检索结果-南通市图书馆

Multi-Channel Based on Attention Network for Infrared small target detection

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 414-427页

作者：张彦军王碧云蔡云泽 Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Shanghai Institute of Aerospace Control Technology Shanghai 201109China Infrared detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai 201109China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China

Infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking ***,the complex background,the strong noise,and the characteristics of small scale and weak intensity of targets bring great difficulties to the detection of infrared small targets.A multi-channel based on attention network is proposed in this paper,aimed at the problem of high missed detection rate and false alarm rate of traditional algorithms and the problem of large model,high complexity and poor detection performance of deep learning ***,given the difficulty in extracting the features of infrared multiscale and small dim targets,the multiple channels are designed based on dilated convolution to capture multiscale target ***,the coordinate attention block is incorporated in each channel to suppress background clutters adaptively and enhance target *** addition,the fusion of shallow detail features and deep abstract semantic features is realized by synthesizing the contextual attention fusion ***,it is verified that,compared with other state-of-the-art methods based on the datasets SIRST and MDFA,the proposed algorithm further improves the detection effect,and the model size and computational complexity are smaller.

关键词： infrared image small target detection deep learning attention mechanism feature fusion

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dim Moving small target detection by Local and Global Variance Filtering on Temporal Profiles in Infrared Sequences

引用

航空兵器 2019年第6期26卷 43-49页

作者： Chen Hao Liu Delian School of Electronic Engineering Xidian UniversityXi’an 710071China School of Physics and Optoelectronic Engineering Xidian UniversityXi’an 710071China

In this paper, the temporal different characteristics between the target and background pixels are used to detect dim moving targets in the slow-evolving complex background. A local and global variance filter on temporal profiles is presented that addresses the temporal characteristics of the target and background pixels to eliminate the large variation of background temporal profiles. Firstly, the temporal behaviors of different types of image pixels of practical infrared scenes are ***, the new local and global variance filter is proposed. The baseline of the fluctuation level of background temporal profiles is obtained by using the local and global variance filter. The height of the target pulse signal is extracted by subtracting the baseline from the original temporal profiles. Finally, a new target detection criterion is designed. The proposed method is applied to detect dim and small targets in practical infrared sequence images. The experimental results show that the proposed algorithm has good detection performance for dim moving small targets in the complex background.

关键词： small target detection infrared image sequences complex background temporal profile variance filtering

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

small target detection Algorithm in Sea-Sky-Line Area Based on Lifting Wavelet Mutual Energy

Small Target Detection Algorithm in Sea-Sky-Line Area Based ...

引用

第三十九届中国控制会议

作者： Li Su Yuhan Suo Shihui Wen Ruizhe Zhang Di Pang College of Automation Harbin Engineering University

small target detection in complex sea-sky background is a difficult problem in the field of computer vision. Aiming at the panoramic marine visible light images collected by the panoramic vision system, a small target detection algorithm based on lifting wavelet mutual energy in the sea-sky-line area is proposed in this paper. First of all, the AC method is used to eliminate the influence of most hulls and equipment in the panoramic image;then, the sea-sky-line can be extracted by using the improved gradient Hough circle transform algorithm;finally, utilizing the characteristics of small targets as non-stationary signals in the image, the coefficients of lifting wavelet are cross-calculated, and because the mutual energy value of the small target is higher than other non-target points, small targets can be detected in the panoramic sea-sky-line area. Experimental results show that this method can effectively detect small targets in the panoramic sea-sky-line area.

关键词： small target detection lifting wavelet mutual energy method sea-sky-line detection visual saliency map improved gradient Hough circle transformation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Improved small target detection Method for SAR Image Based on YOLOv7

引用

印刷与数字媒体技术研究 2024年第5期 53-62页

作者： YANG Ke SI Zhan-jun ZHANG Ying-xue SHI Jin-yu College of Artificial Intelligence Tianjin University of Science and TechnologyTianjin 300457China

In order to solve the problems that the current synthetic aperture radar(SAR)image target detection method cannot adapt to targets of different sizes,and the complex image background leads to low detection accuracy,an improved SAR image small target detection method based on YOLOv7 was proposed in this *** proposed method improved the feature extraction network by using Switchable Around Convolution(SAConv)in the backbone network to help the model capture target information at different scales,thus improving the feature extraction ability for small *** on the attention mechanism,the DyHead module was embedded in the target detection head to reduce the impact of complex background,and better focus on the small *** addition,the NWD loss function was introduced and combined with CIoU *** to the CIoU loss function typically used in YOLOv7,the NWD loss function pays more attention to the processing of small targets,so as to further improve the detection ability of small *** experimental results on the HRSID dataset indicate that the proposed method achieved mAP@0.5 and mAP@0.95 scores of 93.5%and 71.5%,*** to the baseline model,this represents an increase of 7.2%and 7.6%,*** proposed method can effectively complete the task of SAR image small target detection.

关键词： small target detection Synthetic aperture radar YOLOv7 DyHead module Switchable Around Convolution

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Wavelet Mutual Energy Combination Method detection Algorithm for small target in Complex Background

Wavelet Mutual Energy Combination Method Detection Algorithm...

引用

第七届国际粉体检测与控制学术会议

作者： Wei Ying Li Jun Ma Lai Luan Guoxin College of Information Science and Engineering,Northeastem University,China No.11,Lane 3,Wenhua Road,Heping District,Shenyang 110004,China

A small target detection method of infrared imagery in complex background of sea and sky is studied,and an al- gorithm based on wavelet analysis and mutual energy combination is *** Mutual Energy Combination (WMEC)functions are defined in horizontal and vertical *** are enhanced and disturbances of background are weakened efficiently by WMEC processing at the two *** are coarsely segmented with thresholds which are set automatically by a method of part gray histogram *** of coarse segmentation in the two direc- tions are integrated,and targets are located by means of maximum energy *** size of targets is decided by comparing the dissimilarity between a couple of *** results indicate that the method can be appropriate in both kinds background of land and *** is with high correct detection ratio from a single image,and high speed to re- alize.

关键词： small target detection Wavelet mutual energy combination Gray histogram analysis

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Hybrid Feature Fusion Traffic Sign detection Algorithm Based on YOLOv7

引用

Computers, Materials & Continua 2024年第7期80卷 1425-1440页

作者： Bingyi Ren Juwei Zhang Tong Wang School of Mechanical Engineering Henan University of Science and TechnologyLuoyang471000China School of Information Engineering Henan University of Science and TechnologyLuoyang471000China School of Electronic Information Zhengzhou Institute of Aeronautical Industry ManagementZhengzhou450046China Henan Province New Energy Vehicle Power Electronics and Power Transmission Engineering Research Center Luoyang471000China

Autonomous driving technology has entered a period of rapid development,and traffic sign detection is one of the important *** target detection networks are difficult to adapt to scenarios where target sizes are seriously imbalanced,and traffic sign targets are small and have unclear features,which makes detection more ***,we propose aHybrid Feature Fusion Traffic Sign detection algorithmbased onYOLOv7(HFFTYOLO).First,a self-attention mechanism is incorporated at the end of the backbone network to calculate feature interactions within scales;Secondly,the cross-scale fusion part of the neck introduces a bottom-up multi-path fusion *** reuse paths at the end of the neck,paying particular attention to cross-scale fusion of highlevel *** addition,we found the appropriate channel width through a lot of experiments and reduced the superfluous *** terms of training,a newregression lossCMPDIoUis proposed,which not only considers the problem of loss degradation when the aspect ratio is the same but the width and height are different,but also enables the penalty term to dynamically change at different ***,our proposed improved method shows excellent results on the TT100K *** with the baseline model,without increasing the number of parameters and computational complexity,AP0.5 and AP increased by 2.2%and 2.7%,respectively,reaching 92.9%and 58.1%.

关键词： small target detection YOLOv7 traffic sign detection regression loss

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An improved defect recognition framework for casting based on DETR algorithm

引用

Journal of Iron and Steel Research International 2023年第5期30卷 949-959页

作者： Long Zhang Sai-fei Yan Jun Hong Qian Xie Fei Zhou Song-lin Ran Anhui Province Key Laboratory of Metallurgical Engineering&Resources Recycling Anhui University of TechnologyMa’anshan 243002AnhuiChina School of Metallurgical Engineering Anhui University of TechnologyMa’anshan 243002AnhuiChina Technical Department Anhui Highly Precision Casting Co.Ltd.Ma’anshan 238100AnhuiChina Anhui Engineering Laboratory for Intelligent Applications and Security of Industrial Internet Anhui University of TechnologyMa’anshan 243032AnhuiChina

The current casting surface defect detection algorithms suffer from poor small target defect recognition and imbalance between detection performance and detection *** improved algorithmic framework for casting defect detection was proposed based on the detection TRansformer(DETR)*** algorithm takes ResNet with an efficient channel attention(ECA)-Net module as the backbone *** addition,based on the original algorithm architecture,dynamic anchor boxes,improved multi-scale deformable attention module,and SIoU loss function are introduced to improve the sensitivity of transformer structure to input location information and scale size,and the small target defect detection performance is effectively *** recognition performance of the algorithm in a self-built casting defect dataset was *** improved DETR algorithm has 97.561% accuracy in recognizing two defects,namely sandinclusion and notch,with the detection rate being improved by 65.854% and 17.073% compared with the original DETR and you only look once(Yolo)-V5,*** algorithm verifies the applicability of the transformer architecture target detection algorithm for casting defect detection tasks and provides new ideas for detecting other similar application scenarios.

关键词： Casting defect recognition detection TRansformer small target detection Deep learning Attention mechanism

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A spatiotemporal intelligent framework and experimental platform for urban digital twins

引用

Virtual Reality & Intelligent Hardware 2023年第3期5卷 213-231页

作者： Jinxing HU Zhihan LV Diping YUAN Bing HE Wenjiang CHEN Xiongfei YE Donghao LI Ge YANG Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Department of Game Design Faculty of ArtsUppsala UniversityUppsala SE-75105Sweden Shenzhen Urban Public Safety and Technology Institute Co.Ltd Shenzhen 518172China

Backgrounds This work emphasizes the current research status of the urban Digital Twins to establish an intelligent spatiotemporal framework.A Geospatial Artificial Intelligent(GeoAI)system is developed based on the Geographic Information System and Artificial *** integrates multi-video technology and Virtual City in urban Digital *** Besides,an improved small object detection model is proposed:YOLOv5-Pyramid,and Siamese network video tracking models,namely MPSiam and FSSiamese,are ***,an experimental platform is built to verify the georeferencing correction scheme of video *** The MultiplyAccumulate value of MPSiam is 0.5B,and that of ResNet50-Siam is ***,the model is compressed by *** inference speed has increased by 3.3 times,reaching 83 Frames Per Second.3%of the Average Expectation Overlap is ***,the urban Digital Twins-oriented GeoAI framework established here has excellent performance for video georeferencing and target detection problems.

关键词： Spatiotemporal intelligence Urban digital twins Geographic information system Artificial intelligence small target detection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

FPC-BTB detection and positioning system based on optimized YOLOv5

引用

Biomimetic Intelligence & Robotics 2023年第4期3卷 56-66页

作者： Changyu Jing Tianyu Fu Fengming Li Ligang Jin Rui Song School of Control Science and Engineering Shandong UniversityJinan 250000China School of Information and Engineering Shandong Jianzhu UniversityJinan 250101China Shandong Industrial Technology Research Institute Jinan 250100China

With the aim of addressing the visual positioning problem of board-to-board(BTB)jacks during the automatic assembly of flexible printed circuit(FPC)in mobile phones,an FPC-BTB jack detection method based on the optimized You Only Look Once,version 5(YOLOv5)deep learning algorithm was proposed in this *** FPC-BTB jack real-time detection and positioning system was developed for the real-time target detection and pose output synchronization of the BTB *** that basis,a visual positioning experimental platform that integrated a UR5e manipulator arm and Hikvision industrial camera was built for BTB jack detection and positioning *** indicated by the experimental results,the developed FPC-BTB jack detection and positioning system for BTB target recognition and positioning achieved a success rate of 99.677%.Its average detection accuracy reached 99.341%,the average confidence of the detected target was 91%,the detection and positioning speed reached 31.25 frames per second,and the positioning deviation was less than 0.93 mm,which conforms to the practical application requirements of the FPC assembly process.

关键词： detection and positioning systems Deep learning small target detection Posture estimation Flexible printed circuit

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

RT-YOLO:A Residual Feature Fusion Triple Attention Network for Aerial Image target detection

引用

Computers, Materials & Continua 2023年第4期75卷 1411-1430页

作者： Pan Zhang Hongwei Deng Zhong Chen College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China

In recent years,target detection of aerial images of unmannedaerial vehicle(UAV)has become one of the hottest ***,targetdetection of UAV aerial images often presents false detection and *** proposed a modified you only look once(YOLO)model toimprove the problems arising in object detection in UAV aerial images:(1)A new residual structure is designed to improve the ability to extract featuresby enhancing the fusion of the inner features of the single *** the sametime,triplet attention module is added to strengthen the connection betweenspace and channel and better retain important feature information.(2)Thefeature information is enriched by improving the multi-scale feature pyramidstructure and strengthening the feature fusion at different scales.(3)A newloss function is created and the diagonal penalty term of the anchor frame isintroduced to improve the speed of training and the accuracy of *** proposed model is called residual feature fusion triple attention YOLO(RT-YOLO).Experiments showed that the mean average precision(mAP)ofRT-YOLO is increased from 57.2%to 60.8%on the vehicle detection in aerialimage(VEDAI)dataset,and the mAP is also increased by 1.7%on the remotesensing object detection(RSOD)*** results show that theRT-YOLOoutperforms other mainstream models in UAV aerial image object detection.

关键词： Attention mechanism small target detection YOLOv5s RT-YOLO

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：