检索结果-内蒙古大学图书馆

ES4LUCC: A GIS-tool for remotely monitoring landscape dynamics

COMPUTERS & GEOSCIENCES 2012年 49卷 72-80页

作者： Forzieri, Giovanni Battistini, Alessandro Catani, Filippo Commiss European Communities Joint Res Ctr Climate Risk Management Unit Inst Environm & Sustainabil I-21027 Ispra VA Italy Univ Florence Dept Earth Sci Florence Italy

Given the potential impacts of land cover changes on surface processes, accurate mapping of landscape dynamics is a crucial task in environmental monitoring. The use of commercial software for remote sensing of landscape changes requires appropriate expertise in sensor technology and computing resources that are not always available to decision makers. This paper presents the development of an experimental prototype of a lightweight and user-friendly GIS tool - ES4LUCC - a semiautomatic software for change detection and classification of land use/cover. The tool is based on image processing techniques applied on multi-temporal remotely sensed spectral and surface model data. The GIS-based tiling approach allows to non-specialists of remote sensing to manage high-dimensional data even from low performance computing platforms. The paper synthesizes the implemented digital image processing that form the basis of ES4LUCC, including data correction, classification and change detection, map refinements. It also describes the software architecture, the main IDL modules and the integration with GIS through a tight coupling approach *** calling functions. The main modelling process is controlled through a powerful GUI developed as part of the ArcMap component of ESRI ArcGIS. The software is tested by using bi-temporal color-infrared ADS40 and Light detection and ranging data acquired on a 80-km transect of the Marecchia river (Italy). The outputs of ES4LUCC give an understanding of the natural- and human-induced surface processes, such as urban planning, agricultural and forest practices, fluvial dynamics and slope instability. The model provides reliable maps (90.77% overall classification accuracy) that represent useful layers for environmental landscape management. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Environmental monitoring classification Change detection Remote sensing ENVI IDL ArcGIS

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of digital airborne multispectral camera system

Design and Implementation of digital airborne multispectral ...

引用

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

作者： Lin, Zhaorong Zhang, Xuguo Wang, Li Pan, Deai Beijing Inst Space Mech & Elect Beijing 10076 Peoples R China

ISBN: (纸本)9780819492821

The multispectral imaging equipment is a kind of new generation remote sensor, which can obtain the target image and the spectra information simultaneously. A digital airborne multispectral camera system using discrete filter method had been designed and implemented for unmanned aerial vehicle (UAV) and manned aircraft platforms. The digital airborne multispectral camera system has the advantages of larger frame, higher resolution, panchromatic and multispectral imaging. It also has great potential applications in the fields of environmental and agricultural monitoring and target detection and discrimination. In order to enhance the measurement precision and accuracy of position and orientation, Inertial Measurement Unit (IMU) is integrated in the digital airborne multispectral camera. Meanwhile, the Temperature Control Unit (TCU) guarantees that the camera can operate in the normal state in different altitudes to avoid the window fogging and frosting which will degrade the imaging quality greatly. Finally, Flying experiments were conducted to demonstrate the functionality and performance of the digital airborne multispectral camera. The resolution capability, positioning accuracy and classification and recognition ability were validated.

关键词： Multispectral remote sensing spectral division target classification image fusion

来源：评论

学校读者我要写书评

暂无评论

基于级联分类器的红外弱小目标快速检测

引用

高技术通讯 2012年第7期22卷 772-777页

作者：许庆晗金立左费树岷东南大学自动化学院南京210096

为克服弱小目标检测在大尺寸图像上存在时间开销大的问题，提出了一种多级处理的检测算法。首先在整幅图像上搜索局部灰度极值作为候选目标位置，随后对候选目标位置的邻域进行特征提取，最后在特征空间中进行分类。针对小目标特性，提... 详细信息

为克服弱小目标检测在大尺寸图像上存在时间开销大的问题，提出了一种多级处理的检测算法。首先在整幅图像上搜索局部灰度极值作为候选目标位置，随后对候选目标位置的邻域进行特征提取，最后在特征空间中进行分类。针对小目标特性，提出了一种灰度分布特征，以此特征对候选目标位置进行特征提取，进而提出了一种加权逻辑斯蒂回归算法，用其在特征空间建立分类器，将检测问题转化为二分类问题。实验结果表明，该算法对低信噪比图像可以达到较高的检测率和较低的虚警率，并具有较好的实时性。

关键词：红外小目标检测灰度分布特征加权逻辑斯蒂回归

来源：评论

学校读者我要写书评

暂无评论

A feature selection strategy for the analysis of spectra from a photoacoustic sensing system

A feature selection strategy for the analysis of spectra fro...

引用

Conference on Optical Materials and Biomaterials in Security and Defence Systems technology IX

作者： Ulrici, Alessandro Seeber, Renato Calderisi, Marco Foca, Giorgia Uotila, Juho Carras, Mathieu Fiorello, Anna Maria Univ Modena & Reggio Emilia Dipartimento Sci Vita Via Amendola 2 I-42122 Reggio Emilia Italy Consorzio INSTM I-50121 Florence Italy Univ Modena & Reggio Emilia Dipartimento Scienze Chimiche Geologiche I-41125 Modena Italy Gasera Ltd FI-20520 Turku Finland EIII Lab Palaiseau France Selex SI I-00131 Rome Italy

ISBN: (纸本)9780819492869

In the frame of the EU project CUSTOM, a new sensor system for the detection of drug precursors in gaseous samples is being developed, which also includes an External Cavity-Quantum Cascade Laser Photo Acoustic Sensor (EC-QCLPAS). In order to define the characteristics of the laser source, the optimal wavenumbers within the most effective 200 cm(-1) range in the mid-infrared region must be identified, in order to lead to optimal detection of the drug precursor molecules in presence of interfering species and of variable composition of the surrounding atmosphere. To this aim, based on simulations made with FT-IR spectra taken from literature, a complex multivariate analysis strategy has been developed to select the optimal wavenumbers. Firstly, the synergistic use of Experimental Design and of Signal Processing techniques led to a dataset of 5000 simulated spectra of mixtures of 33 different gases (including the 4 target molecules). After a preselection, devoted to disregard noisy regions due to small interfering molecules, the simulated mixtures were then used to select the optimal wavenumber range, by maximizing the classification efficiency, as estimated by Partial Least Squares - Discriminant Analysis. A moving window 200 cm(-1) wide was used for this purpose. Finally, the optimal wavenumber values were identified within the selected range, using a feature selection approach based on Genetic Algorithms and on resampling. The work made will be relatively easily turned to the spectra actually recorded with the newly developed EC-QCLPAS instrument. Furthermore, the proposed approach allows progressive adaptation of the spectral dataset to real situations, even accounting for specific, different environments.

关键词： Signal Processing Feature Selection classification Wavelet Transform Genetic Algorithms mid-infrared spectra drug precursors

来源：评论

学校读者我要写书评

暂无评论

Robust multi-stage approach for the detection of moving target from infrared imagery

引用

OPTICAL ENGINEERING 2012年第6期51卷 067006-067006页

作者： Chen, Bingwen Wang, Wenwei Qin, Qianqing Wuhan Univ Sch Elect Informat Wuhan 430079 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

We present a multi-stage classification approach to detect targets in widely varying thermal imagery. A multi-level spatial-temporal median filter is utilized to extract the background frame, with which the background clutters are suppressed by using the principal component analysis technique. A spatially related fuzzy adaptive resonance theory (ART) neural network is then applied to identify the local regions-of-interest. Within each region, another fuzzy ART neural network is utilized to detect the targets. Experimental results demonstrate that the proposed approach is capable of detecting infrared moving targets effectively for F1 measurement up to 96.3%. (c) 2012 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/***.51.6.067006]

关键词： multi-stage classification multi-level spatial-temporal median filter spatially related fuzzy adaptive resonance theory neural network principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Unmanned ground vehicle perception using thermal infrared cameras

Unmanned ground vehicle perception using thermal infrared ca...

引用

Conference on Unmanned Systems technology XIII

作者： Rankin, Arturo Huertas, Andres Matthies, Larry Bajracharya, Max Assad, Christopher Brennan, Shane Bellutta, Paolo Sherwin, Gary W. CALTECH Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA Gen Dynam Robot Syst Pittsburgh PA 15221 USA

ISBN: (纸本)9780819486196

The ability to perform off-road autonomous navigation at any time of day or night is a requirement for some unmanned ground vehicle (UGV) programs. Because there are times when it is desirable for military UGVs to operate without emitting strong, detectable electromagnetic signals, a passive only terrain perception mode of operation is also often a requirement. Thermal infrared (TIR) cameras can be used to provide day and night passive terrain perception. TIR cameras have a detector sensitive to either mid-wave infrared (MWIR) radiation (3-5 mu m) or long-wave infrared (LWIR) radiation (7-14 mu m). With the recent emergence of high-quality uncooled LWIR cameras, TIR cameras have become viable passive perception options for some UGV programs. The Jet Propulsion Laboratory (JPL) has used a stereo pair of TIR cameras under several UGV programs to perform stereo ranging, terrain mapping, tree-trunk detection, pedestrian detection, negative obstacle detection, and water detection based on object reflections. In addition, we have evaluated stereo range data at a variety of UGV speeds, evaluated dual-band TIR classification of soil, vegetation, and rock terrain types, analyzed 24 hour water and 12 hour mud TIR imagery, and analyzed TIR imagery for hazard detection through smoke. Since TIR cameras do not currently provide the resolution available from megapixel color cameras, a UGV's daytime safe speed is often reduced when using TIR instead of color cameras. In this paper, we summarize the UGV terrain perception work JPL has performed with TIR cameras over the last decade and describe a calibration target developed by General Dynamics Robotic Systems (GDRS) for TIR cameras and other sensors.

关键词： Thermal infrared MWIR LWIR stereo vision passive perception terrain classification calibration

来源：评论

学校读者我要写书评

暂无评论

红外图像中人体目标检测技术研究

引用

现代电子技术 2012年第18期35卷 111-113,118页

作者：赵君钦李林国防科学技术大学ATR实验室湖南长沙410073

针对红外序列图像中人体目标检测问题,采用了基于特征点的特征区域提取方法,先用FAST算法快速提取特征点,然后基于提取出的特征点,使用LBP算法提取特征区域,在得到感兴趣的特征区域(ROI区域)后,用对ROI区域进行基于离散小波变换的小波... 详细信息

针对红外序列图像中人体目标检测问题,采用了基于特征点的特征区域提取方法,先用FAST算法快速提取特征点,然后基于提取出的特征点,使用LBP算法提取特征区域,在得到感兴趣的特征区域(ROI区域)后,用对ROI区域进行基于离散小波变换的小波熵特征提取,并采用复合分类方法对ROI区域进行分类,利用此方法有效地将人体目标从红外序列图像中检测出来。

关键词：红外序列图像 FAST CS-LBP 离散小波变换 SVM Adaboost

来源：评论

学校读者我要写书评

暂无评论

Automated detection and Discrimination of Buried Explosive Threats Using Feature Extraction and Cost Based Probability Updating

Automated Detection and Discrimination of Buried Explosive T...

引用

作者： Minh Dao-Johnson Tran University of South Australia

学位级别：博士

Landmines and improvised explosive devices (IEDs) are a significant problem to both the military and local civilians in many countries around the world. Examples of these threats include antipersonnel and antitank mines, and unexploded ordnance (UXO) that have ei- ther been abandoned after periods of conflict, or reused as components in IEDs. A major dilemma regarding these explosive threats is they often have no means of self-neutralisation or self-destruction, and hence can remain active long after their intended period of use. The majority of the victims directly affected by landmines and IEDs are unfortunately local civil- ians. Over the years a number of different technologies have been trialled and operated to detect explosive threats such landmines and UXOs. These technologies include ground penetrat- ing and synthetic aperture radar, infrared, acoustic devices, and biological sensors such as canines, rats, and gerbils. The most successful and frequently used technology for detecting these threats in the field to date is the metal detector (MD). However a common occurrence in many areas where these explosive threats are located is the presence of benign clutter. The majority of the current commercial-off-the-shelf detection systems do not have the capabil- ity for discriminating between targets of interest and irrelevant clutter, which has become the source of a significant number of false alarms. These false alarms dictate the overall performance of all systems designed for explosive threat detection. Although more recently software based approaches have been implemented to perform the identification task, these systems are still limited and prone to high false alarm rates (FARs). A number of these sys- tems also still require a heavy reliance on human operators to perform the discrimination despite their utilisation of software tools. This thesis presents a methodology for target detection and classification. The methodol- ogy was used to implement a decisi

关键词：

来源：评论

学校读者我要写书评

暂无评论

利用特征空间主分量分解实现自适应小目标检测算法

引用

哈尔滨理工大学学报 2011年第3期16卷 62-67页

作者：孙慧孙凯侯晴宇哈尔滨理工大学电工电子教学与实训中心黑龙江哈尔滨150080 黑河学院网络信息中心黑龙江黑河164300 哈尔滨工业大学空间光学工程研究中心黑龙江哈尔滨150001

为了实现非平稳复杂背景干扰下的红外小目标检测,在特征选择阶段同时考虑了目标的强度、分布梯度以及与背景之间的阶越特性,并提取对比度、临域标准差以及多孔小波变换高频分量的模值三维特征予以描述.将目标检测过程视为特征空间中的... 详细信息

为了实现非平稳复杂背景干扰下的红外小目标检测,在特征选择阶段同时考虑了目标的强度、分布梯度以及与背景之间的阶越特性,并提取对比度、临域标准差以及多孔小波变换高频分量的模值三维特征予以描述.将目标检测过程视为特征空间中的两类分类问题,通过主分量分解获取背景的统计聚类参数,将目标像素特征向量视为背景特征聚类之外的异常点,并建立了统计距离作为检测判据.同时,以背景特征向量的多元正态统计分布为假设前提,利用各主分量偏度作为限制进行了用于小目标检测的统计距离阈值的选择,进一步提高了算法的自适应性能.实测试验证明了算法的有效性.

关键词：目标检测红外特征描述主分量分解自适应检测

来源：评论

学校读者我要写书评

暂无评论

infrared Point target detection with Fisher Linear Discriminant and Kernel Fisher Linear Discriminant

引用

JOURNAL OF infrared MILLIMETER AND TERAHERTZ WAVES 2010年第12期31卷 1491-1502页

作者： Liu, Ruiming Zhi, Hongliang Huaihai Inst Technol Sch Elect Engn Lianyungang 222005 Jiangsu Peoples R China Jiangsu Automat Res Inst Lianyungang 222006 Jiangsu Peoples R China

It is a challenging task to detect point targets from an infrared image. Recently, the pattern recognition theory has been used to detect targets. The principal component analysis (PCA) has gained success in this field. We propose a linear subspace detection method based on Fisher linear discriminant (FLD) in this paper. If we consider images are made up of target class data and background class data, the target detection problem can be translated into a two-class classification problem. The FLD as one of pattern recognition algorithms can be used to find potential targets from image background. After classification by FLD, a map function, Gaussian map function, is developed to generate detection images in which the larger target-to-background contrast is obtained. FLD is a linear detection method without taking the higher-order statistics of image data into account. To improve detection performance, we extend this detection method to its nonlinear version, kernel FLD (KFLD) detection. Because the nonlinear subspace is capable of capturing the part of higher-order statistics, the better detection performance can be achieved. The well-devised experiments verify that KFLD detection outperforms FLD and other common used detection methods.

关键词： target detection infrared image PCA FLD Kernel method

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：