cages in complex backgrounds is difficult,the purpose of this study is to build a specialized dataset and design a targeted detection model that enhances recognition accuracy and robustness for practical aquaculture management.[Methods]A dataset of aquaculture net cages was constructed using highresolution remote sensing imagery collected from seven representative farming regions(Australia,Canada,Chile,Croatia,Greece,China,and the Faroe Islands),and Cage-YOLO,a deep learning model based on YOLOv5,was proposed for detecting dense and small aquaculture net cages.First,an adaptive dense perception algorithm was introduced,which automatically selects and generates feature maps that reflect the high-density distribution of small aquaculture net cages.Second,an enhanced module based on spatial pyramid pooling fast was integrated to effectively reduce background noise interference and improve global feature extraction capabilities.Finally,a mixed attention block was incorporated to further enhance the model's perception of dense and small objects.[Results and Discussions]Experimental results showed that the proposed Cage-YOLO achieved improvements over the original YOLOv5 in terms of precision,recall,and mean average precision by 5.6,21.8,and 17.4 percentage points,respectively.The model size was maintained at 16.9 MB,demonstrating both strong performance and deployment advantages.[Conclusions]This study provides a new approach for dense and small object detection and offers technical support for the intelligent management of marine cage aquaculture. 展开更多
关键词 aquaculture net cage small object detection adaptive dense perception algorithm enhancement spatial pyramid pooling mix attention block
暂未订购 下载PDF
Transformer-Driven Multimodal for Human-Object Detection and Recognition for Intelligent Robotic Surveillance 认领 引用
5
作者 Aman Aman Ullah Yanfeng Wu +3 位作者 Shaheryar Najam Nouf Abdullah Almujally Ahmad Jalal Hui Liu 《Computers, Materials & Continua》 SCIE EI 2026年第4期1364-1383,共20页
Human object detection and recognition is essential for elderly monitoring and assisted living however,models relying solely on pose or scene context often struggle in cluttered or visually ambiguous settings.To addre... Human object detection and recognition is essential for elderly monitoring and assisted living however,models relying solely on pose or scene context often struggle in cluttered or visually ambiguous settings.To address this,we present SCENET-3D,a transformer-drivenmultimodal framework that unifies human-centric skeleton features with scene-object semantics for intelligent robotic vision through a three-stage pipeline.In the first stage,scene analysis,rich geometric and texture descriptors are extracted from RGB frames,including surface-normal histograms,angles between neighboring normals,Zernike moments,directional standard deviation,and Gabor-filter responses.In the second stage,scene-object analysis,non-human objects are segmented and represented using local feature descriptors and complementary surface-normal information.In the third stage,human-pose estimation,silhouettes are processed through an enhanced MoveNet to obtain 2D anatomical keypoints,which are fused with depth information and converted into RGB-based point clouds to construct pseudo-3D skeletons.Features from all three stages are fused and fed in a transformer encoder with multi-head attention to resolve visually similar activities.Experiments on UCLA(95.8%),ETRI-Activity3D(89.4%),andCAD-120(91.2%)demonstrate that combining pseudo-3D skeletonswith rich scene-object fusion significantly improves generalizable activity recognition,enabling safer elderly care,natural human–robot interaction,and robust context-aware robotic perception in real-world environments. 展开更多
关键词 Human object detection elderly care RGB-based pose estimation scene context analysis object recognition Gabor features point cloud reconstruction
暂未订购 下载PDF
Terahertz video analysis for hidden object detection using deep learning techniques 认领 引用
6
作者 Parama BAGCHI Olga Sergeevna SUSHKOVA +1 位作者 Alexei Alexandrovich MOROZOV Debotosh BHATTACHARJEE 《Optoelectronics Letters》 EI 2026年第4期223-228,共6页
This paper is based on automatically detecting hazardous and non-dangerous objects from terahertz images.First,we trained a neural network to automatically analyze dangerous and non-dangerous items,which can be used f... This paper is based on automatically detecting hazardous and non-dangerous objects from terahertz images.First,we trained a neural network to automatically analyze dangerous and non-dangerous items,which can be used for experiment with terahertz images generated by a prototype terahertz video system.The system comprises a terahertz video database of people hiding dangerous and non-dangerous objects under their clothing.Secondly,visual geometry group-19(VGG-19)is trained on dangerous and non-dangerous objects from our database.After training,the accuracy received was 99.6%for safe items and 85.85%for dangerous items.We tested the network with various categories of objects not included in the training set and found that most were correctly identified as dangerous and nondangerous items.Also,we have identified some of the critical issues that need to be addressed to make this technology more accessible and widely used.Our work can pave the way for future research in this field and help to address the challenges associated with terahertz imaging technologies.The paper describes some preliminary terahertz video surveillance experiments necessary for developing a natural terahertz video surveillance system. 展开更多
关键词 terahertz video database hazardous objects non dangerous objects terahertz imaging experiment terahertz images terahertz imagesfirstwe neural network deep learning
暂未订购 下载PDF
An Improved Variant of Multi-Population Cooperative Constrained Multi-Objective Optimization(MCCMO)for Multi-Objective Optimization Problem 认领 引用
7
作者 Muhammad Waqar Khan Adnan Ahmed Siddiqui Syed Sajjad Hussain Rizvi 《Computers, Materials & Continua》 SCIE EI 2026年第2期1874-1888,共15页
The multi-objective optimization problems,especially in constrained environments such as power distribution planning,demand robust strategies for discovering effective solutions.This work presents the improved variant... The multi-objective optimization problems,especially in constrained environments such as power distribution planning,demand robust strategies for discovering effective solutions.This work presents the improved variant of the Multi-population Cooperative Constrained Multi-Objective Optimization(MCCMO)Algorithm,termed Adaptive Diversity Preservation(ADP).This enhancement is primarily focused on the improvement of constraint handling strategies,local search integration,hybrid selection approaches,and adaptive parameter control.Theimproved variant was experimented on with the RWMOP50 power distribution systemplanning benchmark.As per the findings,the improved variant outperformed the original MCCMO across the eleven performance metrics,particularly in terms of convergence speed,constraint handling efficiency,and solution diversity.The results also establish that MCCMOADP consistently delivers substantial performance gains over the baseline MCCMO,demonstrating its effectiveness across performancemetrics.The new variant also excels atmaintaining the balanced trade-off between exploration and exploitation throughout the search process,making it especially suitable for complex optimization problems in multiconstrained power systems.These enhancements make MCCMO-ADP a valuable and promising candidate for handling problems such as renewable energy scheduling,logistics planning,and power system optimization.Future work will benchmark the MCCMO-ADP against widely recognized algorithms such as NSGA-Ⅱ,NSGA-Ⅲ,and MOEA/D and will also extend its validation to large-scale real-world optimization domains to further consolidate its generalizability. 展开更多
关键词 MCCMO algorithms adaptive diversity preservation RWMOP50 power distribution system multi-modal multi objective optimization evolutionary algorithm multi objective problem
暂未订购 下载PDF
Accurate Real-Time Measurement of Small and Irregular Road Abandoned Objects Using a Lightweight Vision-Based Framework 认领 引用
8
作者 Ying Tang Chuanyi Ma +1 位作者 Feng Guo Wenhao Sun 《Computers, Materials & Continua》 SCIE EI 2026年第8期1535-1557,共23页
Road Abandoned Objects(RAOs)pose significant threats to traffic safety,particularly due to their small size,irregular shapes,and unpredictable distribution in complex road environments.The primary objective of this st... Road Abandoned Objects(RAOs)pose significant threats to traffic safety,particularly due to their small size,irregular shapes,and unpredictable distribution in complex road environments.The primary objective of this study is to develop an accurate and real-time detection framework for RAOs while maintaining low computational cost for practical deployment.To achieve this,we propose RAO-YOLO,a lightweight vision-based detection framework built upon an enhanced YOLO architecture.Specifically,a Mixed Aggregation Network(MANet)is introduced to improve multi-scale feature representation,and a Lightweight Shared Detail-Enhanced Detection(LSDD)head is designed to enhance localization accuracy for small and irregular objects.Furthermore,a Focal-MPDIoU loss function is proposed to address sample imbalance and geometric irregularity during training.Extensive experiments conducted on the RAOD dataset demonstrate that the proposed method achieves superior performance compared to state-of-the-art detectors,achieving a mAP@0.5:0.95 of 56.1%while maintaining real-time inference speed.These results validate the effectiveness of the proposed framework for practical intelligent transportation applications. 展开更多
关键词 Road abandoned objects real-time object detection road safety intelligent transportation systems
暂未订购 下载PDF
Robust 3D object tracking with X-Triplet markers:A machine learning-based approach 认领 引用
9
作者 Cai Meng Yue Zeng +2 位作者 Hongbin Shen Xinliang Deng Diansheng Chen 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第2期145-154,共10页
Object tracking in 3D space is a classical problem in computer vision.In this paper,an efficient and robust X-Triplet detection method is proposed based on the support vector machine(SVM) and an adjacent matrix for lo... Object tracking in 3D space is a classical problem in computer vision.In this paper,an efficient and robust X-Triplet detection method is proposed based on the support vector machine(SVM) and an adjacent matrix for locating and tracking objects through stereo vision with minimal feature points.The X-Triplet,denoted as Tri-X,is a composite marker consisting of three sequential X-corners.The definition and types of Tri-X markers are introduced at first.Then a fast and robust X-corner detector based on the block search strategy and SVM is proposed to extract X-corner candidates with sub-pixel locations and orientations.Thereafter the X-corner adjacent matrix(XAM) is constructed using the orientation angle error to describe the possibility that any X-corner pair form a valid edge vector.The Tri-X candidates are then extracted efficiently from the XAM.Finally once the Tri-X markers are detected in binocular images,their 6D pose information can be recovered through stereo matching and triangulation technique.When multiple targets are involved simultaneously,different Tri-X markers can be utilized to identify different objects.Experimental results show that the proposed method outperformed the state-of-the-art in terms of both accuracy and efficiency for Tri-X marker detection.In localization precision test,it achieved 0.1 mm error for the position and 1° error for the orientation.Our method exhibits great potential for utilization in user-defined specific tracking tasks,offering flexibility and adaptability to various tracking requirements,especially multi-tool tracking in medical robotics. 展开更多
关键词 Object tracking Localization Tri-X composite marker Support vector machine X-corner adjacent matrix
暂未订购 下载PDF
Orbital parameter characterization and objects cataloging for Earth-Moon collinear libration points 认领 引用
10
作者 Chenyuan QIAO Xi LONG +2 位作者 Leping YANG Yanwei ZHU Peng WANG 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2026年第4期551-566,共16页
Owing to the chaotic and non-integrable nature of three-body dynamics,the conventional Keplerian elements are rendered inadequate for cataloging cislunar space objects.Currently,there has been a conspicuous absence of... Owing to the chaotic and non-integrable nature of three-body dynamics,the conventional Keplerian elements are rendered inadequate for cataloging cislunar space objects.Currently,there has been a conspicuous absence of universally recognized parameters for the characterization and cataloging of such objects,thereby posing an urgent challenge to cislunar space situational awareness.This paper proposes a novel approach to parameterize the orbits of Earth-Moon collinear libration points by leveraging the theoretical frameworks of canonical transformations.First,under the Hamiltonian-form dynamical equations of the libration point,symplectic transformations are employed to extract 3 modes of motion from locally linearized part.A subsequent canonical transformation then decouples the hyperbolic invariant manifold from the center manifold within the nonlinear remainder.Finally,6 characteristic parameters obtained via action-angle variables are established in a bijective correspondence with the state variables,where two parameters characterize the motion of the invariant manifold and four parameters characterize the motion of the central manifold.Furthermore,a distribution map of the Earth-Moon libration point orbits is drawn utilizing Poincare sections,which can be used to describe the distribution of libration point object.Simulation results demonstrate that the proposed parameters are not only applicable to orbit identification and object cataloging but also exhibit remarkable consistency and robustness against variations in observation arc length and observational errors. 展开更多
关键词 Canonical transformation Characteristic parameters Cislunar space Collinear libration points Objects cataloging Orbital calculations Spacecraft
暂未订购 下载PDF
AdvYOLO:An Improved Cross-Conv-Block Feature Fusion-Based YOLO Network for Transferable Adversarial Attacks on ORSIs Object Detection 认领 引用
11
作者 Leyu Dai Jindong Wang +2 位作者 Ming Zhou Song Guo Hengwei Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第4期767-792,共26页
In recent years,with the rapid advancement of artificial intelligence,object detection algorithms have made significant strides in accuracy and computational efficiency.Notably,research and applications of Anchor-Free... In recent years,with the rapid advancement of artificial intelligence,object detection algorithms have made significant strides in accuracy and computational efficiency.Notably,research and applications of Anchor-Free models have opened new avenues for real-time target detection in optical remote sensing images(ORSIs).However,in the realmof adversarial attacks,developing adversarial techniques tailored to Anchor-Freemodels remains challenging.Adversarial examples generated based on Anchor-Based models often exhibit poor transferability to these new model architectures.Furthermore,the growing diversity of Anchor-Free models poses additional hurdles to achieving robust transferability of adversarial attacks.This study presents an improved cross-conv-block feature fusion You Only Look Once(YOLO)architecture,meticulously engineered to facilitate the extraction ofmore comprehensive semantic features during the backpropagation process.To address the asymmetry between densely distributed objects in ORSIs and the corresponding detector outputs,a novel dense bounding box attack strategy is proposed.This approach leverages dense target bounding boxes loss in the calculation of adversarial loss functions.Furthermore,by integrating translation-invariant(TI)and momentum-iteration(MI)adversarial methodologies,the proposed framework significantly improves the transferability of adversarial attacks.Experimental results demonstrate that our method achieves superior adversarial attack performance,with adversarial transferability rates(ATR)of 67.53%on the NWPU VHR-10 dataset and 90.71%on the HRSC2016 dataset.Compared to ensemble adversarial attack and cascaded adversarial attack approaches,our method generates adversarial examples in an average of 0.64 s,representing an approximately 14.5%improvement in efficiency under equivalent conditions. 展开更多
关键词 Remote sensing object detection transferable adversarial attack feature fusion cross-conv-block
暂未订购 下载PDF
YOLO-VSF:An Improved YOLO Model by Incorporating Attention Mechanism for Object Detection in Traffic Scenes 认领 引用
12
作者 MIAO Jun GONG Shaocui +4 位作者 DENG Yongqiang LIANG Hao LI Juanjuan QI Honggang ZHANG Maoxuan 《Journal of Shanghai Jiaotong university(Science)》 EI 2026年第2期334-347,共14页
Intelligent transportation and autonomous driving systems have made urgent demands on the techniques with high performance on object detection in traffic scenes.This paper proposes an improved object detection model Y... Intelligent transportation and autonomous driving systems have made urgent demands on the techniques with high performance on object detection in traffic scenes.This paper proposes an improved object detection model YOLO-VSF over the YOLOv4 model,which is a representative work with excellent performance among YOLO series of object detection models.The main improvement measures include:The backbone feature extraction network CSPDarknet53 of YOLOv4 is replaced with VGG16 to improve the feature extraction capability;SENet attention mechanism is incorporated to improve the salient and correlation feature representation capability;Focal Loss is integrated into the loss function to overcome the sample imbalance problem.In addition,the detection performance of small targets is improved by increasing the resolution of input images.Experimental results show that on the VanJee traffic image dataset provided by Beijing VanJee Technology Co.,Ltd.,the proposed YOLO-VSF model achieves an average mean accuracy(mAP)of 92.21 percentage points,which improves the mAP by 3.04 percentage points compared with the YOLOv4 model while maintaining the detection speed of the original model.On the UA-DETRAC dataset,the average accuracy of YOLO-VSF is close to that of the latest YOLOv7 model with the number of parameters reduced by 1.329×107.The proposed method can provide a support for object detection in traffic scenes. 展开更多
关键词 object detection traffic scenes backbone network attention mechanism Focal Loss
暂未订购 下载PDF
Hybrid Quantum Gate Enabled CNN Framework with Optimized Features for Human-Object Detection and Recognition 认领 引用
13
作者 Nouf Abdullah Almujally Tanvir Fatima Naik Bukht +3 位作者 Shuaa S.Alharbi Asaad Algarni Ahmad Jalal Jeongmin Park 《Computers, Materials & Continua》 SCIE EI 2026年第4期2254-2271,共18页
Recognising human-object interactions(HOI)is a challenging task for traditional machine learning models,including convolutional neural networks(CNNs).Existing models show limited transferability across complex dataset... Recognising human-object interactions(HOI)is a challenging task for traditional machine learning models,including convolutional neural networks(CNNs).Existing models show limited transferability across complex datasets such as D3D-HOI and SYSU 3D HOI.The conventional architecture of CNNs restricts their ability to handle HOI scenarios with high complexity.HOI recognition requires improved feature extraction methods to overcome the current limitations in accuracy and scalability.This work proposes a Novel quantum gate-enabled hybrid CNN(QEH-CNN)for effectiveHOI recognition.Themodel enhancesCNNperformance by integrating quantumcomputing components.The framework begins with bilateral image filtering,followed bymulti-object tracking(MOT)and Felzenszwalb superpixel segmentation.A watershed algorithm refines object boundaries by cleaning merged superpixels.Feature extraction combines a histogram of oriented gradients(HOG),Global Image Statistics for Texture(GIST)descriptors,and a novel 23-joint keypoint extractionmethod using relative joint angles and joint proximitymeasures.A fuzzy optimization process refines the extracted features before feeding them into the QEH-CNNmodel.The proposed model achieves 95.06%accuracy on the 3D-D3D-HOI dataset and 97.29%on the SYSU3DHOI dataset.Theintegration of quantum computing enhances feature optimization,leading to improved accuracy and overall model efficiency. 展开更多
关键词 Pattern recognition image segmentation computer vision object detection
暂未订购 下载PDF
A 3D Object Recovery Framework for Enhancing In-Vehicle Network Resilience to Data Tampering Attack 认领 引用
14
作者 Gangtao Han Yurui Chen +3 位作者 Song Wang Enqing Chen Lingling Li Gaofeng Pan 《Computers, Materials & Continua》 SCIE EI 2026年第6期2418-2436,共19页
The integrity of perception data transmitted over in-vehicle networks is important for the safety of autonomous driving.However,legacy protocols like the Controller Area Network(CAN)bus which lacks essential security ... The integrity of perception data transmitted over in-vehicle networks is important for the safety of autonomous driving.However,legacy protocols like the Controller Area Network(CAN)bus which lacks essential security features make In-Vehicle Networks(IVNs)vulnerable to data tampering attacks.Current research typically focuses on detecting the attack itself but ignores the information recovery from the missing data,leading to an unsafe autonomous driving system.To address the issue,we propose a 3D object recovery framework to recover the missing data caused by the tampering attack that occurred in in-vehicle networks.The proposed framework exploits both temporal and spatial context for the 3D object recovery,where a temporal branch is designed to learn the coordinate offsets of 3D objects based on historical data from previous frames,while a spatial branch employs information from the adjacent views of the attacked objects to locate the recovered objects from the overlapped regions in the current frame.By integrating the temporal and spatial clues,the framework effectively recovers the missing objects from the resting ones,thereby enhancing the immunity of in-vehicle networks for the tampering attack.Extensive experiments on the nuScenes dataset demonstrate that the proposed framework significantly improves 3D object detection performance under the attack when compared to the method without recovery.Additionally,the recovery performance becomes better as the attack intensity increases,highlighting the framework’s robustness in high-risk scenarios.The source will be available upon publication. 展开更多
关键词 3D object recovery data tampering attack in-vehicle networks autonomous driving security temporal-spatial context
暂未订购 下载PDF
DGRDet: Dynamic Gaussian Receptive Field Encoding-Based Spiking Neural Networks for Remote Sensing Object Detection 认领 引用
15
作者 Li Chen Fan Zhang +3 位作者 Guangwei Xie Yanzhao Gao Xiaofeng Qi Mingqian Sun 《Computers, Materials & Continua》 SCIE EI 2026年第8期1247-1271,共25页
Remote sensing object detection aims to identify and localize specific targets in satellite or aerial imagery.Spiking Neural Networks(SNNs),benefiting from their implicit feedback-based and event-driven brain-inspired... Remote sensing object detection aims to identify and localize specific targets in satellite or aerial imagery.Spiking Neural Networks(SNNs),benefiting from their implicit feedback-based and event-driven brain-inspired dynamics,offer a promising solution to alleviate the high energy consumption of conventional ANN-based detection models.However,existing SNN-based approaches for remote sensing object detection—particularly for small,arbitrarily rotated objects—are still in their infancy and suffer from a substantial performance gap compared with ANN counterparts.In this work,we draw inspiration from the hierarchical sparse perception mechanisms of biological vision and integrate dynamic receptive field modulation into the encoding stage,proposing a high-precision spiking object detection framework tailored for remote sensing image.Specifically,we design a Hierarchical Feedback-based Gaussian Encoding(HFG)scheme,in which the parameters of Gaussian kernels are dynamically adjusted through spike-triggered top-down feedback connections.This mechanism enables the encoding process to adaptively respond to complex geometric variations of remote sensing objects,including rotation and scale changes.Based on the proposed encoding strategy,we develop DGRDet(Dynamic Gaussian Receptive Field Encoding-based Spiking Neural Networks for Remote Sensing Object Detection),a directly trained deep SNN detector for remote sensing image.Extensive evaluations on the large-scale public DOTA dataset demonstrate that DGRDet achieves competitive detection accuracy,outperforming existing SNN-based object detection methods.Moreover,compared with ANN models of comparable detection performance,DGRDet reduces spike activity by 81.31%and requires only 0.12%of the inference energy consumption,achieving a favorable balance between detection accuracy,efficiency,and energy efficiency. 展开更多
关键词 Remote sensing image object detection spiking neural networks(SNNs) hierarchical sparse dynamic gaussian encoding
暂未订购 下载PDF
Inference and Performance Analysis of Optimized YOLOv9 for Indoor Object Detection&Classification 认领 引用
16
作者 Muhammad Asim Muhammad Amin Shahid +5 位作者 Abdullah Khan Muhammad Ishaq Jawad Khan Syed Qamrun Nisa Muhammad Amir Khan Ines Hilali Jaghdam 《Computers, Materials & Continua》 SCIE EI 2026年第9期1576-1598,共23页
Indoor object detection presents unique challenges such as occlusions,varying lighting conditions,and cluttered environments.While several object detection frameworks,including RetinaNet,Faster R-CNN,SSD,and Efficient... Indoor object detection presents unique challenges such as occlusions,varying lighting conditions,and cluttered environments.While several object detection frameworks,including RetinaNet,Faster R-CNN,SSD,and EfficientDet,have been proposed,they often suffer from high computational cost,reduced inference speed,and limited accuracy in terms of mean Average Precision(mAP),particularly in real-time scenarios.In this study,lightweight YOLO variants,namely YOLOv7,YOLOv8s,YOLOv9s,and a fine-tuned YOLOv9s which considers the optimized training strategy based on albumentations.All the models are evaluated for indoor object detection using the RGB TUT Indoor dataset.The models are assessed using precision,recall,mAP@0.5,and mAP@0.5:0.95.The experimental results demonstrate that the fine-tuned YOLOv9s consistently outperforms the baseline YOLOv9s model across all evaluation metrics,confirming the effectiveness of proposed training optimizations.Specifically,the fine-tuned YOLOv9s achieves a precision of 97.9%,recall of 96.1%,mAP@0.5 of 99.1%,and mAP@0.5:0.95 of 88.7%.These improvements highlight the impact of systematic training refinement beyond standard model configuration.Among the evaluated models,YOLOv8s achieves the highest inference speed of 90 FPS in 11.1 ms,making it suitable for ultra-low-latency applications such as smart homes,assistive systems,and robotics.In contrast,the fine-tuned YOLOv9s provides a superior balance between accuracy and efficiency,making it more suitable for accuracy-sensitive indoor environments where detection reliability is critical.Overall,the study demonstrates that carefully optimized training strategies can significantly enhance the performance of YOLOv9s without architectural modifications,providing practical insights for real-time indoor object detection systems. 展开更多
关键词 Image classification deep learning indoor object detection You Only Look Once(YOLO)
暂未订购 下载PDF
Deep-learning-based object detection of pelvic autonomic nerves during total mesorectal excision 认领 引用
17
作者 Qiao Zhang Jin Li +3 位作者 Tao Meng Zhi-Fen Chen Xue-Zhi Zhou Xing-Rong Lu 《World Journal of Gastroenterology》 SCIE CAS 2026年第30期91-103,共13页
BACKGROUND Recognition of pelvic autonomic nerves(PAN)during total mesorectal excision(TME)largely depends on the surgeon’s expertise,making it susceptible to misrecognition and unintentional damage.There is an urgen... BACKGROUND Recognition of pelvic autonomic nerves(PAN)during total mesorectal excision(TME)largely depends on the surgeon’s expertise,making it susceptible to misrecognition and unintentional damage.There is an urgent need for objective and real-time support methods.AIM To develop a deep learning(DL)model for precise recognition and visual annotation of 5 categories of PAN during TME.METHODS This single-center retrospective study enrolled 120 TME videos from January 2021 to January 2023.A total of 3246 high-quality images were obtained and split 9:1 into training and internal test sets.Difficult-to-recognize characteristics were summarized.An additional 20 independent TME videos from June 2023 to January 2024 were used for external validation.The DL model performance was compared with that of surgeons and verified pathologically.χ2,Fisher’s exact test and t-tests were applied(P<0.05).RESULTS The DL model achieved a precision of 0.839,a recall of 0.769,and a mean average precision at intersection over union 50 of 0.873.The overall recognition rate in external validation was 76.0%,similar to senior surgeons(73.9%,P=0.156)but superior to junior surgeons(64.9%,P=0.001).The miss rate of 5 PAN categories ranged from 12.9%to 29.6%.Initial recognition time(2.08-2.21 seconds)was shorter than that of senior surgeons(5.65-6.19 seconds,P<0.01);mean continuous tracking duration was prolonged by 57.21-66.45 seconds compared with that of senior surgeons(P<0.01).Low nerve exposure caused most DL model false negatives,while cord-like fibrous tissue dominated false positives.All 7 harvested specimens were pathologically confirmed to contain nerve tissue,with a processing speed of 25 frames per second.CONCLUSION The model demonstrates recognition performance comparable to that of senior surgeons,with pathological confirmation.It may potentially help preserve PAN during TME and shorten the learning curve for junior surgeons. 展开更多
关键词 Rectal cancer Total mesorectal excision Pelvic autonomic nerve Deep learning Object detection
暂未订购 下载PDF
DA-T3D:Distribution-Aware Cross-Modal Distillation Framework for Temporal 3D Object Detection 认领 引用
18
作者 Tianzhe Jiao Yuming Chen +2 位作者 Xiaoyue Feng Chaopeng Guo Jie Song 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第4期1-21,共21页
Knowledge distillation bridges the performance gap between camera-based and LiDAR-based 3D detectors by leveraging the precise geometric information from LiDAR.However,cross-modal knowledge transfer remains challengin... Knowledge distillation bridges the performance gap between camera-based and LiDAR-based 3D detectors by leveraging the precise geometric information from LiDAR.However,cross-modal knowledge transfer remains challenging due to the inherent modality heterogeneity between LiDAR and camera data,which often leads to instability during training.In this work,we find that these instabilities are closely related to distribution mismatch in the cross-modal feature space and noisy teacher signals.To address this issue,we propose a novel distribution-aware cross-modal distillation framework,named DA-T3D.Specifically,we first explicitly model the LiDAR teacher’s Bird’sEye-View(BEV)feature distribution and use the learned distribution as a statistical prior to guide the student features toward high-density and geometrically stable regions in the teacher’s BEV feature space.This ensures feature alignment in BEV space by constraining the student model’s feature distribution to match that of the LiDAR teacher model within foreground regions.Next,we further introduce response-level distillation to directly transfer the teacher’s prediction behavior to the student detection head,providing direct output-space supervision that complements feature distillation and effectively reduces modality-induced ambiguity,leading to more accurate and stable classification confidence and bounding-box regression.Furthermore,we perform temporal modeling on the distilled cross-modal features to produce fused BEV representations that capture more comprehensive scene context.Finally,we utilize the fused BEV features to generate 3D detection results.Through experiments,we validate the effectiveness and superiority of DA-T3D on the nuScenes dataset,achieving 46.7%mAP and 58.1%NDS. 展开更多
关键词 3D object detection Bird’s-Eye-View perception cross-modal knowledge distillation Dirichlet process Gaussian mixture model temporal modeling
暂未订购 下载PDF
Railway Track Defect Detection Based on Dynamic Multi-Modal Fusion and Challenging Object Enhanced Perception 认领 引用
19
作者 Yaguan Wang Linlin Kou +3 位作者 Yang Gao Qiang Sun Yong Qin Genwang Peng 《Structural Durability & Health Monitoring》 EI 2026年第2期195-212,共18页
The fasteners employed in the railway tracks are susceptible to defects arising from their intricate composition.Foreign objects are frequently observed on the track bed in an open environment.These two types of defec... The fasteners employed in the railway tracks are susceptible to defects arising from their intricate composition.Foreign objects are frequently observed on the track bed in an open environment.These two types of defects pose potential threats to high-speed trains,thus necessitating timely and accurate track inspection.The majority of extant automatic inspection methods are predicated on the utilization of single visible light data,and the efficacy of the algorithmic processes is influenced by complex environments.Furthermore,due to the single information dimension,the detection accuracy of defects in similar,occluded,and small object categories is low.To address the aforementioned issues,this paper proposes a track defect detectionmethod based on dynamicmulti-modal fusion and challenging object enhanced perception.First,in light of the variances in the representation dimensions ofmultimodal information,this paper proposes a dynamic weighted multi-modal feature fusion module.The fused multi-modal features are assigned weights,and thenmultiplied with the extracted single-modal features atmultiple levels,achieving adaptive adjustment of the response degree of fusion features.Second,a novel stepwise multi-scale convolution feature aggregation module is proposed for challenging objects.The proposed method employs depth separable convolution and cross-scale aggregation operations of different receptive fields to enhance feature extraction and reuse,thereby reducing the degree of progressive loss of effective information.The experimental results demonstrate the efficacy of the proposed method in comparison to eight established methods,encompassing both single-modal and multi-modal methods,as evidenced by the extensive findings within the constructed RGBD dataset. 展开更多
关键词 Railway safety track defect detection multi-modal data object detection
暂未订购 下载PDF
Hyperbolic cosine transformer for LiDAR 3D object detection 认领 引用
20
作者 Jigang TONG Fanhang YANG +1 位作者 Sen YANG Shengzhi DU 《Optoelectronics Letters》 EI 2026年第3期160-166,共7页
Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points.To address these limitations,we propose the cosh-attention,which reduces the computation... Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points.To address these limitations,we propose the cosh-attention,which reduces the computation complexity of space and time from the quadratic order to linear order with respect to the number of points.In the cosh-attention,the traditional softmax operator is replaced by non-negative Re LU activation and hyperbolic-cosine-based operator with re-weighting mechanism.Then based on the key component,cosh-attention,we present a two-stage hyperbolic cosine transformer(ChTR3D)for 3D object detection from point clouds.It refines proposals by applying cosh-attention in linear computation complexity to encode rich contextual relationships among points.Extensive experiments on the widely used KITTI dataset and Waymo Open Dataset demonstrate that compared with vanilla attention,the cosh-attention significantly improves the inference speed with competitive performance.Among two-stage state-of-the-art methods using point-level features for refinement,the proposed ChTR3D is the fastest one. 展开更多
关键词 key co lidar d object detection point wise methods computation complexity hyperbolic cosine transformer cosh attention space time softmax operator
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈