检索结果-内蒙古大学图书馆

飞控与探测 2023年第2期6卷 79-86页

作者：李士刚李思佳隋钧铖宋敏敏海装驻上海地区第六军事代表室上海201109 西北工业大学无人机系统技术研究院西安710072 上海航天控制技术研究所上海201109

复杂干扰条件下的红外空中目标识别技术是空战对抗领域的热点研究课题,复杂人工干扰严重遮蔽目标,导致目标特征的连续性与显著性遭到破坏,无法全面描述识别对象的特性,造成空中目标识别准确率下降。针对此问题,提出一种基于图像混合深... 详细信息

复杂干扰条件下的红外空中目标识别技术是空战对抗领域的热点研究课题,复杂人工干扰严重遮蔽目标,导致目标特征的连续性与显著性遭到破坏,无法全面描述识别对象的特性,造成空中目标识别准确率下降。针对此问题,提出一种基于图像混合深度特征的空中目标抗干扰识别算法。首先,基于卷积神经网络进行图像深度特征的提取,将深度特征与梯度直方图(Histogram of Gradient,HOG)特征进行有效融合,构建混合深度特征。针对作战场景中的目标与干扰的对抗态势多样性,将支持向量机的二分类模型改进为三分类模型,对目标、干扰以及目标干扰粘连三种状态进行精确分类。实验结果表明:在复杂干扰环境下,基于混合深度特征的空中目标抗干扰识别算法正确率为92.29%,该算法可以有效地解决目标被干扰遮蔽、形成目标干扰粘连状态时的抗干扰识别问题。

关键词：红外图像目标识别支持向量机卷积神经网络 HOG特征

来源：评论

学校读者我要写书评

暂无评论

EEG Effective Channel Selection based on target detection

EEG Effective Channel Selection based on Target Detection

引用

Information technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Ziyan Zou Kuiying Yin Nanjing Research Institute of Electronic Technology Nanjing China

ISBN: (纸本)9781665428781

In the target detection task of brain-computer interface based on the fast sequence visual presentation (RSVP), P300 is usually used as the most effective feature to capture the target image in the rapidly presented image stream. For online rsvp experiments, the target detection speed is one of the important parameters in the application. For EEG data from whole brain channels, too many channels will bring too much redundant information, which will bring more time complexity and invalid features to the data processing. In the p300-based target detection experiment, people usually simply select the channel data of the central area of the p300 fixed brain area for target detection in the experiment, but there is no detailed analysis of the selection of different brain areas and the quantitative comparison of results. This paper selects the frontal and parietal areas, and does an interpretation experiment of infrared ship images. The experimental results of different brain areas are compared and analyzed offline. Compared with other electrode selection schemes, the EEG signals of 53 electrodes related to frontal region, parietal region and central region reached the highest classification accuracy, the accuracy is 89.38%. In addition, the test results may provide some ideas for the reduction of channels in wearable devices.

关键词： Electrodes Brain Visualization Wearable computers Object detection Streaming media Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A robot system for the autodetection and classification of apple internal quality attributes

引用

POSTHARVEST BIOLOGY AND technology 2021年 180卷 111615-111615页

作者： Zhao, Miao Peng, Yankun Li, Long China Agr Univ Coll Engn 17 Tsinghua East Rd Beijing 100083 Peoples R China

Soluble solids content (SSC) is an important index of apple internal quality. To invent a more flexible and efficient method of apple internal quality detection and classification, a robot system for the autodetection and classification of apple internal quality attributes was developed. Visible and near infrared (Vis/NIR) spectroscopy is a promising technology for the nondestructive detection of the internal quality attributes of apples. The end effector of the robot system mainly carried the Vis/NIR spectra collection module and gripping mechanism. The Vis/NIR spectrum was collected when the end effector gripped the apple. Single shot multibox detector (SSD) target detection algorithm was applied to process the images and calculate the position of the apple, which greatly reduced the low accuracy of apple identification caused by light intensity and complex backgrounds, and the speed was approximately 0.055 s per frame. In comparing different modeling results, the normalized spectral ratio (NSR) pretreatment combined with the competitive adaptive reweighted sampling algorithm (CARS) obtained the best modeling result, with Rc and Rcv values of 0.979 and 0.969 and RMSEC and RMSECV values of 0.335 % and 0.385 %, respectively. The classification accuracy of independent validation was 90.0 % with Rp and RMSEP values of 0.952 and 0.393 %. The robot system required approximately 5.200 s to complete a classification for each sample. The results showed feasibility of the robot system to detect the internal quality attributes of apples.

关键词： classification Apple Robot system Spectroscopy Internal quality Machine vision

来源：评论

学校读者我要写书评

暂无评论

TOWARDS detection of THERMAL ANOMALIES in LARGE URBAN AREAS USING SIMULATION 24

TOWARDS DETECTION of THERMAL ANOMALIES in LARGE URBAN AREAS ...

引用

2020 24th ISPRS Congress - Technical Commission II

作者： Burkard, E. Bulatov, D. Kottler, B. Fraunhofer IOSB Gutleuthausstrasse 1 Ettlingen76275 Germany Curtin University of Technology Department of Spatial Sciences GPO Box U1987 PerthWA6845 Australia

Anomaly detection in imagery has widely been studied and enhanced towards the requirements of today's available sensor data, whereas many of them require a background estimation in order to identify an anomaly or target. In this paper, we examine an analysis of simulation as background estimator for anomaly detection in thermal images of urban sceneries. We generate a surface temperature image and a sensor-like infrared image by combined image and elevation data and a thermal model suited for large scenes and fast simulation. With the simulated thermal image, we define anomalies as deviation between measurement and simulation. Pixel-wise image differencing of the measured and simulated temperatures and infrared images respectively are performed and evaluated concerning the full images as well as class-wise, including a material classification of the observed area. Our approach shows complementary results compared to RXD application on the measured infrared images. Metal roofs which appear warm in the thermal image and are not visually distinguishable from the residual image are detected. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

基于YOLOv8的遥感图像舰船目标检测算法

引用

飞控与探测 2024年第3期7卷 56-66页

作者：姜忠旭高磊关智聪辛苗阮洋上海航天控制技术研究所上海201109 中国航天科技集团有限公司红外探测技术研发中心上海201109 中国人民解放军93145部队上海200000

针对遥感图像背景复杂、舰船目标尺度变化大和方向任意等问题,提出了一种基于YOLOv8的遥感图像舰船目标检测算法。首先为了提高特征融合的效率,在特征融合模块将原有的路径聚合网络优化为渐进式特征融合网络;其次为了强化模型的多尺度... 详细信息

针对遥感图像背景复杂、舰船目标尺度变化大和方向任意等问题,提出了一种基于YOLOv8的遥感图像舰船目标检测算法。首先为了提高特征融合的效率,在特征融合模块将原有的路径聚合网络优化为渐进式特征融合网络;其次为了强化模型的多尺度检测能力,在颈部网络加入基于大卷积核分解和空间选择机制的选择性大卷积核注意力模块;然后为了提高模型的分类和定位能力,在解耦检测头的检测框回归分支添加视觉注意力模块,在目标分类分支添加坐标注意力模块;最后为了将通用目标检测算法转换为旋转目标检测算法,在检测头引入角度参数并优化损失函数,优化网络训练时的正负样本标签分配策略以提升网络训练时的效率。在公开数据集HRSC2016上的实验结果表明,所提算法以3.02×10^(6)的参数量,实现了90.55%的检测准确率,与当前其他主流旋转目标检测算法相比,在参数量和准确率上都具有先进性。

关键词：舰船检测遥感图像旋转目标检测图像处理 YOLO

来源：评论

学校读者我要写书评

暂无评论

Achieving Autonomy and SWaP Reduction in Real-Time Molecular Chemical Imaging Platforms and Applications 12

Achieving Autonomy and SWaP Reduction in Real-Time Molecular...

引用

Conference on Micro- and Nanotechnology Sensors, Systems, and Applications XII

作者： Nelson, Matthew P. Tazik, Shawna K. Treado, Patrick J. ChemImage Corp 7325 Penn AveSuite 200 Pittsburgh PA 15208 USA

ISBN: (数字)9781510635562

ISBN: (纸本)9781510635562;9781510635555

Explosive, chemical and narcotic materials, when in the wrong hands, pose an immediate threat to public health and safety. As the nature of these threats become more pervasive and lethal to innocent bystanders and unsuspecting military and law enforcement authorities, there is a growing demand for rapid and effective detection of materials in real-time with a high degree of autonomy and portability at safe distances. In an effort to address this need, ChemImage has been developing novel, adaptable, handheld, short-wave infrared (SWIR) molecular chemical imaging systems for real-time analysis of complex environments, including for detection of hazardous materials (e.g., explosives, chemical warfare agents, drugs of abuse). At the heart of this sensor is the Conformal Filter (CF), which is a liquid crystal based tunable filter (LCTF) that transmits multi-band waveforms that mimic the functionality of a discriminant vector for classification of target threats amongst background clutter. Real-time detection (>= 10 detection fps) is achieved by operating two CFs in tandem within a dual polarization (DP) system, allowing for simultaneous acquisition of the compressed hyperspectral imaging data. This paper will focus on the development, characterization and testing results of a prototype handheld DP-CF sensor. Details of the autonomous, low size, weight and power (SWaP) sensor and applications of the technology to address real-world detection challenges including High Throughput Mail Screening (HTMS) and Chemical Warfare Agent (CWA) surveying and mapping will be discussed.

关键词： hyperspectral imaging (HSI) standoff detection explosives drugs chemical warfare agents (CWAs) compressive sensing conformal filter shortwave infrared (SWIR)

来源：评论

学校读者我要写书评

暂无评论

基于混合神经网络的绝缘子污秽等级分类方法

引用

广东电力 2023年第5期36卷 89-97页

作者：魏东亮王植袁聪南方电网广东东莞供电局广东东莞523000

针对输电线路中瓷绝缘子表面污秽堆积、闪络频发的问题,基于红外成像技术和混合深度神经网络,提出瓷绝缘子表面污秽状态自动检测和智能分类方法。首先,利用红外热像仪,对输电线路上多个瓷绝缘子进行成像,获得不同污秽等级的红外图像;其... 详细信息

针对输电线路中瓷绝缘子表面污秽堆积、闪络频发的问题,基于红外成像技术和混合深度神经网络,提出瓷绝缘子表面污秽状态自动检测和智能分类方法。首先,利用红外热像仪,对输电线路上多个瓷绝缘子进行成像,获得不同污秽等级的红外图像;其次,通过掩模区域卷积神经网络(Mask R-CNN)对瓷绝缘子红外图像进行目标分割和提取,以抑制背景干扰;最后,结合卷积神经网络(convolutional neural network,CNN)和双向长短期记忆(bi-directional long short-term memory,BiLSTM)网络,构建用于瓷绝缘子红外图像自动分类的混合深度神经网络,从而评估绝缘子的污秽严重性。性能对比实验证明所提方法取得了更精确的分类效果,准确度达到98.86%,特异度达到99.72%,精度达到98.86%,F1分数达到98.86%,为瓷绝缘子表面污秽等级分类、危险性评估提供了智能化技术手段。

关键词：瓷绝缘子污秽等级分类红外图像混合深度神经网络

来源：评论

学校读者我要写书评

暂无评论

A new adaptive algorithm for target detection in hyperspectral images

引用

infrared PHYSICS & technology 2019年第0期99卷 222-230页

作者： Bakhshi, Gholamreza Shahtalebi, Kamal Momeni, Mehdi Univ Isfahan Dept Elect Engn Hezar Jerib Ave Esfahan 81744 Iran Univ Isfahan Dept Geomat Engn Hezar Jerib Ave Esfahan 81744 Iran

In this paper, a novel adaptive algorithm for target detection in hyperspectral images (HSIs) is proposed. In a general classification, the proposed method belongs to the category of those methods which are not based on the statistical moments of the observed HSI (e.g. correlation or covariance matrix). The main processing burden of the proposed method is over a known set of spectral signatures. Assuming a linear spectral mixing model, the proposed method takes a set of spectral signatures which one of them relates to the target material and the others relate to the background materials. Based on an adaptive approach, the normalized least mean square (NLMS) adaptive algorithm is engaged to estimate a weight vector which is almost orthogonal to the background materials spectral signature whereas it makes an absolutely non-orthogonal pair with the target material spectral signature. The estimated weight vector is multiplied by the observed HSI to make the final decision. One synthetic and two real hyperspectral images are considered to evaluate the performance of the proposed method. The evaluation results show that the proposed method outperforms its counterparts.

关键词： Hyperspectral images Linear spectral mixing model target detection Adaptive algorithms NLMS algorithm

来源：评论

学校读者我要写书评

暂无评论

基于激光雷达与红外图像融合的车辆目标识别算法

引用

激光与红外 2021年第9期51卷 1238-1242页

作者：战荫泽张立东秦颖长春理工大学光电信息学院吉林长春130000

为了提高车辆目标在不同测试条件下的识别效率,降低系统的漏检率和误检率,提出了一种基于激光雷达与红外图像融合的车辆目标识别算法。该算法利用目标原点矩参量表征目标的红外特征,用匹配相似度表征目标的点云特征,再经过轴系对齐和尺... 详细信息

为了提高车辆目标在不同测试条件下的识别效率,降低系统的漏检率和误检率,提出了一种基于激光雷达与红外图像融合的车辆目标识别算法。该算法利用目标原点矩参量表征目标的红外特征,用匹配相似度表征目标的点云特征,再经过轴系对齐和尺度变换实现图像融合。实验采用激光雷达与红外同轴光路获取的两类数据进行图像融合,再利用目标匹配阈值进行迭代筛选,最终识别车辆目标。对比了1帧、20帧和40帧图像中具有不同属性的车辆目标识别效果,结果显示,本算法输出的目标识别区域正确适当。在1000帧图像的多种测试条件的实验中,本算法的漏检率均小于10.0%,误检率均小于5.0%,明显优于传统的距离向数据分类法和光谱分类法,验证了其具有较好的鲁棒性。

关键词：目标识别图像融合红外特征提取点云匹配

来源：评论

学校读者我要写书评

暂无评论

The infrared moving target extraction and fast video reconstruction algorithm

引用

infrared PHYSICS & technology 2019年 97卷 85-92页

作者： Qiu, Shi Tang, Ying Du, Yun Yang, Song Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Shaanxi Peoples R China Chengdu Univ Technol Coll Informat Sci & Technol Chengdu Sichuan Peoples R China Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian Shaanxi Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Minist Sci & Technol High Technol Res & Dev Ctr Beijing Peoples R China

Due to the problems of targets submerged to the background, which could easily produce ghosts, and hard complete extraction of dim targets in the surveillance video, we propose the moving target extraction and fast video reconstruction algorithm in accord with visual principle. The sample selection strategy of VIBE algorithm is improved to alleviate the errors of pixel classification. The infrared imaging features are fused to suppress the artifact. A regional growth mechanism is established to extract and store moving targets and pure background regions, and according to the characteristics of video surveillance, it is the first to establish the mapping mechanism of target, background and video to propose the fast video reconstruction algorithm. The experiment shows that the algorithm can extract the moving target completely, establish the pure background in a variety of complex conditions, and greatly reduce the storage room of the surveillance video.

关键词： infrared image Moving target extraction Background reconstruction VIBE

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：