检索结果-南通市图书馆

Feature Enhancement Network for Object Detection in Optical remote Sensing Images

在线全文

学校读者我要写书评

暂无评论

Journal of remote Sensing 2021年第1期2021卷 197-210页

作者： Gong Cheng Chunbo Lang Maoxiong Wu Xingxing Xie Xiwen Yao Junwei Han School of Automation Northwestern Polytechnical UniversityXi’an 710129China

Automatic and robust object detection in remote sensing images is of vital significance in real-world applications such as land resource management and disaster ***,poor performance arises when the state-of-the-art natural image detection algorithms are directly applied to remote sensing images,which largely results from the variations in object scale,aspect ratio,indistinguishable object appearances,and complex background *** this paper,we propose a novel Feature Enhancement Network(FENet)for object detection in optical remote sensing images,which consists of a Dual Attention Feature Enhancement(DAFE)module and a Context Feature Enhancement(CFE)***,the DAFE module is introduced to highlight the network to focus on the distinctive features of the objects of interest and suppress useless ones by jointly recalibrating the spatial and channel feature *** CFE module is designed to capture global context cues and selectively strengthen class-aware features by leveraging image-level contextual information that indicates the presence or absence of the object *** this end,we employ a context encoding loss to regularize the model training which promotes the object detector to understand the scene better and narrows the probable object categories in *** achieve our proposed FENet by unifying DAFE and CFE into the framework of Faster *** the experiments,we evaluate our proposed method on two large-scale remote sensing image object detection datasets including DIOR and DOTA and demonstrate its effectiveness compared with the baseline methods.

关键词： remote image disaster

Basic research in the field of thermal infrared remote sensing

维普期刊数据库评论

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) 2000年第S1期43卷 1-8页

作者：徐冠华 Ministry of Science and Technology PR China Beijing China

This overview paper points out that one of the problems impeding further development of remote sensing is that not much attention has been paid to basic research. Key contents of basic research in remote sensing, including modeling, inversion, scaling and scientific experiments, are reviewed. Significance of basic research is demonstrated through summarizing the intentions and progress of the project "Quantitative remote Sensing Research on Land Surface Energy Exchange".

关键词： basic research TIR remote sensing modeling scaling experiment.

Mapping Tree Species Using Advanced remote Sensing Technologies: A State-of-the-Art Review and Perspective

在线全文

学校读者我要写书评

暂无评论

Journal of remote Sensing 2021年第1期2021卷 211-236页

作者： Ruiliang Pu School of Geosciences University of South Florida4202 E.Fowler Ave.NES 107TampaFL 33620USA

Timely and accurate information on tree species(TS)is crucial for developing strategies for sustainable management and conservation of artificial and natural *** the last four decades,advances in remote sensing technologies have made TS classification *** many studies on the topic have been conducted and their comprehensive results and novel findings have been published in the literature,it is necessary to conduct an updated review on the status,trends,potentials,and challenges and to recommend future *** review will provide an overview on various optical and light detection and ranging(LiDAR)sensors;present and assess current various techniques/methods for,and a general trend of method development in,TS classification;and identify limitations and recommend future *** this review,several concluding remarks were *** include the following:(1)A large group of studies on the topic were using high-resolution satellite,airborne multi-/hyperspectral imagery,and airborne LiDAR data.(2)A trend of“multiple”method development for the topic was observed.(3)Machine learning methods including deep learning models were demonstrated to be significant in improving TS classification accuracy.(4)Recently,unmanned aerial vehicle-(UAV-)based sensors have caught the interest of researchers and practitioners for the topic-related research and *** addition,three future directions were recommended,including refining the three categories of“multiple”methods,developing novel data fusion algorithms or processing chains,and exploring new spectral unmixing algorithms to automatically extract and map TS spectral information from satellite hyperspectral data.

关键词： directions LiDAR remote

remote sensing for energy resources:Introduction

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Geoscience 2022年第2期3卷 134-135页

作者： K.S.Sajinkumar Thomas Oommen Department of Geology University of KeralaThiruvananthapuram695581KeralaIndia Department of Geological and Mining Engineering and Sciences Michigan Technological UniversityHoughtonMI49931USA

Energy resources are critical for human *** energy that we use is obtained from the Earth,its atmosphere,or the *** of these energy resources we obtain from the subsurface through the mining or extraction process,like gas,coal,oil,geothermal,and ***,we also harness from the surface like wind,solar,and *** and geological engineers play a critical role in developing energy resources,maintaining its operation,and evaluating their environmental *** recent years,the advancement in satellite and aerial remote sensing is a tool that is widely used by geoscientists and engineers to address various aspects of energy *** application of remote sensing to energy resources,starting from reconnaissance to detailed studies,utilizing multispectral to hyperspectral and radar to LiDAR techniques,have gained significant *** remote sensing applications include identifying potential source of fuels used in the energy.

关键词： remote utilizing gained

Monitoring earthquake precursor field of NW Yunnan by stress remote sensing

维普期刊数据库评论

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 Earth Sciences 2000年第6期43卷 661-669页

作者：游永雄王荣敏李爱军樊昌尧戎志国 Department of Environment Science China University of Geosciences Beijing 100083 China State Satellite Meteorological Center Beijing 100081 China Computer Center Ministry of Geology and Mineral Resources Beijing 100083 China

The orbit perturbation of meteorologic satellite is used for the inversion of stress drop dynamic field of regional crustal structure. Rapid scanning over vast area is carried out to obtain short term earthquake-generating precursor field of seismic source and near-source districts in order to predict the three earthquake elements: epicenter, magnitude and commencement time of earthquake with the same effect as weather forecast. Taking the strong earthquakes that occurred in recent years in the NW of Yunnan as examples, direct deduction has been made for Lijiang and Wuding earthquakes, and curves of dynamic characteristics of stress drop before and after earthquakes as well as abnormal fluctuations of precursor stress drop and commencement time of earthquake have been plotted.

关键词： stress remote sensing monitoring over the earthquake precursor field tectonic stress field area of Lijiang and Wuding of NW Yunnan.

MICROWAVE remote SENSING OF ATMOSPHERIC PROPERTY AND WEATHER PROCESS

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 1991年第3期34卷 352-362页

作者：赵柏林傅强杜金林胡成达李慧心 Department of Geophysics Peking University

In this paper, the principle and test of remote sensing of atmospheric property and weatherprocess with 5mm (52.9Ghz, 54.5GHz), 1.35cm (22.235GHz) and 8mm (35,3 GHz) radio-meters are described. The assessment of the ability of remote sensing of atmospheric tem-perature, humidity, liquid water content of clond in all weather (except rain) has been *** efficiency of remote sensing of the atmospheric sounding has been proved by the fieldexperiment. The field experiment results show that it could meet the need of atmosphericsounding in clear and cloudy weather. To monitor the weather, such as the change of airmass, the process of precipitation and the disturbance of microscale and mesoscale weather, thesignal reveals itself significantly in the atmospheric microwave radiation. The effect couldbe used in the nowcasting and artificial precipitation area.

关键词： remote sensing of atmosphere atmospheric microwave radiation

Bi-criteria Optimal Fault-Tolerable Control for SY-II remote Operated Vehicle

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2013年第5期18卷 542-548页

作者：姜述强金鸿章魏凤梅 College of Automation Harbin Engineering University College of Computer Science and Technology Harbin Engineering University School of Technology Harbin University

This paper proposed a bi-criteria weighting approach for fault tolerant control(FTC)of SY-II remote operated vehicle(ROV).This approach integrates the minimum kinetic energy(2-norm optimal)approach with the infinity-norm approach through a weighting coefcient,on the basis of SY-II ROV force allocation *** the realization of fault tolerable control,this approach converts a quadratic programming problem into primaldual neural *** the motion control simulations and experiments,bi-criteria optimization approach outperforms minimum kinetic energy optimization in FTC,SY-II ROV can realize 2-degree of freedom(DOF)horizontal fault tolerant control with one main thruster and any of horizontal ***,this scheme is proved to be of superiority and computational efciency,both the reliability and safety for ROV have been improved.

关键词： remote operated vehicle(ROV) bi-criteria control quadratic programming fault tolerance control(FTC)

Improved Region Merging Algorithm for remote Sensing Images

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2020年第1期29卷 72-79页

作者： Zhuo Wu Xiaohua Wang Yongwen Shen Yueting Shi School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China

To segment high-resolution remote sensing images(RSIs)accurately on an object level and meet the precise boundary dividing requirement,an improved superpixel segmentation and region merging algorithm is *** linear iterative clustering(SLIC)is widely used because of its advantages in performance and effect;however,it causes over-segmentation,which is very disadvantageous to information *** this proposed method,SLIC is firstly adopted for initial superpixel *** second stage follows the iterative merging procedure,which uses a hierarchical clustering algorithm and introduces a local binary pattern(LBP)texture feature operator during the process of *** experimental results indicate that the proposed method achieved a good segmentation and region merging performance,and worked effectively on cloud detection preprocessing in high-resolution RSIs with cloud and snow overlap situations.

关键词： superpixel remote sensing image region merging hierarchical clustering

Rainfall retrieval over land from satellite remote sensing (SSM/I)

在线全文

学校读者我要写书评

暂无评论

Chinese Science Bulletin 1998年第22期43卷 1913-1917页

作者： Li Li Yuanjing Zhu Bolin Zhao Peking Univ State Key Lab Severe Storm Res Dept Geophys Beijing 100871 Peoples R China

Composite microwave index (CMI) method is used with the satellite SSM/I data to retrieve summer rainfall rate over 96°E-127°E, 17°N-44°N. The results of verification are : the root_of_mean_square error is 0.9 mm/h in the actual rain rate range from 2 to 2.9 mm/h; 1.6 mm/h in that from 3 to 5 mm/h and the maximum rms error is 4.2 mm/h in that from 5.1 to 50 mm/h. Case study shows the decision tree and CMI method presented in the note are effective to the rainfall recognition and rain rate retrieval over land of East China.

关键词： satellite microwave remote sensing rainfall retrieval over land.