检索结果-南通市图书馆

数字图像识别在混合油类三维荧光光谱分析中的应用

在线全文

学校读者我要写书评

暂无评论

光谱学与光谱分析 2019年第11期39卷 3407-3413页

作者：孔德明崔耀耀孔令富王书涛史慧超燕山大学电气工程学院河北秦皇岛066004 燕山大学信息科学与工程学院河北秦皇岛066004 北京化工大学信息科学与技术学院北京100029 Department of Telecommunications and Information processing Ghent UniversityB-9000GhentBelgium

海上溢油已成为全球环境污染的重要问题之一,溢油严重破坏了海洋生态的平衡,并导致人类健康受到危害。因此,研究高效的溢油检测方法对保护海洋生态环境具有重要意义。三维荧光光谱技术因能获得溢油的“指纹”图谱而成为溢油鉴别领域的... 详细信息

海上溢油已成为全球环境污染的重要问题之一,溢油严重破坏了海洋生态的平衡,并导致人类健康受到危害。因此,研究高效的溢油检测方法对保护海洋生态环境具有重要意义。三维荧光光谱技术因能获得溢油的“指纹”图谱而成为溢油鉴别领域的有效分析手段,其与平行因子分析算法相结合获得了良好的溢油鉴别效果。但平行因子算法在使用过程中需要确定不同石油产品本身所适用的浓度范围,且其对预估计组分数敏感,组分数选择是否准确直接影响最终定性定量结果,这些问题都会对油类检测造成使用上的限制。油类组分极为复杂,其中各组分间不存在统一的线性浓度范围,其相互之间还受到荧光猝灭效应的影响。直接对未经稀释的油类样本进行光谱数据采集,所获得的三维荧光光谱会因样本中组分的种类及其含量不同而存在较大差异,导致对三维荧光光谱数据进行解析的平行因子分析算法不再适用。但组分的种类及含量相近的油样其光谱特征相似度较高,并且随着特定组分及其含量的改变,其光谱形状的变化规律也较为明显。基于此,将三维荧光光谱和数字图像识别相结合,提出一种针对混合油类样本的辨识方法。首先,利用五种矿物油(汽油、柴油、航空煤油、机油和润滑油)配制三类混合油样本,其中每类混合油是用其中两种不同矿物油以不同体积比直接混合配制而成;然后利用FS920荧光光谱仪获取样本的三维荧光光谱数据,并对该数据进行求导及灰度化预处理,进而得到三维荧光导数光谱灰度图;其次提取样本三维荧光导数光谱灰度图的颜色、纹理和形状等数字图像特征;最后,通过Fisher判别分析建立样本的分类模型,采用逐步回归建立混合油样本各组分相对体积的定量模型。分类模型对三类混合油样本的分类及识别效果良好。所建立的定量模型的线性相关性R大于0.99,显著性检验p值小于0.05。研究结果表明,三维荧光光谱的数字图像特征可以被本文所述方法有效提取并用于对油类样本的定性定量分析。该研究为海面溢油检测提供了一种简单、可靠的识别方法。

关键词：溢油检测三维荧光光谱数字图像识别 Fisher判别逐步回归

Laser tracking leader-follower automatic cooperative navigation system for UAVs

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2022年第2期15卷 165-176页

作者： Rui Ming Zhiyan Zhou Zichen Lyu Xiwen Luo Le Zi Cancan Song Yu Zang Wei Liu Rui Jiang College of Engineering South China Agricultural University/Guangdong Laboratory for Lingnan Modern AgricultureGuangzhou 510642China College of Computer and Control Engineering Minjiang University/Fujian Provincial Key Laboratory of Information Processing and Intelligent ControlFuzhou 350108China Guangdong Provincial Key Laboratory for Agricultural Artificial Intelligence(GDKL-AAI) Guangzhou 510642China Guangdong Engineering Research Center for Agricultural Aviation Application(ERCAAA) Guangzhou 510642China Key Laboratory of Key Technology on Agricultural Machine and Equipment South China Agricultural UniversityMinistry of Education of P.R.ChinaGuangzhou 510642China

Currently,small payload and short endurance are the main problems of a single UAV in agricultural applications,especially in large-scale *** is one of the important methods to solve the above problems of UAVs by improving operation efficiency through multi-UAV cooperative *** study proposed a laser tracking leader-follower automatic cooperative navigation system for *** leader in the cluster fires a laser beam to irradiate the follower,and the follower performs a visual tracking flight according to the light spot at the relative position of the laser tracking *** on the existing kernel correlation filter(KCF)tracking algorithm,an improved KCF real-time spot tracking method was *** with the traditional KCF tracking algorithm,the recognition and tracking rate of the optimized algorithm was increased from 70%to 95%in indoor environment,and was increased from 20%to 90%in outdoor *** navigation control method was studied from two aspects:the distance coordinate transformation model based on micro-gyroscope and navigation control *** error of spot position was reduced from the maximum(3.12,−3.66)cm to(0.14,0.12)cm by correcting the deviation distance of the spot at different angles through a coordinate correction *** image coordinate conversion model was established for a complementary metal-oxide-semiconductor(CMOS)camera and laser receiving device at different mounting *** laser receiving device was divided into four regions,S0-S3,and the speed of the four regions is calculated using an uncontrollable discrete Kalman *** outdoor flight experiments of two UAVs were carried out outdoors using this *** experiment results show that the average flight error of the two UAVs on the X-axis is 5.2 cm,and the coefficient of variation is *** average flight error on the Z-axis is 7.3 cm,and the coefficient of variation is *** study demonstrated the possibility

关键词： two-UAVs cooperative visual navigation laser tracking

Method for pests detecting in stored grain based on spectral residual saliency edge detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Grain & Oil Science and Technology 2019年第2期2卷 33-38页

作者： Yao Qin Yanli Wu Qifu Wang Suping Yu College of Information Science and Engineering Henan University of TechnologyZhengzhou 450001China Key Laboratory of Grain Information processing and Control Henan University of TechnologyMinistry of EducationZhengzhou 450001China Henan Academy of Science Applied Physics Institute Co.LtdZhengzhou 450001China Luoyang inst.tute of Science and Technology Department of Computer and Information EngineeringLuoyang 471000China

Pests detecting is an important research subject in grain storage *** the past decades,many edge detection methods have been applied to the edge detection of stored grain *** some of them can realize the stored grain pests detecting,precision and robustness are not good *** residual(SR)saliency edge detection defines the logarithmic spectrumof image as novelty part of the image *** remaining spectrumis converted to the airspace to obtain edge detection *** algorithm is completely based on frequency domain *** not only can effectively simplify the target detection algorithm,but also can improve the effectiveness of target *** experimental results show that the edge results of stored grain pests detected by SR method are effective and stable.

关键词： Stored grain pests Saliency detection Spectral residual (SR) Edge detection

Mineral 4/recognition 4： A Universal Optical image Analysis Package for Iron Ore, Sinter and Coke Characterization

在线全文

学校读者我要写书评

暂无评论

Journal of Energy and Power Engineering 2017年第1期11卷 16-30页

作者： Eugene Donskoi Andrei Poliakov Keith Vining Sarath Hapugoda Project Leader Mineral Processing Modelling CSIRO Mineral Resources PO Box 883 Kenmore QLD 4069 Australia Senior Experimental Scientist CSIRO Mineral Resources PO Box 883 Kenmore QLD 4069 Australia Group Leader - Carbon Steel Futures CSIRO Mineral Resources PO Box 883 Kenmore QLD 4069 Australia Process Mineralogist CSIRO Mineral Resources PO Box 883 Kenmore QLD 4069 Australia

OIA （optical image analysis） has traditionally been used for reliable identification of different iron oxides and oxyhydroxides in iron ore. The automated CSIRO OIA system Mineral 4/recognition 4 was created for rapid mineral and textural charaeterisation of iron ore providing identification of different minerals and different morphologies. The technique has further been applied to processed iron ore products such as iron ore sinter to determine key parameters such as porosity, different morphologies of hematite （primary and secondary）, and different morphologies of SFCA （silicon ferrite of calcium and alumininm）. Application of textural identification has recently been extended to coke characterisation where the software gives comprehensive characterisation of porosity, IMDC （inert material derived components）, RMDC （reactive material derived components） and the boundaries between IMDC and RMDC. The software also has many unique features needed for iron ore research including characterisation of large objects like pellets and ore lumps; automated gangue （including quartz） identification; automated particle separation; multiple image set processing and on-line measurements. All these features make the Mineral 4/recognition 4OIA system a unique, reliable, industry/research focused tool for ore, sinter, pellet and coke characterisation.

关键词： image analysis automated characterisation iron ore sinter coke.

Improving the accuracy of image-based forest fire recognition and spatial positioning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2010年第S1期53卷 184-190页

作者： JIANG LiLi 1,QI QingWen 1,ZHANG An 1,GUO ChaoHui 2 & CHENG Xi 1,3 1 inst.tute of Geographical Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China 2 China Center for Resources Satellite Data and Applications,Beijing 100094,China 3Graduate University of Chinese Academy of Sciences,Beijing 100049,China Chinese Acad Sci Inst Geog Sci & Nat Resources Res Beijing 100101 Peoples R China China Ctr Resources Satellite Data & Applicat Beijing 100094 Peoples R China Chinese Acad Sci Grad Univ Beijing 100049 Peoples R China

Forest fires are frequent natural *** is necessary to explore advanced means to monitor,recognize and locate forest fires so as to establish a scientific system for the early detection,real-time positioning and quick fighting of forest *** paper mainly expounds methods and algorithms for improving accuracy and removing uncertainty in image-based forest fire recognition and spatial ***,we discuss a method of forest fire recognition in visible-light *** are four aspects to improve accuracy and remove uncertainty in fire recognition:(1)eliminating factors of interference such as road and sky with high brightness,red leaves,other colored objects and objects that are lit up at night,(2)excluding imaging for specific periods and azimuth angles for which interference phenomena repeatedly occur,(3)improving the thresholding method for determining the flame border in image processing by adjusting the threshold to the season,weather and region,and (4)integrating the visible-light image method with infrared image ***,we examine infrared-image-based methods and approaches of improving the accuracy of forest fire recognition by combining the spectrum threshold with an object feature value such as the normalized difference vegetation index and excluding factors of disturbance such as interference signals,extreme weather and high-temperature ***,a method of visible analysis to enhance the accuracy of forest fire positioning is examined and realized;the method includes decreasing the visual angle,selecting central points,selecting the largest spots,and judging the selection of fire spots according to the central *** studies are examined and the results are found to be satisfactory.

关键词： forest fire monitoring spatial positioning accuracy improvement

A Local Binary pattern-Based Method for Color and Multicomponent Texture Analysis

在线全文

学校读者我要写书评

暂无评论

Journal of Signal and Information processing 2020年第3期11卷 58-73页

作者： Yao Taky Alvarez Kossonou Alain Clément Bouchta Sahraoui Jérémie Zoueu Laboratoire d’inst.umentation Image et Spectroscopie (L2IS) Institut National Polytechnique-Felix Houphou&eumlt Boigny Yamoussoukro C&ocircte d’Ivoire Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS) Université d’Angers Institut Universitaire de Technologie 4 Bd Lavoisier Angers Cedex France inst.tut des Sciences et Technologies Moléculaires d’Angers (MOLTECH ANJOU) UMR CNRS 6200 Université d’Angers 2 Bd Lavoisier Angers Cedex 2 France

Local Binary patterns (LBPs) have been highly used in texture classification for their robustness, their ease of implementation and their low computational cost. Initially designed to deal with gray level images, several methods based on them in the literature have been proposed for images having more than one spectral band. To achieve it, whether assumption using color information or combining spectral band two by two was done. Those methods use micro structures as texture features. In this paper, our goal was to design texture features which are relevant to color and multicomponent texture analysis without any assumption. Based on methods designed for gray scale images, we find the combination of micro and macro structures efficient for multispectral texture analysis. The experimentations were carried out on color images from Outex databases and multicomponent images from red blood cells captured using a multispectral microscope equipped with 13 LEDs ranging from 375 nm to 940 nm. In all achieved experimentations, our proposal presents the best classification scores compared to common multicomponent LBP methods. 99.81%, 100.00%, 99.07% and 97.67% are maximum scores obtained with our strategy respective

关键词： Multispectral images Local Binary patterns (LBP) Texture Analysis Rotation Invariance Illumination Variation Blurring Invariance

Unsupervised Style Control for image Captioning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

国际计算机前沿大会会议论文集 2022年第1期 413-424页

作者： Junyu Tian Zhikun Yang Shumin Shi School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Beijing Engineering Research Center of High Volume Language Information processing and Cloud Computing Applications BeijingChina

We propose a novel unsupervised image captioning *** captioning involves two fields of deep learning,natural language processing and computer *** excessive pursuit ofmodel evaluation results makes the caption style generated by the model too monotonous,which is difficult to meet people’s demands for vivid and stylized image ***,we propose an image captioning model that combines text style transfer and image emotion recognition methods,with which the model can better understand images and generate controllable stylized *** proposed method can automatically judge the emotion contained in the image through the image emotion recognition module,better understand the image content,and control the description through the text style transfermethod,thereby generating captions thatmeet people’s *** our knowledge,this is the first work to use both image emotion recognition and text style control.

关键词： image caption image sentiment recognization Text style transfer

Fuzzy Logic in Classification of Radio Communication Signals

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

通讯和计算机（中英文版） 2013年第2期10卷 207-213页

作者： Zuzana Didekova Beata Mikovicova inst.tute of Control and Industrial Informatics Faculty of Electrical Engineering and Information Technology Slovak Universityof Technology (FEI STU) in Bratislava Bratislava 81219 SlovaMa Laboratory of Computer Science Signal and lmage Processing Electronics and Telecommunications Institute SuperiorElectronic of Paris (ISEP) Paris 75006 France.

Characterization of radio communication signals aims at automatic recognition of different characteristics of radio signals in order to detect their modulation type, the central frequency, and the level. The authors" purpose is to apply techniques used in image processing in order to extract pertinent characteristics. To the single analysis (recognition of membership of certain frequency signal to a radio communication using its characteristics), the authors add several rules for checking the consistency of hypotheses using fuzzy logic. This allows taking into account ambiguity and uncertainty that may remain after the extraction of individual characteristics. The task has been realized in MATLAB. The aim is to improve the process of radio communications characterization.

关键词：通信信号模糊逻辑无线电分类 MATLAB 中心频率信号特征无线通信