检索结果-内蒙古大学图书馆

Signal processing of pyroelectric infrared sensor for classification of multiple moving human targets

International Journal of Information and Communication technology 2017年第4期10卷 419-436页

作者： Zhao, Ning Li, Fangmin Liu, Xuedong Li, Yanyan Key Laboratory of Fiber Optic Sensing Technology and Information Processing School of Information and Engineering Wuhan University of Technology China School of Logistics Engineering Wuhan University of Technology China

Nowadays, with the features of low energy consumption and flexible networking, the pyroelectric sensor has been applied widely in areas such as network instruction detection or human body target tracking recognition. However, due to the deficiency of prominent biological morphological characteristics, such as fingerprint, iris or facial features, in the human target signals captured by pyroelectric sensor networks node, the precise classification and identification of multi-human targets in pyroelectric sensor networks become very difficult. In this paper, we apply the wavelet packet to multi-resolution to decompose the signals of pyroelectric infrared sensors and extract the energy variation of reconstructed signals to compose feature vectors to represent various characteristics of different moving human targets. Then, we generate a classifier using those feature vectors. Through some simulation experiments, it proves that this method not only can better extract the characteristics of human targets that are in detection zone of pyroelectric infrared sensor, but also an ideal classification and recognition result can be obtained of multiple human targets by training the support vector machine classifier with proper kernel function and parameters. Copyright © 2017 Inderscience Enterprises Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

AN ADAPTATION OF CNN FOR SMALL target detection IN THE infrared

AN ADAPTATION OF CNN FOR SMALL TARGET DETECTION IN THE INFRA...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Dong Zhao Huixin Zhou Shenghui Rong Xiuping Jia School of Physics and Optoelectronic Engineering Xidian University Xi'an China School of Engineering and Information Technology University of New South Wales Canberra NSW Australia

Due to the low signal to noise ratio and limited spatial resolution, small target detection in an infrared image is a challenging task. Existing methods often have high false alarm rates and low probabilities of detection when infrared small targets submerge in the background clutter. In this paper, the Convolutional Neural Network (CNN) is adapted to extract the hidden features of small targets from infrared imagery with a proposed technique for a large amount of training data generation. The Point Spread Function (PSF) is employed to model the small target data and generate positive samples. The random background image patches are selected as the negative samples. In this way, the detection problem is skillfully converted into a problem of pattern classification using CNN. Extensive synthetic and real small targets were tested to evaluate the performance of this novel small target detection framework. The experimental results indicate that the proposed algorithm is simple and effective with satisfactory detection accuracy.

关键词： Object detection Feature extraction Training Clutter Learning systems classification algorithms Transforms

来源：评论

学校读者我要写书评

暂无评论

基于最优可免域神经免疫网络的深度模糊红外目标提取算法

引用

红外 2019年第1期40卷 16-23页

作者：于晓周子杰高强天津理工大学电气电子工程学院复杂系统控制理论与应用重点实验室天津300384

深度模糊是模糊红外图像的一类表现特征,准确提取红外图像的深度模糊区域是提取模糊红外目标的基础。基于生物免疫系统在抗原检测、提取和消除上表现出识别、学习、记忆、耐受和协调配合等优异特性,结合生物免疫中神经系统与免疫系统相... 详细信息

深度模糊是模糊红外图像的一类表现特征,准确提取红外图像的深度模糊区域是提取模糊红外目标的基础。基于生物免疫系统在抗原检测、提取和消除上表现出识别、学习、记忆、耐受和协调配合等优异特性,结合生物免疫中神经系统与免疫系统相互作用的关系,提出了一种基于最优可免域神经免疫网络的深度模糊红外目标提取算法。该算法通过设计神经网络能给进行模糊红外图像目标与背景分类的免疫网络以指导作用。依靠独立于免疫系统神经网络先验知识的作用,设计了最优可免域神经免疫网络,实现了针对深度模糊红外目标的准确提取。实验结果证明,相对于其他传统目标提取算法,该算法能更有效和更准确地提取模糊红外目标图像中的目标。

关键词：目标提取可免域深度模糊红外图像

来源：评论

学校读者我要写书评

暂无评论

Automatic target recognition and detection in infrared imagery under cluttered background 3

Automatic target recognition and detection in infrared image...

引用

Congress on target and Background Signatures III

作者： Gundogdu, Erhan Koc, Aykut Alatan, A. Aydin ASELSAN Res Ctr Intelligent Data Analyt Res Prog Dept Ankara Turkey Middle East Tech Univ Elect & Elect Engn Dept Ankara Turkey Middle East Tech Univ Ctr Image Anal OGAM Ankara Turkey

ISBN: (纸本)9781510613294;9781510613287

Visual object classification has long been studied in visible spectrum by utilizing conventional cameras. Since the labeled images has recently increased in number, it is possible to train deep Convolutional Neural Networks (CNN) with significant amount of parameters. As the infrared (IR) sensor technology has been improved during the last two decades, labeled images extracted from IR sensors have been started to be used for object detection and recognition tasks. We address the problem of infrared object recognition and detection by exploiting 15K images from the real-field with long-wave and mid-wave IR sensors. For feature learning, a stacked denoising autoencoder is trained in this IR dataset. To recognize the objects, the trained stacked denoising autoencoder is fine-tuned according to the binary classification loss of the target object. Once the training is completed, the test samples are propagated over the network, and the probability of the test sample belonging to a class is computed. Moreover, the trained classifier is utilized in a detect-by-classification method, where the classification is performed in a set of candidate object boxes and the maximum confidence score in a particular location is accepted as the score of the detected object. To decrease the computational complexity, the detection step at every frame is avoided by running an efficient correlation filter based tracker. The detection part is performed when the tracker confidence is below a pre-defined threshold. The experiments conducted on the real field images demonstrate that the proposed detection and tracking framework presents satisfactory results for detecting tanks under cluttered background.

关键词： autoencoders neural networks infrared object recognition

来源：评论

学校读者我要写书评

暂无评论

基于红外视觉的野外搜救无人机的设计与实现

引用

传感器与微系统 2019年第1期38卷 104-106,109页

作者：邵延华张得沛楚红雨常志远展华益饶云波西南科技大学信息工程学院四川绵阳621000 西北大学电子工程和计算机系美国伊利诺斯州埃文斯顿60208 电子科技大学信息与软件工程学院四川成都610054

针对当前野外搜救效率低下、搜救效果易受环境因素(如夜间)影响等问题,设计制作了一种采用红外视觉的野外搜救无人机。搜救无人机通过机载的红外热像仪FLIR TAU2对搜救区域进行图像采集;将拍摄的红外图像传输给机载的TK1实现对红外图像... 详细信息

针对当前野外搜救效率低下、搜救效果易受环境因素(如夜间)影响等问题,设计制作了一种采用红外视觉的野外搜救无人机。搜救无人机通过机载的红外热像仪FLIR TAU2对搜救区域进行图像采集;将拍摄的红外图像传输给机载的TK1实现对红外图像中人体目标的实时检测;无人机将检测到的人体目标的地理位置发送给地面站,以便搜救人员能够及时完成救援任务。在红外人体目标检测阶段,采用方向梯度直方图(HOG)对红外目标进行特征描述,并通过线性支持向量机(SVM)分类器对HOG特征分类检测。试验结果验证了所设计的搜救无人机可以在多种真实野外场景下完成野外搜救任务。

关键词：红外视觉野外搜救方向梯度直方图支持向量机人体目标检测无人机

来源：评论

学校读者我要写书评

暂无评论

Applying self-structured data learning algorithm to aerial infrared and visual images

Applying self-structured data learning algorithm to aerial i...

引用

Cyber Sensing 2017

作者： Li, Jenfeng Sam Ternovskiy, Igor Graham, James Ilin, Roman Georgia Institute of Technology AtlantaGA30332 United States Automatic Target Recognition Center Right State Research Institute BeavercreekOH45431 United States Sensors Directorate Air Force Research Laboratory Wright Patterson AFB OH45433 United States Riverside Research BeavercreekOH45431 United States

ISBN: (纸本)9781510608719

Previously, we proposed and implemented a Self-structuring Data Learning Algorithm. This realized software package and the concept are still progressing. Earlier, it was tested with synthetic data and exhibited interesting results. The objectives of this paper are testing the algorithm with raw infrared and visual images and updating the algorithm as required. We first performed registration transformation and detection from the images with an existing software package. We then registered the detections with the registration transformations from both infrared and visual images. The registered detections were delivered to the algorithm for target detection and tracking without modification. Results revealed inability to handle very noisy infrared image features. To overcome this problem, we developed multiscale grid processing to improve detection classification in the algorithm. This updated algorithm shows much better target detection and tracking with the real-world data. More algorithm enhancements are in work such as incorporating pattern recognition, classification, and fusion. © 2017 SPIE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

典型旋翼形状参数微多普勒激光探测计算方法

引用

红外与激光工程 2018年第9期47卷 107-115页

作者：王云鹏胡以华雷武虎郭力仁国防科技大学脉冲功率激光技术国家重点实验室安徽合肥230037

为实现旋翼的遥感探测分类与识别,对基于微多普勒效应的扩展旋翼面目标激光回波特征开展研究。采用物理光学面元法构建了运动扩展旋翼的相干激光探测微多普勒回波模型,分析计算了旋翼激光角度散射特性,证明远场条件下旋翼各处回波反射... 详细信息

为实现旋翼的遥感探测分类与识别,对基于微多普勒效应的扩展旋翼面目标激光回波特征开展研究。采用物理光学面元法构建了运动扩展旋翼的相干激光探测微多普勒回波模型,分析计算了旋翼激光角度散射特性,证明远场条件下旋翼各处回波反射率一致。对三种典型形状旋翼的激光探测回波进行了仿真,通过平滑伪魏格纳维利(SPWV)变换得到了扩展旋翼的时频特征。电磁散射机理证实各频率带的产生与旋翼结构形状相关,且桨叶数量以及整体平动速度并不影响旋翼形状在时频图中的特征表达。据此提出了旋翼形状参数的激光探测求解方法,通过仿真验证了展弦比、根梢比以及桨尖后掠角三种参数算法的正确性,为后续的旋翼探测识别奠定了基础。

关键词：微多普勒效应激光探测典型旋翼形状参数时频分析

来源：评论

学校读者我要写书评

暂无评论

The Utility of Polarimetry within Passive Military Imaging Systems 14

The Utility of Polarimetry within Passive Military Imaging S...

引用

Conference on Electro-Optical and infrared Systems - technology and Applications XIV

作者： Hickman, Duncan L. Smith, Moira I. Kim, Kyung Su Choi, Hyun-Jin Tektonex Ltd Argyll Rd Kilcreggan Scotland Agcy Def Dev Sunamdong Daejeon South Korea

ISBN: (数字)9781510613317

ISBN: (纸本)9781510613317;9781510613300

An ongoing challenge for many military imaging systems is the detection and classification of weak target signatures in a cluttered environment. In such cases, the use of image contrast and relative target motion alone does not always provide a sufficient level of target discrimination to give operational confidence and it is therefore necessary to consider the use of other discriminatory scene information. Polarisation is one such source of information and this paper reports on an extensive series of polarimetric trials undertaken across the visible, NIR, SWIR, MWIR and LWIR spectral bands. Using this data, the benefits and limitations of polarisation discrimination are reviewed in the context of practical military scenarios. It is shown that polarisation signatures vary with viewing geometry and atmospheric conditions. This would lead to an unpredictable performance level if the sensor discrimination was based solely on polarisation. However, by carefully combining polarisation with other scene information, useful operational benefits can be obtained and this is illustrated through a consideration of different data fusion approaches.

关键词： Polarisation Polarimetry Spectral Processing Automatic target detection and Recognition (ATD/R) Clutter Suppression EO Sensor Performance Robustness Image and Data Fusion

来源：评论

学校读者我要写书评

暂无评论

球载雷达与红外联合探测系统研究

引用

现代雷达 2018年第5期40卷 8-12页

作者：张靖李迎旭刘婧逸南京电子技术研究所南京210039 空军试飞局哈尔滨150060

针对球载预警探测装备的应用需求，探讨了在系留气球平台实现雷达与红外联合探测系统的意义；研究了雷达与红外联合探测信息融合的处理流程，包括搜索与跟踪和联合目标分类与识别的处理流程，提供了基于点迹、航迹的搜索与跟踪融合处理... 详细信息

针对球载预警探测装备的应用需求，探讨了在系留气球平台实现雷达与红外联合探测系统的意义；研究了雷达与红外联合探测信息融合的处理流程，包括搜索与跟踪和联合目标分类与识别的处理流程，提供了基于点迹、航迹的搜索与跟踪融合处理算法；构建了外场试验系统，开展了搜索与跟踪融合处理算法的系统检验，验证了雷达与红外联合探测系统对目标探测精度和跟踪稳定性提高的有效性。试验结果表明，雷达与红外联合探测系统可提高球载预警探测系统的作战效能。

关键词：球载雷达联合探测多源信息融合雷达与红外

来源：评论

学校读者我要写书评

暂无评论

Hazardous Gas detection for FTIR-Based Hyperspectral Imaging System Using DNN and CNN 14

Hazardous Gas Detection for FTIR-Based Hyperspectral Imaging...

引用

Conference on Electro-Optical and infrared Systems - technology and Applications XIV

作者： Kim, Yong-Chan Yu, Hyeong-Geun Lee, Jae-Hoon Park, Dong-Jo Nam, Hyun-Woo Korea Adv Inst Sci & Technol Sch Elect Engn 291 Daehak Ro Daejeon South Korea Agcy Def Dev POB 35 Daejeon South Korea

ISBN: (数字)9781510613317

ISBN: (纸本)9781510613317;9781510613300

Recently, a hyperspectral imaging system (HIS) with a Fourier Transform infrared (FTIR) spectrometer has been widely used due to its strengths in detecting gaseous fumes. Even though numerous algorithms for detecting gaseous fumes have already been studied, it is still difficult to detect target gases properly because of atmospheric interference substances and unclear characteristics of low concentration gases. In this paper, we propose detection algorithms for classifying hazardous gases using a deep neural network (DNN) and a convolutional neural network (CNN). In both the DNN and CNN, spectral signal preprocessing, e.g., offset, noise, and baseline removal, are carried out. In the DNN algorithm, the preprocessed spectral signals are used as feature maps of the DNN with five layers, and it is trained by a stochastic gradient descent (SGD) algorithm (50 batch size) and dropout regularization (0.7 ratio). In the CNN algorithm, preprocessed spectral signals are trained with 1 x 3 convolution layers and 1 x 2 max-pooling layers. As a result, the proposed algorithms improve the classification accuracy rate by 1.5% over the existing support vector machine (SVM) algorithm for detecting and classifying hazardous gases.

关键词： FTIR spectrometry hazardous gas detection hyperspectral detection algorithm deep neural network convolutional neural network remote sensing

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：