检索结果-内蒙古大学图书馆

detection of Magnesite and Associated Gangue Minerals using Hyperspectral Remote Sensing-A Laboratory Approach

REMOTE SENSING 2020年第8期12卷 1325-1325页

作者： Chung, Baru Yu, Jaehyung Wang, Lei Kim, Nam Hoon Lee, Bum Han Koh, Sangmo Lee, Sangin Chungnam Natl Univ Dept Astron Space Sci & Geol Daejeon 34134 South Korea Chungnam Natl Univ Dept Geol Sci Daejeon 31134 South Korea Louisiana State Univ Dept Geog & Anthropol Baton Rouge LA 70803 USA Korea Inst Geosci & Mineral Resources Convergence Res Ctr Dev Mineral Resources DMR Daejeon 34132 South Korea Chungnam Natl Univ Dept Informat & Stat Daejeon 31134 South Korea

This study introduced a detection method for magnesite and associated gangue minerals, including dolomite, calcite, and talc, based on mineralogical, chemical, and hyperspectral analyses using hand samples from thirteen different source locations and Specim hyperspectral short wave infrared (SWIR) hyperspectral images. Band ratio methods and logistic regression models were developed based on the spectral bands selected by the random forest algorithm. The mineralogical analysis revealed the heterogeneity of mineral composition for naturally occurring samples, showing various carbonate and silicate minerals as accessory minerals. The Mg and Ca composition of magnesite and dolomite varied significantly, inferring the mixture of minerals. The spectral characteristics of magnesite and associated gangue minerals showed major absorption features of the target minerals mixed with the absorption features of accessory carbonate minerals and talc affected by mineral composition. The spectral characteristics of magnesite and dolomite showed a systematic shift of the Mg-OH absorption features toward a shorter wavelength with an increased Mg content. The spectral bands identified by the random forest algorithm for detecting magnesite and gangue minerals were mainly associated with spectral features manifested by Mg-OH, CO3, and OH. A two-step band ratio classification method achieved an overall accuracy of 92% and 55.2%. The classification models developed by logistic regression models showed a significantly higher accuracy of 9899.9% for training samples and 82-99.8% for validation samples. Because the samples were collected from heterogeneous sites all over the world, we believe that the results and the approach to band selection and logistic regression developed in this study can be generalized to other case studies of magnesite exploration.

关键词： magnesite gangue mineral hyperspectral random forest logistic regression natural occurrence exploration

来源：评论

学校读者我要写书评

暂无评论

基于光谱角与光谱距离的目标识别方法

引用

大气与环境光学学报 2020年第5期15卷 393-400页

作者：高冬阳龙华保吴双卿杨俊彦李大鹏陈龙江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 浙大宁波理工学院浙江宁波315100

针对红外精确制导中抗干扰的问题,开展基于光谱角和光谱距离等特征参量的目标光谱识别技术仿真和实验研究。在目标、干扰均为灰体辐射的前提条件下,对目标和干扰在不同发射率模型、不同辐射温度下的红外光谱辐射分布进行理论建模,定量... 详细信息

针对红外精确制导中抗干扰的问题,开展基于光谱角和光谱距离等特征参量的目标光谱识别技术仿真和实验研究。在目标、干扰均为灰体辐射的前提条件下,对目标和干扰在不同发射率模型、不同辐射温度下的红外光谱辐射分布进行理论建模,定量分析了目标和干扰的光谱角和光谱距离特征参量与其温度、发射率的关系,数值表征了目标和干扰的光谱差异。为验证上述光谱区分方法的有效性,实验采集并分析了目标和干扰的光谱数据。研究结果表明光谱角和光谱距离能够将两者进行有效的区分,为复杂背景下目标识别提供理论和实验基础。

关键词：光谱角光谱距离光谱识别

来源：评论

学校读者我要写书评

暂无评论

基于室内高光谱激光雷达的典型树种叶片光谱观测和分类

引用

红外与毫米波学报 2020年第3期39卷 372-380页

作者：胡佩纶陈育伟蒋长辉林起楠李伟漆建波俞琳锋邵慧黄华国北京林业大学林学院省部共建森林培育与保护教育部重点实验室北京100083 芬兰地理空间研究所遥感和摄影测量部芬兰基尔科努米202431 中国科学院光电研究院定量遥感信息技术重点实验室北京100094 安徽建筑大学电子与信息工程学院安徽合肥230601

高光谱激光雷达综合了高光谱和激光雷达特征,可为植被生理生化参数提取提供更加精确的遥感探测,但其应用潜力尚未得到充分挖掘。以北京10个典型树种的单叶为样本,开展室内高光谱激光雷达的叶片观测试验,并进行树种分类研究,为未来高光... 详细信息

高光谱激光雷达综合了高光谱和激光雷达特征,可为植被生理生化参数提取提供更加精确的遥感探测,但其应用潜力尚未得到充分挖掘。以北京10个典型树种的单叶为样本,开展室内高光谱激光雷达的叶片观测试验,并进行树种分类研究,为未来高光谱激光雷达的林业应用提供基础。首先进行可调谐高光谱激光雷达(Hyperspectral LiDAR,HSL)叶片高光谱测量,并完成与ASD地物光谱仪所测数据对比实验;其次,应用随机森林方法实现10种叶片的分类研究,其输入的特征指数为融合全部波段、部分敏感波段的光谱指数。结果表明:(a)HSL在波段650~1000 nm(71个通道)内观测的叶片高光谱和ASD光谱一致(R^2=0.9525~0.9932,RMSE=0.0587);(b)只用原始波段反射率分类精度为78.31%,其中分类贡献率最大波段的是650~750 nm,使用此波段进行分类精度为94.18%,表明利用红边波段(650~750nm)进行树种分类是十分有效的;(c)对树种敏感的波段为680 nm、685 nm、690 nm、715 nm、720 nm、725 nm、730 nm;(d)结合敏感波段光谱指数与植被指数分类精度82.65%。该研究结果表明在单叶级别,利用高光谱激光雷达能够准确地反映目标叶片的光谱特征并且能有效进行树种分类;未来将可能在野外应用中精确提取目标的生理生化参数。

关键词：高光谱激光雷达叶片分类全波形植被参数

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Exo-atmospheric infrared Objects Discrimination

Generative Adversarial Networks for Exo-atmospheric Infrared...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Dongya Wu Huanzhang Lu Huamin Tao Bendong Zhao Ming Zhao National University of Defense Technology Changsha China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

External atmospheric infrared (IR) target recognition is an important research topic of space surveillance systems. The different micromotion states of the target result in respective features in the obtained sequence of IR radiation intensities, and such differences are difficult to visually describe and difficult to extract efficiently. Due to the difficulty of spatial experiments, the target sample data is very limited. In the case of limited labeled samples, there are few methods that can effectively classify time series effectively, resulting in low classification accuracy and difficulty in meeting practical application requirements. We use generative adversarial networks(GAN) for semi-supervised learning, combining neural network classifiers with adversarial generation models for the classification of infrared grayscale time series of spatial targets. The effective classification of the target is achieved with a small number of labeled target samples. The experiment proves the effectiveness of the method and the classification effect is better than other methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the application of infrared weak and small target detection algorithm based on SVM posterior probability in weekly vision search system

Research on the application of infrared weak and small targe...

引用

Conference on Optical Sensing and Imaging Technologies and Applications / International Symposium on Optoelectronic technology and Application (OTA) / Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE)

作者： He, Zhuo Zhang, Jinsuo Chen, Xu Nan, Tianzhang Tianjin Jinhang Inst Tech Phys 58 Zhonghuan Xi Rd Tianjin 300381 Peoples R China

ISBN: (纸本)9781510623354

infrared weak and small target detection has important application value in military field, and is a hot research topic in the field of target detection. With the research and development of technology, some guiding and innovative detection algorithms are emerging, especially the advantage of machine learning algorithm. In this paper, the infrared week and small target detection is considered as the two classification problem of target and background, and an infrared week and small target detection algorithm based on multiple features SVM posterior probability is proposed and applied to the weekly vision search system. In the experiment, the SVM classification model is obtained by using 8 good segmentation characteristics as the main reference value of the identification target and background, and training the training set through a large number of target and background samples. Finally, the SVM posterior probability is selected as the output of the detection result. The simulation experiment of this algorithm and the application experiment in the transplant week search system show that the method of this method has higher target detection probability (not less than 95%), the false alarm probability is lower, and the time complexity of the algorithm is low, and the hardware resource is less, and it has a good prospect of engineering application.

关键词： SVM posteriori probabilities weekly vision search system multiple features

来源：评论

学校读者我要写书评

暂无评论

基于稀疏表示的红外空中目标分类算法（英文）

引用

红外与毫米波学报 2019年第5期38卷 578-586页

作者：金璐李范鸣刘士建王霄中国科学院上海技术物理研究所上海200083 中国科学院大学北京100049 中国科学院红外探测与成像技术重点实验室上海200083

针对红外空中目标,提出了一种基于稀疏表示的快速分类算法.该工作的技术难点表现在训练样本较少,算法需要具有旋转不变性、较高的抗噪性和实时性.针对这些难点,首先根据红外空中面目标的梯度信息和统计特性,计算出图像主方向,然后将主... 详细信息

针对红外空中目标,提出了一种基于稀疏表示的快速分类算法.该工作的技术难点表现在训练样本较少,算法需要具有旋转不变性、较高的抗噪性和实时性.针对这些难点,首先根据红外空中面目标的梯度信息和统计特性,计算出图像主方向,然后将主方向旋转至同一参考方向.接着基于稀疏表示原理,把分类问题转化为1范数最小化问题,最后用快速收敛方法得到分类结果.实验结果表明该方法能够达到98.3%的正确率,给测试图像50%的像素叠加噪声后,分类正确率仍大于80%.

关键词：红外图像空中目标旋转不变性稀疏表示分类

来源：评论

学校读者我要写书评

暂无评论

Separate estimation schemes for time-frequency overlapped micro-doppler signal in single channel infrared laser detection

引用

infrared PHYSICS & technology 2018年 94卷 134-141页

作者： Guo, Liren Hu, Yihua Xu, Shilong Dong, Xiao Li, Minle Natl Univ Def Technol Coll Elect Engn State Key Lab Pulsed Power Laser Technol Hefei 230037 Anhui Peoples R China Anhui Prov Key Lab Elect Restrict Technol Hefei 230037 Anhui Peoples R China

The micro-Doppler (MD) effect of weak vibration target is obvious in infrared laser detection. This provides the foundation for precise estimation of micro-motion parameters, and makes the target classification and recognition possible. The multi-targets or multi-scattering points existing in the detecting field will generate the single-channel multi-component (SCMC) signal in laser detection. Further, the similar micro-motion parameters will lead to the feature overlapping in time-frequency domain, which will increase the difficulty of parameter estimation. In this paper, a separate parameter estimator based on the maximum likelihood framework and singular value decomposition is proposed to deal with this mixed signal. First, an improved singular value ratio (SVR) spectrum with detailed period scanning is presented to locate the vibration frequency. The amplitude ratio information of each component is also extracted from the SVR spectrum. Then, the analytic expression of the maximum likelihood estimation (MLE) of micro-motion parameters is derived. To solve the high nonlinear\ problem in laser MD signal, a new likelihood function (LF) is designed in the derivation process. The Robustness and efficiency are both increased with this new LF. The Markov chain Monte Carlo (MCMC) sampling is employed to implement the MLE. Finally, the simulation results verifies the validity of the proposed method. The comparison with the Cramer-Rao bound shows the ability of accurate estimation of the proposed method.

关键词： Laser micro-Doppler Parameter estimation Maximum likelihood estimation Singular value ratio spectrum

来源：评论

学校读者我要写书评

暂无评论

Fast Recognition of infrared targets Based on CNN

Fast Recognition of Infrared Targets Based on CNN

引用

Electronic Information technology and Computer Engineering (EITCE), International Conference on

作者： Xiaowei Wei Jiahao Deng Sha Xu Zuodong Duan Qiang Fan School of Mechatronical Engineering Beijing Institute of Technology Beijing China

ISBN: (数字)9781728135847

ISBN: (纸本)9781728135854

Deep learning is a problem in the field of infrared target detection. The main reason is that infrared data has less information. Therefore, traditional detection algorithms have lower detection speed and detection accuracy. In this paper, we mainly propose a fast detection algorithm based on YOLOv3. Due to the real-time nature of YOLOv3 needs to be improved, we merged the improved Mobilenetv2 and YOLOv3 to get a new network structure. Experiments on the standard target detection data set show that the network parameters of the new network are only 30% of the original network, and the detection speed is increased by 3 times. At the same time, the mAP is also improved. Through the experiments on the infrared dataset, we get the following test results: the detection speed of the new constructed network structure can reach 11ms/f, and in good weather conditions, mAP can also reach 76%. This indicates that the network structure proposed in this paper can achieve better results in the fast recognition of infrared.

关键词： Feature extraction Convolution Object detection classification algorithms Prediction algorithms Training Real-time systems

来源：评论

学校读者我要写书评

暂无评论

基于生成对抗式神经网络的红外目标仿真方法

引用

光学学报 2019年第3期39卷 150-156页

作者：谢江荣李范鸣卫红李冰中国科学院上海技术物理研究所上海200083 中国科学院大学北京100049 中国科学院红外探测与成像技术重点实验室上海200083

提出了一种应用于红外目标仿真的模型。利用训练后的条件深度卷积生成对抗网络,只需输入随机噪声和类别标签,便能够自动产生预期类别的红外目标仿真图像。在手写数字数据集(MNIST)和红外数据集上分别训练模型参数,再进行自动生成实验,... 详细信息

提出了一种应用于红外目标仿真的模型。利用训练后的条件深度卷积生成对抗网络,只需输入随机噪声和类别标签,便能够自动产生预期类别的红外目标仿真图像。在手写数字数据集(MNIST)和红外数据集上分别训练模型参数,再进行自动生成实验,均可以产生高真实度的样本图像;将判别网络提取的特征用于分类实验,并将所提方法合成的图像用于数据增强,以提升分类器性能。研究结果表明,所提方法能够有效模仿红外辐射特征。

关键词：成像系统红外图像目标仿真深度学习条件深度卷积生成对抗网络

来源：评论

学校读者我要写书评

暂无评论

TBC-Net: A real-time detector for infrared small target detection using semantic constraint

arXiv

引用

arXiv 2019年

作者： Zhao, Mingxin Cheng, Li Yang, Xu Feng, Peng Liu, Liyuan Wu, Nanjian Key Laboratory of Superlattices and Microstructures Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing100049 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing100083 China

infrared small target detection is a key technique in infrared search and tracking (IRST) systems. Although deep learning has been widely used in the vision tasks of visible light images recently, it is rarely used in infrared small target detection due to the difficulty in learning small target features. In this paper, we propose a novel lightweight convolutional neural network TBC-Net for infrared small target detection. The TBCNet consists of a target extraction module (TEM) and a semantic constraint module (SCM), which are used to extract small targets from infrared images and to classify the extracted target images during the training, respectively. Meanwhile, we propose a joint loss function and a training method. The SCM imposes a semantic constraint on TEM by combining the high-level classification task and solve the problem of the difficulty to learn features caused by class imbalance problem. During the training, the targets are extracted from the input image and then be classified by SCM. During the inference, only the TEM is used to detect the small targets. We also propose the data synthesis method to generate the training data. The experimental results show that compared with the traditional methods, TBC-Net can better reduce the false alarm caused by complicated background, the proposed network structure and joint loss have a significant improvement on small target feature learning. Besides, TBC-Net can achieve real-time detection on the NVIDIA Jetson AGX Xavier development board, which is suitable for applications such as field research with drones equipped with infrared sensors. Copyright © 2019, The Authors. All rights reserved.

关键词： infrared imaging

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：