检索结果-内蒙古大学图书馆

信号处理 2023年第9期39卷 1608-1620页

作者：熊博莅孙忠镇邹博计科峰匡纲要国防科技大学电子科学学院湖南长沙410073 国防科技大学电子科学学院电子信息系统复杂电磁环境效应国家重点实验室湖南长沙410073 陆军航空兵学院研究所北京101121

随着深度学习在计算机视觉领域取得令人鼓舞的成果,基于深度学习技术实现对合成孔径雷达(Synthetic Aperture Radar,SAR)图像中时敏目标的分类识别已成为可能,实测SAR图像中时敏目标自动识别应用再次吸引了全球广大学者的目光。受客观... 详细信息

随着深度学习在计算机视觉领域取得令人鼓舞的成果,基于深度学习技术实现对合成孔径雷达(Synthetic Aperture Radar,SAR)图像中时敏目标的分类识别已成为可能,实测SAR图像中时敏目标自动识别应用再次吸引了全球广大学者的目光。受客观条件所限,高质量实测SAR目标样本切片的获取代价大、成本高、数量少,且SAR对成像参数和目标姿态敏感,导致SAR图像面临的少样本条件下的目标识别问题更为突出。本文深度挖掘MSTAR(Moving and Stationary Target Acquisition and Recognition)数据集的目标识别潜力,针对10类SAR图像车辆目标分类识别潜能进行了研究和分析。为衡量不同样本数量条件下SAR目标识别潜能,同时降低对目标样本选取的随机性,提出利用不同数量实测训练样本,生成全角度训练数据集,对参与训练的样本进行规范化和合理化采样处理;将全角度扩充后得到的训练样本集作为标准模板数据集,通过遍历模板数据集,采用似然比相似性度量(Likelihood Ratio Similarity Measure,LiRSM)来衡量目标相似性,利用SAR图像的灰度统计特性,基于变化检测技术构建变化检测量,实现SAR车辆目标的分类识别;基于MSTAR数据集,深入开展了10-Way-N-Shot的少样本条件下的SAR车辆目标分类识别问题研究,并通过试验对比形成性能基准,方便其他学者在该数据集中进一步开展少样本条件下目标识别对比分析。

关键词：合成孔径雷达目标识别深度学习时敏目标少样本

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Vibration Analysis through data-Backed Pipeline Optimisation

引用

SENSORS 2021年第19期21卷 6678-6678页

作者： Sokolovsky, Artur Hare, David Mehnen, Jorn Univ Strathclyde Dept Design Mfg & Engn Management Glasgow G1 1XJ Lanark Scotland Bosch Rexroth Ltd St Neots PE19 2ES England

Vibration analysis is an active area of research, aimed, among other targets, at an accurate classification of machinery failure modes. The analysis often leads to complex and convoluted signal processing pipeline designs, which are computationally demanding and often cannot be deployed in IoT devices. In the current work, we address this issue by proposing a data-driven methodology that allows optimising and justifying the complexity of the signal processing pipelines. Additionally, aiming to make IoT vibration analysis systems more cost- and computationally efficient, on the example of MAFAULDA vibration dataset, we assess the changes in the failure classification performance at low sampling rates as well as short observation time windows. We find out that a decrease of the sampling rate from 50 kHz to 1 kHz leads to a statistically significant classification performance drop. A statistically significant decrease is also observed for the 0.1 s time window compared to the 5 s one. However, the effect sizes are small to medium, suggesting that in certain settings lower sampling rates and shorter observation windows might be worth using, consequently making the use of the more cost-efficient sensors feasible. The proposed optimisation approach, as well as the statistically supported findings of the study, allow for an efficient design of IoT vibration analysis systems, both in terms of complexity and costs, bringing us one step closer to the widely accessible IoT/Edge-based vibration analysis.

关键词： signal processing optimisation IoT MAFAULDA vibration analysis failure mode classification machine learning effect sizes hypothesis testing

来源：评论

学校读者我要写书评

暂无评论

基于几何透视图像预处理和CNN的全景图像交通标志识别算法

引用

计算机应用与软件 2024年第7期41卷 171-176页

作者：曹峻凡张向利闫坤张红梅桂林电子科技大学广西无线宽带通信与信号处理重点实验室广西桂林541004

为解决深度学习方法在高清全景图像中检测交通标志遇到图形处理器资源不足、小目标容易漏检、检测速度过慢等问题,采用小目标过采样训练数据生成方法、图像分块和几何透视检测预处理方法以及改进的轻量神经网络Improved-Tiny-YOLOv3,提... 详细信息

为解决深度学习方法在高清全景图像中检测交通标志遇到图形处理器资源不足、小目标容易漏检、检测速度过慢等问题,采用小目标过采样训练数据生成方法、图像分块和几何透视检测预处理方法以及改进的轻量神经网络Improved-Tiny-YOLOv3,提出了一种基于深度学习的轻量级全景图像中交通标志检测方法。并在Tsinghua-Tencent 100K数据集上进行了实验,mAP值达到92.7%,在Nvidia 1080Ti显卡上检测速度可达到20 FPS,实验结果验证了所提方法的有效性。

关键词：交通标志检测识别 Improved-Tiny-YOLOv3 几何透视法随机裁剪 CIoU 全景图像

来源：评论

学校读者我要写书评

暂无评论

Compressive Radar Imaging of Stationary Indoor targets With Low-Rank Plus Jointly Sparse and Total Variation Regularizations

引用

IEEE TRANSACTIONS ON IMAGE processing 2020年 29卷 4598-4613页

作者： Tang, Van Ha Bouzerdoum, Abdesselam Phung, Son Lam Le Quy Don Tech Univ Fac Informat Technol Hanoi 10000 Vietnam Hamad Bin Khalifa Univ Informat & Comp Technol Div Coll Sci & Engn Doha Qatar Univ Wollongong Sch Elect Comp & Telecommun Engn Wollongong NSW 2522 Australia

This paper addresses the problem of wall clutter mitigation and image reconstruction for through-wall radar imaging (TWRI) of stationary targets by seeking a model that incorporates low-rank (LR), joint sparsity (JS), and total variation (TV) regularizers. The motivation of the proposed model is that LR regularizer captures the low-dimensional structure of wall clutter;JS guarantees a small fraction of target occupancy and the similarity of sparsity profile among channel images;TV regularizer promotes the spatial continuity of target regions and mitigates background noise. The task of wall clutter mitigation and target image reconstruction is formulated as an optimization problem comprising LR, JS, and TV regularization terms. To handle this problem efficiently, an iterative algorithm based on the forward-backward proximal gradient splitting technique is introduced, which captures wall clutter and yields target images simultaneously. Extensive experiments are conducted on real radar data under compressive sensing scenarios. The results show that the proposed model enhances target localization and clutter mitigation even when radar measurements are significantly reduced.

关键词： Clutter Radar imaging TV Image reconstruction Optimization Antenna measurements Through-the-wall radar imaging wall clutter mitigation compressed sensing regularized optimization low-rank matrix recovery sparse signal reconstruction proximal gradient technique

来源：评论

学校读者我要写书评

暂无评论

data-Driven Target Localization Using Adaptive Radar processing and Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Venkatasubramanian, Shyam Gogineni, Sandeep Kang, Bosung Pezeshki, Ali Rangaswamy, Muralidhar Tarokh, Vahid The Department of Electrical and Computer Engineering Duke University DurhamNC27705 United States Information Systems Laboratories Inc. DaytonOH45431 United States The University of Dayton Research Institute DaytonOH45469 United States The Department of Electrical and Computer Engineering Colorado State University Fort CollinsCO80523 United States The United States Air Force Research Laboratory Wright-Patterson Air Force Base OH45433 United States

Leveraging the advanced functionalities of modern radio frequency (RF) modeling and simulation tools, specifically designed for adaptive radar processing applications, this paper presents a data-driven approach to improve accuracy in radar target localization post adaptive radar detection. To this end, we generate a large number of radar returns by randomly placing targets of variable strengths in a predefined area, using RFView®, a high-fidelity, site-specific, RF modeling & simulation tool. We produce heatmap tensors from the radar returns, in range, azimuth [and Doppler], of the normalized adaptive matched filter (NAMF) test statistic. We then train a regression convolutional neural network (CNN) to estimate target locations from these heatmap tensors, and we compare the target localization accuracy of this approach with that of peak-finding and local search methods. This empirical study shows that our regression CNN achieves a considerable improvement in target location estimation accuracy. The regression CNN offers significant gains and reasonable accuracy even at signal-to-clutter-plus-noise ratio (SCNR) regimes that are close to the breakdown threshold SCNR of the NAMF. We also study the robustness of our trained CNN to mismatches in the radar data, where the CNN is tested on heatmap tensors collected from areas that it was not trained on. We show that our CNN can be made robust to mismatches in the radar data through few-shot learning, using a relatively small number of new training samples. © 2022, CC BY.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

基于损失加权修正的舰船目标HRRP小样本元学习识别方法

引用

信号处理 2022年第12期38卷 2460-2468页

作者：简涛王哲昊王海鹏刘瑜魏广芬海军航空大学信息融合研究所山东烟台264001 山东工商学院信息与电子工程学院山东烟台264005

针对现有小样本高分辨距离像(high resolution range profile,HRRP)元学习识别方法难以适应任务经验差异的问题,提出了基于损失加权修正的舰船目标元学习识别方法。该方法以元学习理论为基础,设计了基础学习器与元学习器相结合的预训练... 详细信息

针对现有小样本高分辨距离像(high resolution range profile,HRRP)元学习识别方法难以适应任务经验差异的问题,提出了基于损失加权修正的舰船目标元学习识别方法。该方法以元学习理论为基础,设计了基础学习器与元学习器相结合的预训练模型。由于不同的特性损失可反映出学习经验的差异程度,故基于任务损失值对元学习器的损失函数进行加权处理,以减轻不同任务的偏差影响。然后,利用预训练模型对仿真数据的学习经验,在小样本测试任务集上进行舰船目标实测HRRP的分类识别。实验结果表明,所提方法与对比模型相比,可在小样本条件下获得更佳的识别效果,具备良好的小样本分类识别能力。

关键词：舰船识别高分辨距离像元学习卷积神经网络小样本

来源：评论

学校读者我要写书评

暂无评论

E-Agriculture Planning Tool for Supporting smallholder Cocoa Intensification Using Remotely Sensed data

引用

REMOTE SENSING 2023年第14期15卷 3492-3492页

作者： Singh, Kanika Fuentes, Ignacio Al-Shammari, Dhahi Fidelis, Chris Butubu, James Yinil, David Sharififar, Amin Minasny, Budiman Guest, David, I Field, Damien J. Univ Sydney Sydney Inst Agr Sch Life & Environm Sci Sydney NSW 2015 Australia Univ Chile Fac Ciencias Fis & Matemat Santiago 8330111 Chile Cocoa Board Papua New Guinea Head Off POB 532 Kokopo Papua N Guinea James Hutton Inst Aberdeen AB15 8QH Aberdeen Scotland

Remote sensing approaches are often used to monitor land cover change. However, the small physical size (about 1-2 hectare area) of smallholder orchards and the cultivation of cocoa (Theobroma cocoa L.) under shade trees make the use of many popular satellite sensors inefficient to distinguish cocoa orchards from forest areas. Nevertheless, high-resolution satellite imagery combined with novel signal extraction methods facilitates the differentiation of coconut palms (Cocos nucifera L.) from forests. Cocoa grows well under established coconut shade, and underplanting provides a viable opportunity to intensify production and meet demand and government targets. In this study, we combined grey-level co-occurrence matrix (GLCM) textural features and vegetation indices from Sentinel datasets to evaluate the sustainability of cocoa expansion given land suitability for agriculture and soil capability classes. Additionally, it sheds light on underexploited areas with agricultural potential. The mapping of areas where cocoa smallholder orchards already exist or can be grown involved three main components. Firstly, the use of the fine-resolution C-band synthetic aperture radar and multispectral instruments from Sentinel-1 and Sentinel-2 satellites, respectively. Secondly, the processing of imagery (Sentinel-1 and Sentinel-2) for feature extraction using 22 variables. Lastly, fitting a random forest (RF) model to detect and distinguish potential cocoa orchards from non-cocoa areas. The RF classification scheme differentiated cocoa (for consistency, the coconut-cocoa areas in this manuscript will be referred to as cocoa regions or orchards) and non-cocoa regions with 97 percent overall accuracy and over 90 percent producer's and user's accuracies for the cocoa regions when trained on a combination of spectral indices and GLCM textural feature sets. The top five variables that contributed the most to the model were the red band (B4), red edge curve index (RECI), blue band (B2),

关键词： cocoa detection land capability uncertainty GLCM Google Earth Engine random forest land use change sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Intelligent System for Real time detection and classification of Aerial targets using CNN

Intelligent System for Real time detection and classificatio...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Madhusudan Upadhyay Somanchi Krishna Murthy A A Bazil Raj Defence Institute of Advanced Technology Pune India

The advancements in drone technology has led to increased usage of drones in civil and military which poses significant security related challenges. The small size of drones and birds pose a significant problem for their accurate detection in real time. These aerial targets have reduced RCS and operate at low altitudes with speeds of 40-80kmph making it difficult to accurately detect and classify them. This paper focusses on the design and development of an intelligent system for the detection and classification of these aerial targets by obtaining their micro-Doppler characteristics. The work integrates the signal processing techniques of radar-based detection with neural network classifier model for real time target classification.

关键词： Training Neural networks data acquisition Process control Object detection signal processing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

small Infrared Target Detection via Iteratively-Reweighted-Nuclear-Norm

Small Infrared Target Detection via Iteratively-Reweighted-N...

引用

International Symposium on Artificial Intelligence and Robotics

作者： Gao, Haoran Ren, Jinlei He, Chunming Deng, Lizhen Nanjing Univ Posts & Tele Commun Coll Telecommun & Informat Engn Nanjing Peoples R China China Acad Launch Vehicle Technol CALT Beijing Peoples R China Wuhan Univ Technol Sch Informat Engn Wuhan Peoples R China Nanjing Univ Posts & Telecommun Bell Honor Sch Nanjing Peoples R China

ISBN: (数字)9781510639690

ISBN: (纸本)9781510639690

The process of infrared images via computer-based algorithms for better application is a frontier field integrating physical technology with computer science. One of the key techniques in infrared image processing is the detection of infrared targets. This technique is extensively applied in security and defense systems and search and tracking systems. However, due to their small size, dim light and lack of texture, the detection of infrared targets is a technical problem. One strategy to address this problem is to transform the detection work into a non-convex optimization problem of recovering a low-rank matrix (background) and a sparse matrix (target) from a patch-image matrix (original image) based on IPI (infrared patch-image) model. When targets are clear and recognizable, the APG (accelerated proximal gradient) algorithm works effectively to solve it. However, when targets become much dimmer and are screened by the intricate texture of background, the experimental detection results degrade dramatically. In order to solve this problem, a novel method via IRNN (iteratively reweighted nuclear norm) is proposed in this paper. Experimental results show that under different complicated backgrounds, targets with higher SCRG (signal-to-clutter ratio gain) values and BSF (background suppression factor) values can be acquired through IRNN algorithm compared with the APG algorithm, which means that our method performs better.

关键词： small target detection Iteratively reweighted nuclear norm infrared patch-image model

来源：评论

学校读者我要写书评

暂无评论

低信噪比下基于YOLOv3的昆虫目标检测

引用

信号处理 2022年第1期38卷 109-117页

作者：梁文哲冯阳凯王锐周超蔡炯北京理工大学信息与电子学院北京100081 上海卫星工程研究所上海200240

掌握昆虫迁飞规律对于农业防治和生态学研究具有重大意义,雷达正是检测昆虫迁飞最有效的手段。昆虫回波弱,传统的恒虚警检测(Constant False Alarm Rate,CFAR)算法在低信噪比(signal To Noise Ratio,SNR)时的检测性能下降;同时昆虫目标... 详细信息

掌握昆虫迁飞规律对于农业防治和生态学研究具有重大意义,雷达正是检测昆虫迁飞最有效的手段。昆虫回波弱,传统的恒虚警检测(Constant False Alarm Rate,CFAR)算法在低信噪比(signal To Noise Ratio,SNR)时的检测性能下降;同时昆虫目标体积小、飞行速度慢,在距离维和多普勒维的扩展性弱,特征少,在一维距离像上或者距离多普勒域基于深度学习的识别算法效果不佳。针对上述问题,本文提出了基于YOLOv3(You Only Look Once v3)网络的昆虫目标检测算法,通过短时傅里叶变换丰富目标的图像特征,利用图像特征对昆虫目标进行识别,提高了在低SNR下的检测率。进一步通过虚警-目标二元训练策略、目标检测置信度筛选策略降低了算法的虚警率。仿真和实测数据结果表明,所提算法在低SNR下的检测性能优于CA-CFAR算法,验证了算法的有效性。

关键词：昆虫目标检测低信噪比深度学习

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：