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246,244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：
Transmission Line Defect Detection Algorithm Based on Improved RT-DETR Model 认领 引用
1
作者 Qi Wu 《Journal of Electronic Research and Application》 2026年第1期227-238,共12页
This paper addresses the urgent need for high-precision and high-efficiency visual perception technologies in power equipment operation and maintenance under the background of rapid development of smart grids.It point... This paper addresses the urgent need for high-precision and high-efficiency visual perception technologies in power equipment operation and maintenance under the background of rapid development of smart grids.It points out the performance limitations of the existing real-time target detection framework RT-DETR when handling small targets,dense targets,and complex backgrounds in power inspection scenarios.To overcome this bottleneck,this study proposes an improved backbone network model,DETR-EVA,based on an efficient visual attention mechanism(EVA).This model innovatively designs an attention computation structure with linear complexity by deeply integrating the EVA mechanism with the C2f module in the RT-DETR backbone network,and combines local detail perception and global dependency modeling capabilities.Its core lies in the introduction of a gated fusion mechanism,which significantly enhances the model’s ability to model long-distance contextual relationships and the adaptive adjustment efficiency of feature weights while retaining the advantages of multi-branch feature extraction and fusion of the C2f module.Experiments were conducted on an inspection image dataset containing typical power equipment targets.The results show that compared with the original RT-DETR model,DETR-EVA improves the overall accuracy index mAP50-95 by 2.5%,reduces computational complexity by 14%,and reduces the number of model parameters by 27%.This effectively verifies that the proposed method can significantly improve the detection accuracy of small targets and complex scenes while maintaining real-time detection speed,providing a better visual solution for intelligent operation and maintenance of power equipment. 展开更多
关键词 RT-DETR Defect detection Efficient vision attention C2f Small object detection
暂未订购 下载PDF
改进RT-DETR的输电线路异物检测算法研究 认领 引用 被引量：3
2
作者 王震洲 孙冬冬 +1 位作者 王建超 苏鹤 《计算机工程与应用》 EI CSCD 北大核心 2026年第2期116-125,共10页
针对无人机智能巡检场景中航拍图像检测精度有限、模型计算复杂和特征提取困难等问题,提出一种改进RT-DETR的算法。在骨干网络中构建轻量级特征提取模块(DynRepFusion block,DRF block),提升检测精度的同时显著降低了模型复杂度和计算成... 针对无人机智能巡检场景中航拍图像检测精度有限、模型计算复杂和特征提取困难等问题,提出一种改进RT-DETR的算法。在骨干网络中构建轻量级特征提取模块(DynRepFusion block,DRF block),提升检测精度的同时显著降低了模型复杂度和计算成本;引入动态特征区域协同注意力模块(dynamic feature region collaborative attention,DFRCA),通过双路径直方图重组策略实现特征的协同提取,降低密集目标的误检率;改进多尺度特征增强融合网络(multi-scale feature fusion network,MSFFN),实现多尺度目标的同步优化;采用EIoU损失函数减少模型对图像尺寸变化的敏感性,有效地提升了检测精度。实验结果表明,改进后模型参数量下降了26.1%、GFLOPs减少了22.2%,同时mAP50和mAP50:95分别提升至94.5%和76.2%,较原模型分别提高了4.2与2.7个百分点;与主流算法中综合性能表现最好的YOLOV8相比,改进后模型在mAP50、F1值分别提升2.1和3.9个百分点。改进RT-DETR算法在巡检无人机作业时提升了检测精度,降低了误检率,节省了计算资源,为无人机目标检测提供了有效解决方案。 展开更多
关键词 无人机(UAV) 异物检测 RT-DETR 轻量化 多尺度特征融合
暂未订购 下载PDF
基于改进RT-DETR的图像识别算法及其应用 认领 引用 被引量：1
3
作者 胡建功 卜旭阳 +2 位作者 郭义凯 王光辉 王莹坤 《实验室研究与探索》 CAS 北大核心 2026年第1期98-103,共6页
RT-DETR网络作为首个端到端的Transformer图像识别网络,在图像识别领域应用广泛。然而,标准RT-DETR网络在处理复杂场景与小目标检测时,仍存在精度不足和速度偏低问题。为此,提出一种改进的RT-DETR网络的图像识别算法,并将其应用于车辆... RT-DETR网络作为首个端到端的Transformer图像识别网络,在图像识别领域应用广泛。然而,标准RT-DETR网络在处理复杂场景与小目标检测时,仍存在精度不足和速度偏低问题。为此,提出一种改进的RT-DETR网络的图像识别算法,并将其应用于车辆识别任务。该算法通过引入空间位置关系建模以增强对小目标(如车辆、行人)的感知能力,并采用门控制机制提升网络的非线性建模性能。同时,通过分离出高频和低频的细节,对特征图进行分割与拼接,实现无损采样。进一步通过压缩遮挡干扰、背景及噪声信息,有效降低计算复杂度,并结合Conv卷积函数、Convec编码卷积函数以及Softmax函数,显著提升特征图分辨率和网络的检测精度。实验结果表明,相比于RT-DETR网络,算法在mAP50、mAP50:95、精度与召回率上分别提升了6.2%、4.5%、4.3%与4.1%。 展开更多
关键词 RT-DETR 车辆识别 多尺度 细粒度特征 空域频域
暂未订购 下载PDF
基于改进RT-DETR的遥感图像目标检测算法 认领 引用 被引量：1
4
作者 肖锋 杨文豪 +2 位作者 张文娟 黄姝娟 周雨洁 《电子测量技术》 北大核心 2026年第2期192-202,共11页
遥感图像中的目标常呈细长、曲折等复杂形态,且伴随尺度变化大与背景干扰强等因素,导致现有检测方法易出现缺检和误检,难以满足高精度检测需求,为此,提出一种改进的遥感图像目标检测算法TriD-DETR。首先,通过动态调整卷积核形状并优化... 遥感图像中的目标常呈细长、曲折等复杂形态,且伴随尺度变化大与背景干扰强等因素,导致现有检测方法易出现缺检和误检,难以满足高精度检测需求,为此,提出一种改进的遥感图像目标检测算法TriD-DETR。首先,通过动态调整卷积核形状并优化通道适配与残差连接方式,设计了DKFE特征提取模块,该模块能够自适应地聚焦于细长曲折的局部区域,从而准确捕捉目标特征;其次,为了提高模型对复杂目标的定位和识别能力,提出DATE尺度内特征交互结构,在重构Transformer编码器的基础上引入可变形注意力机制,增强了模型对高级特征和深层语义信息的捕捉能力;最后,针对多尺度特征融合部分,提出DBFB多样性分支融合模块,通过组合不同尺度和复杂度的多样性分支使特征空间更丰富,从而增强模型的表达能力。实验结果表明,TriD-DETR算法在DIOR和RSOD数据集上分别达到86.8%和94.1%的mAP,相较于原模型RT-DETR-R18,分别提升了1.2%和2.3%,充分证明了TriD-DETR算法的可靠性与高效性。 展开更多
关键词 遥感图像 目标检测 RT-DETR 注意力机制 多尺度特征融合
暂未订购 下载PDF
An improved Alpha-shape algorithm for extracting section contours of the super-high steel bridge tower using point clouds 认领 引用 被引量：2
5
作者 ZHANG Yiming ZHAO Tianhao +2 位作者 LIAO Ruixuan LI Haoqing WANG Hao 《Journal of Southeast University(English Edition)》 EI CAS 2026年第1期26-35,共10页
The virtual preassembly of super-high steel bridge towers faces a challenge in the efficient and precise extraction of complex cross-sectional features.Factors such as fabrication errors,gravity-induced deformations,a... The virtual preassembly of super-high steel bridge towers faces a challenge in the efficient and precise extraction of complex cross-sectional features.Factors such as fabrication errors,gravity-induced deformations,and temperature fluctuations can compromise the accuracy of contour extraction.To address these limitations,an improved Alpha-shape-based point cloud contour extraction method is proposed.The proposed approach uses a hierarchical strategy to process three-dimensional laser scanning point clouds.The processed data are then subjected to curvatureadaptive voxel filtering to reduce acquisition noise.In addition,an enhanced iterative closest point(ICP)variant with correspondence validation accurately aligns the discrete point cloud segments.The proposed curvature-responsive Alpha-shape framework enables multiscale contour delineation through topology-adaptive threshold modulation,which resolves boundary ambiguities in geometrically complex cross-sections.The method was experimentally validated using field-acquired measurement datasets from the Zhangjinggao Yangtze River Bridge tower segments,confirming its capability to reconstruct noncanonical cross-sectional geometries.Three contour extraction methods,including Poisson reconstruction,the conventional Alpha-shape algorithm,and random sample consensus with ICP(RANSAC-ICP),were compared to evaluate the performance of the proposed Alpha-shape algorithm.The results demonstrate that the proposed method achieves superior contour extraction accuracy and data reduction efficiency,highlighting its effectiveness in contour extraction tasks. 展开更多
关键词 super-high steel bridge tower point cloud contour extraction improved Alpha-shape algorithm
暂未订购 下载PDF
Novel Sea Otter Optimization Algorithm for WSN Coverage Intelligence Optimization 认领 引用 被引量：2
6
作者 WU Jin GAO Yaqiong +2 位作者 SU Zhengdong CHONG Gege XIONG Hao 《Journal of Shanghai Jiaotong university(Science)》 EI 2026年第4期828-842,I0002,共15页
A novel intelligent optimization algorithm inspired by nature,called sea otter optimization algorithm(SOOA),is proposed.The SOOA simulates the natural behaviors of sea otters,such as using tactile senses to search for... A novel intelligent optimization algorithm inspired by nature,called sea otter optimization algorithm(SOOA),is proposed.The SOOA simulates the natural behaviors of sea otters,such as using tactile senses to search for food in seawater,grooming their fur,feeding with the aid of stones,and escaping from danger.In the exploration stage,a wetness factor is introduced to control the behavior of sea otters in foraging and grooming;a danger factor is introduced to control the behavior of sea otters in feeding and avoiding dangers in the exploitation stage,and the behaviors of sea otters in responding to different dangers are mathematically modeled.The proposed algorithm is compared with 9 well-known intelligent optimization algorithms,and evaluated in 13 benchmark functions as well as wireless sensor network coverage optimization problems to verify the effectiveness of the proposed algorithm.The experimental results show that the node coverage after SOOA optimization reaches 91.2%in 2D environment and 90.47%in 3D environment.Compared with other algorithms,SOOA is superior and possesses the ability to solve complex optimization problems. 展开更多
关键词 sea otter optimization algorithm(SOOA) swarm intelligence optimization wireless sensor network coverage optimization
暂未订购 下载PDF
Study on the destabilizing damage precursors of cemented tailings backfill based on critical slowing down theory combined with multiple denoising algorithms under consideration of initial defect conditions 认领 引用 被引量：1
7
作者 ZHAO Kang ZHONG Jun-cheng +3 位作者 YAN Ya-jing LIU Yang WEN Dao-tan XIAO Wei-ling 《Journal of Central South University》 SCIE EI CAS CSCD 2026年第1期375-399,共25页
The cemented tailings backfill(CTB)with initial defects is more prone to destabilization damage under the influence of various unfavorable factors during the mining process.In order to investigate its influence on the... The cemented tailings backfill(CTB)with initial defects is more prone to destabilization damage under the influence of various unfavorable factors during the mining process.In order to investigate its influence on the stability of underground mining engineering,this paper simulates the generation of different degrees of initial defects inside the CTB by adding different contents of air-entraining agent(AEA),investigates the acoustic emission RA/AF eigenvalues of CTB with different contents of AEA under uniaxial compression,and adopts various denoising algorithms(e.g.,moving average smoothing,median filtering,and outlier detection)to improve the accuracy of the data.The variance and autocorrelation coefficients of RA/AF parameters were analyzed in conjunction with the critical slowing down(CSD)theory.The results show that the acoustic emission RA/AF values can be used to characterize the progressive damage evolution of CTB.The denoising algorithm processed the AE signals to reduce the effects of extraneous noise and anomalous spikes.Changes in the variance curves provide clear precursor information,while abrupt changes in the autocorrelation coefficient can be used as an auxiliary localization warning signal.The phenomenon of dramatic increase in the variance and autocorrelation coefficient curves during the compression-tightening stage,which is influenced by the initial defects,can lead to false warnings.As the initial defects of the CTB increase,its instability precursor time and instability time are prolonged,the peak stress decreases,and the time difference between the CTB and the instability damage is smaller.The results provide a new method for real-time monitoring and early warning of CTB instability damage. 展开更多
关键词 initial defects cemented tailings backfill critical slowing down acoustic emission RA/AF values denoising algorithms
暂未订购 下载PDF
基于RT-DETR的浅海底栖生物目标检测改进模型 认领 引用 被引量：1
8
作者 邓健志 唐政豪 李云 《热带海洋学报》 CAS CSCD 北大核心 2026年第3期95-108,共14页
浅海底栖生物目标检测在海洋生态监测和资源管理中具有重要意义,但受限于水下图像的低光照、模糊及复杂背景,传统检测算法性能不佳。本文提出了MEIE-RTDETR(multi-scale edge information enhancement real-time detection transformer... 浅海底栖生物目标检测在海洋生态监测和资源管理中具有重要意义,但受限于水下图像的低光照、模糊及复杂背景,传统检测算法性能不佳。本文提出了MEIE-RTDETR(multi-scale edge information enhancement real-time detection transformer)模型,通过设计多尺度边缘信息增强模块强化特征提取,采用自适应稀疏自注意力(adaptive sparse self-attention,ASSA)降低计算冗余,并引入亮度信息增强IEL(intensity enhancement layer)模块改进特征金字塔提升小目标检测能力,最后设计P-IoU(powerful-IoU)+NWD(normalized Wasserstein distance)损失函数增强对边界框模糊和多尺度目标检测的性能。在DUO(detecting underwater objects)和RUOD(rethinking general underwater object detection)数据集上的实验表明,改进后的模型在参数量和计算量显著降低的同时,mAP50分别达到85.0%和85.4%,优于Faster R-CNN(region-based convolutional neural networks)、YOLO(you only look once)系列及原始RT-DETR(real-time detection transformer),为水下轻量化高精度检测提供了有效解决方案。 展开更多
关键词 浅海底栖生物 目标检测 RT-DETR 多尺度特征增强 自适应稀疏自注意力 轻量化模型
暂未订购 下载PDF
Optimization of the frequency offset increment of FDA-MIMO based on cuckoo search algorithm 认领 引用 被引量：2
9
作者 WANG Bo ZHAO Yu +2 位作者 LI Yonglin YANG Rennong XUE Junjie 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2026年第1期157-170,共14页
Frequency diverse array multiple-input multiple-output(FDA-MIMO)radar has gained considerable research attention due to its ability to effectively counter active repeater deception jamming in complex electromagnetic e... Frequency diverse array multiple-input multiple-output(FDA-MIMO)radar has gained considerable research attention due to its ability to effectively counter active repeater deception jamming in complex electromagnetic environments.The effectiveness of interference suppression by FDA-MIMO is limited by the inherent range-angle coupling issue in the FDA beampattern.Existing literature primarily focuses on control methods for FDA-MIMO radar beam direction under the assumption of static beampatterns,with insufficient exploration of techniques for managing nonstationary beam directions.To address this gap,this paper initially introduces the FDA-MIMO signal model and the calculation formula for the FDA-MIMO array output using the minimum variance distortionless response(MVDR)beamformer.Building on this,the problem of determining the optimal frequency offset for the FDA is rephrased as a convex optimization problem,which is then resolved using the cuckoo search(CS)algorithm.Simulations confirm the effectiveness of the proposed approach,showing that the frequency offsets obtained through the CS algorithm can create a dot-shaped beam direction at the target location while effectively suppressing interference signals within the mainlobe. 展开更多
关键词 frequency diverse array multiple-input multiple-output(FDA-MIMO) convex optimization cuckoo search algorithm beampattern
暂未订购 下载PDF
基于改进RT-DETR的叶菜干烧心症状检测方法 认领 引用
10
作者 林开颜 周纪元 +4 位作者 吴军辉 杨学军 陈杰 司慧萍 祝华军 《农业工程学报》 EI CAS CSCD 北大核心 2026年第1期201-209,共9页
植物工厂中叶菜常出现干烧心胁迫症状,针对现有方法在症状初期检测性能不佳的问题,该研究提出一种干烧心症状检测模型RT-DETR-TB(real-time detection transformer for tip-burn)。模型采用基于星运算学习范式的StarNet作为主干网络,实... 植物工厂中叶菜常出现干烧心胁迫症状,针对现有方法在症状初期检测性能不佳的问题,该研究提出一种干烧心症状检测模型RT-DETR-TB(real-time detection transformer for tip-burn)。模型采用基于星运算学习范式的StarNet作为主干网络,实现模型轻量化并加速收敛。颈部编码网络中,联合星运算和通道先验注意力(channel prior convolutional attention,CPCA)设计星注意力特征融合模块(star-attention feature fusion,SAFF),以提升多尺度特征融合效果;并设计跨尺度边缘增强模块(cross-scale edge enhance,CSEE),利用浅层边缘特征信息改善小目标检测性能。试验结果表明,RT-DETR-TB的参数量为16.4M,检测速度达58帧/s,平均精度从86.0%提升至88.4%,小目标精度从46.8%提升至50.7%。同时在不同植物工厂光照环境中,模型对比主流检测方法展现出更好的准确性和鲁棒性。该模型能够满足干烧心症状的早期预警需求,为植物工厂自动化生产提供技术支持。 展开更多
关键词 目标检测 模型 干烧心 RT-DETR 植物工厂
暂未订购 下载PDF
改进RT-DETR的油田人员异常行为检测 认领 引用 被引量：1
11
作者 吴攀超 范文博 王婷婷 《机械与电子》 2026年第3期32-40,46,共9页
为解决油田作业现场因操作不规范导致的安全事故频发问题,提出了一种高效的面向油田复杂场景下异常行为检测的RT-DETR改进算法(HCH-DETR)。首先,设计一种新型主干网络,结合双分支高频细节增强模块(HFERB)和CSP结构,提高模型高频细节特... 为解决油田作业现场因操作不规范导致的安全事故频发问题,提出了一种高效的面向油田复杂场景下异常行为检测的RT-DETR改进算法(HCH-DETR)。首先,设计一种新型主干网络,结合双分支高频细节增强模块(HFERB)和CSP结构,提高模型高频细节特征提取能力,并有效减少模型计算量;其次,针对油田监控中目标尺度变化大、背景复杂等问题,提出一种基于上下文引导的空间特征重构特征金字塔网络(CGFRPN),通过矩形自校准注意力(RCA)增强多尺度特征融合,提高模型对多尺度目标的检测精度,并增强了其在复杂场景下的鲁棒性;最后,引入Haar小波下采样模块(HWD)优化传统下采样,提高模型对小目标的检测能力。在自建油田数据集上进行模型验证:mAP@0.5和mAP@0.5:0.95分别达到85.4%和55.1%,较原始RT-DETR模型提升3.2百分点和2.4百分点,同时计算量减少7.1×109,参数量降低6.5×106;消融实验验证了各改进模块的有效性,泛化实验表明模型在VisDrone数据集上精度亦有提升。 展开更多
关键词 RT-DETR 小目标检测 特征提取 异常行为 深度学习
暂未订购 下载PDF
基于改进RT-DETR的水下色偏环境中小型生物检测 认领 引用
12
作者 董绍江 肖涛 +5 位作者 吕振鸣 夏浩然 罗家元 孙世政 张霞 刘超 《浙江大学学报（工学版）》 EI CAS CSCD 北大核心 2026年第7期1404-1415,共12页
为了实现对水下小型生物的快速、准确检测,针对现有模型在水下色偏环境中检测性能差的问题,提出基于改进RT-DETR的检测方法(FES-DETR).在主干网络中设计高效多尺度注意力特征提取(Faster-Rep-EMA)模块,以优化原有的BasicBlock,提高对色... 为了实现对水下小型生物的快速、准确检测,针对现有模型在水下色偏环境中检测性能差的问题,提出基于改进RT-DETR的检测方法(FES-DETR).在主干网络中设计高效多尺度注意力特征提取(Faster-Rep-EMA)模块,以优化原有的BasicBlock,提高对色偏干扰下微弱目标的特征提取能力和计算效率.在颈部编码网络中,将纠缠Transformer块(ETB)与基于注意力的尺度内特征交互(AIFI)模块融合,实现频率域和空间域特征的联合优化,增强色偏图像的特征表达.设计轻量化小目标增强金字塔(SOEP)模块,增强模型对小目标的检测性能并降低计算冗余.实验结果表明,FES-DETR显著提高了检测性能,准确率、召回率较RT-DETR-r18分别提升了2.6和2.3个百分点,mAP@0.5和mAP@0.5∶0.95分别提升了3.2和2.1个百分点,参数量和计算量分别下降了3.0 M和8.5 G,FPS提高至95.7帧/s.与YOLO系列等主流目标检测模型相比,该模型展现出更优越的性能,为水下小型生物检测提供了高效的技术手段. 展开更多
关键词 色偏环境 小型生物 目标检测 RT-DETR 纠缠Transformer
暂未订购 下载PDF
基于改进RT-DETR的有遮挡交通标志检测算法 认领 引用
13
作者 于天河 杨壮壮 +2 位作者 胡金帅 常梦瑶 王文龙 《工程科学学报》 EI CAS CSCD 北大核心 2026年第2期393-408,共16页
针对交通标志检测中目标尺寸小、检测精度低等问题,尤其是在远距离拍摄、遮挡严重的情况下,传统检测算法往往难以准确识别交通标志.本文提出了一种基于改进RT-DETR的交通标志检测算法.首先,考虑到当前交通标志被遮挡情况下数据集的匮乏... 针对交通标志检测中目标尺寸小、检测精度低等问题,尤其是在远距离拍摄、遮挡严重的情况下,传统检测算法往往难以准确识别交通标志.本文提出了一种基于改进RT-DETR的交通标志检测算法.首先,考虑到当前交通标志被遮挡情况下数据集的匮乏,自建一个遮挡条件下的交通标志数据集.然后,在反向残差移动块中引入膨胀重参数块,构建了一个轻量级的复合膨胀残差块来替换原始主干提取网络中的BasicBlock,增强了模型的特征提取能力.最后,对RT-DETR模型的损失函数进行了优化,提出了DS-IoU联合损失函数加快收模型敛速度.实验结果表明,改进后的算法在自制数据集上的m AP为94.2%,相比于原始算法增加量为4.7%,在公开数据集TT100K和CCTSDB2021的m AP分别为92.8%和91.7%,相比于原始算法增加量分别为3.1%和2.4%,Params和GFLOPs相比于原始的算法分别降低了26.0%和12.5%.本文提出的改进方法极大地减少了计算量和参数数量,有效提升了遮挡情况下的交通标志的检测精度. 展开更多
关键词 交通标志检测 RT-DETR 遮挡数据集 轻量化 联合损失函数
暂未订购 下载PDF
基于改进RT-DETR的储粮害虫检测算法研究 认领 引用
14
作者 吕宗旺 信艺阳 +3 位作者 甄彤 孙福艳 关智中 赵梓涵 《粮油食品科技》 CAS CSCD 北大核心 2026年第4期22-33,I0005,共12页
在粮食储藏过程中开展高效、准确的害虫检测具有重要意义。针对传统检测算法在复杂背景下检测精度不高、易出现误检漏检等问题,本文提出一种改进的RT-DETR检测模型。基于已有的多尺度增强模块与门控部分注意力机制,构建了多尺度增强门... 在粮食储藏过程中开展高效、准确的害虫检测具有重要意义。针对传统检测算法在复杂背景下检测精度不高、易出现误检漏检等问题,本文提出一种改进的RT-DETR检测模型。基于已有的多尺度增强模块与门控部分注意力机制,构建了多尺度增强门控部分注意力网络(MEGPANet)以替换原始主干网络,从而增强模型对害虫边缘轮廓及局部特征的提取能力。引入多样性分支块(DBB)替换原始RepBlock模块以增强模型的跨尺度特征融合能力。在特征交互模块阶段(AIFI)采用条件位置编码生成器(PEG)动态注入位置信息,进一步提升对微小害虫的定位精度和检测精度。结果表明,改进后的模型其精确率、mAP@0.5及mAP@0.5:0.95分别提升0.9、5.5和3.4个百分点。在精度提升的同时,模型的计算量也显著下降。与其他主流目标检测模型相比,本文改进的RT-DETR模型在检测精度和综合性能方面表现出一定优势,表明该模型能够较好地适应复杂储粮场景下的害虫检测任务。 展开更多
关键词 目标检测 RT-DETR 储粮害虫 注意力机制 特征融合
暂未订购 下载PDF
Low-complexity APSK demodulation algorithm based on K-means clustering in LEO satellite communication systems 认领 引用
15
作者 Guangfu Wu Xiangrui Meng +1 位作者 Changlin Chen Biqun Xiang 《Digital Communications and Networks》 SCIE EI CSCD 2026年第2期343-353,共11页
Amplitude Phase Shift Keying(APSK)is more suitable for the nonlinear channels of Low Earth Orbit(LEO)satellite communication systems compared to Quadrature Amplitude Modulation(QAM).To tackle challenges posed by Direc... Amplitude Phase Shift Keying(APSK)is more suitable for the nonlinear channels of Low Earth Orbit(LEO)satellite communication systems compared to Quadrature Amplitude Modulation(QAM).To tackle challenges posed by Direct Current(DC)interference and high demodulation complexity,we propose an APSK demodulation algorithm based on K-means clustering.Initially,static DC components are calculated and removed from the received APSK signals.Subsequently,the estimated APSK constellation points serve as initial centers for K-means clustering.These centers are refined through the K-means process and act as theoretical APSK constellation points for the Max-Log-MAP demodulation algorithm,effectively eliminating residual DC.We then introduce a low-complexity APSK demodulation algorithm that utilizes the symmetry of constellation points along with the Euclidean distance between DC-eliminated signals and these constellation points to minimize the set of constellation points.Simulation results indicate that for 32-APSK,our proposed demodulation submodule reduces computational complexity to approximately one-third that of the Max-Log-MAP algorithm while improving Bit Error Rate(BER)performance by about 0.23 dB.Furthermore,end-to-end simulation experiments conducted within LEO satellite communication systems demonstrate that our approach not only maintains this complexity advantage but also enhances BER performance by approximately 1.1 dB. 展开更多
关键词 DC elimination APSK demodulation LEO satellite communication K-means algorithm Max-Log-MAP algorithm
暂未订购 下载PDF
基于改进RT-DETR的ROV机器人水下小目标检测方法 认领 引用
16
作者 董绍江 陈智雄 +4 位作者 夏浩然 孙世政 罗家元 陈才 夏亮 《计算机工程与应用》 EI CSCD 北大核心 2026年第16期275-286,共12页
针对机器人在水下小目标生物检测过程中,因水下背景环境复杂,存在图像模糊与退化失真,以及模型过大导致移动端部署困难,易出现错检、漏检等问题,提出一种基于RT-DETR(real-time detection transformer)改进的轻量化水下小目标检测算法MS... 针对机器人在水下小目标生物检测过程中,因水下背景环境复杂,存在图像模糊与退化失真,以及模型过大导致移动端部署困难,易出现错检、漏检等问题,提出一种基于RT-DETR(real-time detection transformer)改进的轻量化水下小目标检测算法MSD-DETR(multiscale Starnet dynamics detection transformer)。设计了轻量型网络M-Starnet替代原主干网络,实现模型轻量化并保留丰富的目标特征;引入动态范围直方图自注意力(dynamic-range histogram self-attention,DHSA)模块,通过增强动态范围适应性及保留边缘纹理,提升模型弱信号小目标的细节恢复能力;基于原始的跨尺度特征融合模块设计多尺度小波残差特征增强融合金字塔,在不增加参数的前提下提升小目标的表征能力与检测精度。实验结果表明,MSD-DETR模型相较于基线模型,在DUO数据集上平均精度值mAP提高了2.2个百分点,参数量与计算量分别降低了36.8%与48.1%。由此可见,提出的模型兼顾了轻量化和精度的提升。将算法部署至自研的水下机器人进行测试,验证了方法的实用性。 展开更多
关键词 小目标检测 RT-DETR 轻量化 特征金字塔 ROV机器人
暂未订购 下载PDF
A Metaheuristic Football Optimization Algorithm Integrated with Large Language Models for Automated Seismic Time-Series Modeling 认领 引用
17
作者 Amal H.Alharbi Marwa M.Eid +2 位作者 Nima Khodadadi Ebrahim A.Mattar Sayed Elkenawy 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第5期947-987,共41页
Seismic time series forecasting remains challenging due to the nonlinearity,non-stationarity,and noise of earthquake data,and because deep learning models are sensitive to preprocessing and hyperparameter settings.Alt... Seismic time series forecasting remains challenging due to the nonlinearity,non-stationarity,and noise of earthquake data,and because deep learning models are sensitive to preprocessing and hyperparameter settings.Although recent studies have improved neural architectures and optimization techniques,preprocessing is often treated as a fixed or manually designed stage,with limited integration into model optimization.To address this,this paper proposes an integrated,data-driven modelling framework that combines guided preprocessing with systematic hyperparameter optimization for seismic prediction,specifically forecasting earthquake magnitude from seismic catalog time-series data,with experiments conducted on Canadian seismic records.The method uses a Large Language Model to guide data preparation and feature engineering,rather than fully automate them,and applies deep learning-based forecasting with the N-HITS architecture,optimized via metaheuristic-assisted feature selection and hyperparameter tuning.The Football Optimization Algorithm(FbOA),employed as a metaheuristic optimization strategy in this study,is evaluated and compared with several well-known optimizers under identical conditions.The results show significant performance gains,with FbOA achieving superior accuracy,robustness,and convergence compared to baseline and competing methods.Notably,error metrics are reduced(MSE 3.10×10-7,RMSE 5.57×103),with high performance indicators(r=0.982,R2=0.979,NSE=0.981,WI=0.985).These results highlight the value of integrating guided preprocessing with optimization and demonstrate a scalable framework for high-precision time-series prediction in geophysical and related domains. 展开更多
关键词 Seismic time-series forecasting large language models metaheuristic algorithms football optimization algorithm earthquake modeling
暂未订购 下载PDF
A Quantum-Inspired Algorithm for Clustering and Intrusion Detection 认领 引用
18
作者 Gang Xu Lefeng Wang +5 位作者 Yuwei Huang Yong Lu Xin Liu Weijie Tan Zongpeng Li Xiu-Bo Chen 《Computers, Materials & Continua》 SCIE EI 2026年第4期1180-1215,共36页
The Intrusion Detection System(IDS)is a security mechanism developed to observe network traffic and recognize suspicious or malicious activities.Clustering algorithms are often incorporated into IDS;however,convention... The Intrusion Detection System(IDS)is a security mechanism developed to observe network traffic and recognize suspicious or malicious activities.Clustering algorithms are often incorporated into IDS;however,conventional clustering-based methods face notable drawbacks,including poor scalability in handling high-dimensional datasets and a strong dependence of outcomes on initial conditions.To overcome the performance limitations of existing methods,this study proposes a novel quantum-inspired clustering algorithm that relies on a similarity coefficient-based quantum genetic algorithm(SC-QGA)and an improved quantum artificial bee colony algorithm hybrid K-means(IQABC-K).First,the SC-QGA algorithmis constructed based on quantum computing and integrates similarity coefficient theory to strengthen genetic diversity and feature extraction capabilities.For the subsequent clustering phase,the process based on the IQABC-K algorithm is enhanced with the core improvement of adaptive rotation gate and movement exploitation strategies to balance the exploration capabilities of global search and the exploitation capabilities of local search.Simultaneously,the acceleration of convergence toward the global optimum and a reduction in computational complexity are facilitated by means of the global optimum bootstrap strategy and a linear population reduction strategy.Through experimental evaluation with multiple algorithms and diverse performance metrics,the proposed algorithm confirms reliable accuracy on three datasets:KDD CUP99,NSL_KDD,and UNSW_NB15,achieving accuracy of 98.57%,98.81%,and 98.32%,respectively.These results affirm its potential as an effective solution for practical clustering applications. 展开更多
关键词 Intrusion detection clustering quantum artificial bee colony algorithm K-means quantum genetic algorithm
暂未订购 下载PDF
基于改进RT-DETR的农作物害虫检测算法 认领 引用 被引量：1
19
作者 许光宇 林浩杰 《齐鲁工业大学学报》 CAS 2026年第1期26-37,共12页
针对农作物害虫检测中害虫目标被遮挡、体色与环境相近等情况导致的目标检测准确率不高的问题,提出了一种基于RT-DETR的农作物害虫检测算法RT-DETR-SDIC。首先,原主干网络的前两层(S2,S3)引入多样分支残差模块(Diverse Branch Residual ... 针对农作物害虫检测中害虫目标被遮挡、体色与环境相近等情况导致的目标检测准确率不高的问题,提出了一种基于RT-DETR的农作物害虫检测算法RT-DETR-SDIC。首先,原主干网络的前两层(S2,S3)引入多样分支残差模块(Diverse Branch Residual Block,DBRB),利用多分支拓扑结构以及不同规模的路径提取多尺度的特征信息,在原主干网络的后两层(S4,S5)引入了结合级联注意力的倒立残差移动模块(Invert Residual Mobile Block with Cascade Group Attention,IRMB_CGA),弥补了原主干网络中长距离语义信息无法直接交互的问题,增强了对环境特征的辨别能力;其次,在特征融合网络中,增加了无参数注意力的空间到深度融合层(Space to Depth Convolution with Attention,SPA)提取细粒度的信息,设计了内容引导融合模块(Context Guide Fusion Module,CGFM)来引导多尺度特征融合。实验结果表明模型RT-DETR-SDIC参数下降了19.6%,计算量下降了9.9%,PmA,0.5上升了6.2%,PmA,0.5:0.95上升了2.6%。 展开更多
关键词 害虫检测 多尺度特征融合 RT-DETR 智慧农业
暂未订购 下载PDF
基于改进RT-DETR网络的小目标识别算法研究 认领 引用
20
作者 胡建功 卜旭阳 +2 位作者 高万里 王全伟 秦晋 《汽车技术》 CSCD 北大核心 2026年第8期12-18,共7页
针对RT-DETR(Real-Time Detection Transformer)网络在复杂场景与小目标检测中存在的精度不足与速度受限问题,提出了一种面向车辆图像的改进检测算法。该算法通过引入空间位置关系建模,增强对车辆、行人等小尺度目标的特征捕获能力,并... 针对RT-DETR(Real-Time Detection Transformer)网络在复杂场景与小目标检测中存在的精度不足与速度受限问题,提出了一种面向车辆图像的改进检测算法。该算法通过引入空间位置关系建模,增强对车辆、行人等小尺度目标的特征捕获能力,并采用门控机制提升网络的非线性建模性能。同时,通过分离高频与低频细节信息,结合特征图的分割与拼接操作,实现了无信息丢失的特征采样。通过将卷积单元Conv和批量归一化单元BN融合处理来减少中间处理环节和内存消耗,提高计算效率和优化模型性能。试验结果表明,相较于原始RT-DETR网络,改进算法在mAP50、mAP50∶95、精度及召回率上分别提升了6%、4.5%、4.2%与4%。因此,优化主干网络结构并强化多尺度特征融合,聚焦细粒度信息与空频域特征,是提升复杂环境下车辆检测性能的有效策略。 展开更多
关键词 RT-DETR 车辆识别 特征采样 多尺度特征融合 空频域特征
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